Podcasts about Airflow

This was a fun discussion! Back in the tangent cube at last, we cover some of the highlights of our long trip through Egypt and Turkey, from Cappadocia and Derenkuyu to Gobekli Tepe and Karahan Tepe, the Pyramids and the Osirieon, ancient tools and lost vaults of knowledge. We talk about the mythology connected with the structures, and focus a lot of time on the Osiris Myth. Thank you all for your patience as we travel, and your continued support! We are going to Peru in October of 2025!! Sign up now and join us, Ben from UnchartedX, and Yousef Aywan from the Khemet School on an epic journey through the highlands of Peru: https://unchartedx.com/2025peru2/ Join us, Ben from UnchartedX, Adam Young, and Karoly Poka for an afternoon at The Metropolitan Museum of Art in New York where we will peruse their collection of Ancient Egyptian artifacts, then we will move to the Explorer's Club for dinner and presentations from us and Ben! https://eveningattheexplorersclub.eventbrite.com/   Join our Patreon, support the show, get extra content and early access! https://www.patreon.com/brothersoftheserpent Support the show with a paypal donation: https://paypal.me/snakebros   Chapters 00:00 Welcome Back and Reflections on the Journey 02:53 Exploring Cappadocia's Underground Cities 05:42 The Role of Special Permissions in Archaeology 08:51 Airflow and Structural Integrity of Ancient Tunnels 11:39 Connections to Ancient Myths and Stories 14:45 The Evolution of Gobekli Tepe's Structures 22:02 Symbolism of the Lion's Gate and Sphinxes 26:52 Samson, Gilgamesh, and the Cycle of Civilizations 33:35 The Significance of Hair and Statues in Ancient Egypt 45:36 Exploring Ancient Symbolism and Mythology 47:06 The Osiris Myth: Variations and Interpretations 49:40 Experiencing the Osirian: Personal Reflections 51:32 Architectural Insights: The Construction Techniques of Ancient Egypt 54:38 Theories on Ancient Tools and Techniques 57:41 The Connection Between the Temple and the Osirieon 01:00:21 Excavation Insights: The History of the Osirieon 01:02:56 The Alignment and Purpose of Ancient Structures 01:06:26 The Osiris Myth: A Foundation of Civilization 01:25:06 The Evolution of Myths and Civilizations 01:27:15 The Eye of Horus and Lunar Symbolism 01:29:26 The Sabians: Pilgrims of Knowledge 01:31:46 Hermeticism and Ancient Astronomers 01:35:08 Exploring Gobekli Tepe and Its Mysteries 01:39:02 Lithics and Their Connection to Ancient Cultures 01:42:57 Contrasting Technologies: Lithics vs. Megaliths 01:48:22 The Evolution of Craftsmanship in Ancient Civilizations 02:01:17 Midden Accumulation and Cultural Practices 02:05:48 Future Discoveries in Neolithic Archaeology

In this engaging session, David Richardson breaks down the concept of high-performance HVAC, offering a clear roadmap for industry professionals looking to elevate their craft. Richardson argues that the HVAC industry has long been focused on equipment rather than complete systems, leading to widespread inefficiencies. The average system delivers only about 57% of its rated capacity into buildings, while even code-approved systems barely reach 63%. By implementing high-performance HVAC principles, contractors can achieve up to 88% efficiency while improving safety, health, comfort, and energy performance. Richardson presents a practical framework using the acronym "PATH" - Pressure, Airflow, Temperature, and Heat (BTUs) - as a step-by-step approach to implementing high-performance HVAC. He emphasizes starting with static pressure testing, which he calls "the foundation of airflow" and one of the most misunderstood principles in the industry. Just as doctors check blood pressure as a vital sign during every visit, Richardson advocates for measuring static pressure on every call, or at minimum, when encountering "red flag" issues like repeated equipment failures. From there, professionals can progress to measuring airflow, temperature, and finally BTU delivery to create complete system diagnostics. The presentation offers a journey-based approach, acknowledging that implementation takes time and requires breaking old habits. Richardson introduces the "one degree principle," suggesting that change happens incrementally, with small improvements eventually leading to breakthrough moments. He urges contractors to apply this methodology not just to equipment, but to extend testing into duct systems and even the building envelope. By making these changes visible through measurement, contractors can prove value to themselves, their teams, and ultimately their customers, transforming the way HVAC work is perceived and delivered. Key Topics Covered: The definition of high-performance HVAC: getting back to craftsmanship, challenging the status quo, and confirming work through measurement The industry problem: focusing on equipment instead of complete systems, resulting in just 57% of rated BTU capacity reaching conditioned spaces The PATH framework: Pressure, Airflow, Temperature, and Heat as building blocks for system diagnostics How to implement static pressure testing as the foundation for airflow diagnostics The importance of measuring at both equipment and register/grille locations Breaking down implementation into three areas: equipment, ducts, and building envelope STEPS approach: Show, Teach, Equip, Promote, with application to yourself, your team, and your customers The "one degree principle" for making incremental changes that lead to breakthrough results Common obstacles to implementation and how to overcome resistance to change How measurements make your work transparent and lead to better performance   Have a question that you want us to answer on the podcast? Submit your questions at https://www.speakpipe.com/hvacschool. Purchase your tickets or learn more about the 6th Annual HVACR Training Symposium at https://hvacrschool.com/symposium. Subscribe to our podcast on your iPhone or Android. Subscribe to our YouTube channel. Check out our handy calculators here or on the HVAC School Mobile App for Apple and Android

In this podcast episode, HVAC professionals Chris Hughes and Adam Mufich discuss the intricate challenges technicians face when commissioning modern inverter-based heating and cooling systems. Unlike traditional single-stage or two-stage HVAC equipment, inverter systems introduce a new level of complexity that can leave even experienced technicians feeling uncertain about proper installation and startup procedures. The presentation highlights a fundamental shift in how HVAC systems operate, moving from straightforward single-stage systems to sophisticated inverter-based technologies that modulate compressor, fan, and refrigerant flow dynamically. This technological evolution creates significant challenges for technicians, who previously could rely on simple, consistent commissioning processes. The speakers emphasize that modern inverter systems require a much more nuanced approach, with specific temperature ranges, wait times, and verification methods that are not always clearly documented in manufacturer manuals. Recognizing the industry-wide need for clarity, Chris and Adam have developed a comprehensive spreadsheet resource that consolidates commissioning information across multiple HVAC brands. Their goal is to empower technicians by providing accessible, standardized guidance for working with these complex systems. By sharing their research and encouraging collaboration, they aim to address what they see as a critical gap in manufacturer support and technical documentation. The podcast serves as both an educational resource and a call to action for HVAC professionals and manufacturers alike. Chris and Adam argue that the industry needs more transparency, better documentation, and a collective effort to standardize inverter system commissioning practices. Their work represents a significant step towards demystifying these advanced HVAC technologies and ensuring that technicians can confidently and effectively install and service modern heating and cooling equipment. Key Topics Covered: Differences between single-stage, two-stage, and inverter HVAC systems Commissioning challenges with modern inverter technologies Critical factors in proper system startup, including: Outdoor and indoor temperature requirements Wait times for system stabilization Refrigerant charging methods Airflow measurement and verification The importance of precise refrigerant charging (superheat and subcooling) Challenges with manufacturer documentation and technical support The need for standardized commissioning procedures across HVAC brands Strategies for verifying system performance during commissioning The speakers' collaborative effort to create a comprehensive inverter system commissioning guide   Have a question that you want us to answer on the podcast? Submit your questions at https://www.speakpipe.com/hvacschool. Purchase your tickets or learn more about the 6th Annual HVACR Training Symposium at https://hvacrschool.com/symposium. Subscribe to our podcast on your iPhone or Android. Subscribe to our YouTube channel. Check out our handy calculators here or on the HVAC School Mobile App for Apple and Android

Thibault Lefèvre est Global Data & AI Product Manager sur le périmètre Manufacturing et Supply chez Sanofi, le groupe pharmaceutique leader mondial. Il nous parle des 3 piliers de leur stratégie Data et IA.On aborde :

This podcast contains a handful of visuals that we thought would be helpful, so we've published a video version of this podcast at https://youtu.be/NZ2qp06oET8. The Testo 605i that Mark mentioned can be found at https://amzn.to/41TYFjsTo find the chart that Mark referenced, go to https://efficientcomfort.net/charts/. Check this link to IEB Unite: https://events.iebcoaching.com/IEBUnite2025You can find Mark at https://besttampainspector.com.Reuben Saltzman, Tessa Murry, and Mark Cramer delve into the intricacies of air conditioning testing, focusing on how home inspectors can improve their methods. They discuss the importance of understanding temperature splits, the role of humidity, and the need for advanced measurement techniques. Mark emphasizes the limitations of basic thermometers and advocates for more accurate tools to assess air conditioning performance. The discussion also covers real-world examples, practical applications, and the significance of airflow in HVAC systems. In this conversation, the speakers delve into the intricacies of HVAC measurement techniques, focusing on the use of advanced tools like the Measure Quick app. They discuss the importance of accurate temperature readings, the role of humidity in system performance, and the shift toward non-invasive testing methods. The conversation highlights the challenges faced by HVAC professionals in adapting to new technologies and the implications of energy efficiency on system performance.TakeawaysAir conditioning is crucial for comfort, especially in humid climates.Home inspectors often rely on basic thermometers, which may not provide accurate readings.Temperature splits in air conditioning can vary significantly based on humidity levels.Understanding latent heat is essential for accurate air conditioning assessments.Advanced measurement tools can provide more precise data than traditional methods.Humidity plays a critical role in determining the effectiveness of air conditioning systems.Real-world examples illustrate the importance of proper testing techniques.Airflow issues are a common problem in HVAC systems that can affect performance.Using technology like hygrometers can enhance the accuracy of air conditioning evaluations.The ideal temperature split for air conditioning systems typically falls between 18-20 degrees. Using two probes allows for the simultaneous measurement of return and supply air.The Measure Quick app simplifies the process of HVAC measurements.Accurate temperature readings are crucial for assessing system performance.Non-invasive methods are becoming the preferred approach in HVAC inspections.Humidity levels significantly impact the efficiency of air conditioning systems.High-efficiency systems may struggle with humidity control despite their performance.Understanding airflow and duct conditions is essential for accurate HVAC assessments.Investing in advanced measurement tools can enhance inspection accuracy.The HVAC industry is gradually shifting away from traditional gauge methods.Education and resources are vital for HVAC professionals to stay updated. Chapters00:00 Introduction to Air Conditioning Testing09:14 Advanced Measurement Techniques for Air Conditioning18:01 Understanding Temperature Differential and Humidity31:31 Understanding Measurement Techniques in HVAC Systems43:12 Cost and Accessibility of HVAC Measurement Tools48:13 Key Factors Affecting HVAC Performance56:18 Resources for Further Learning in HVAC

In this episode of the HVAC Know It All Podcast, host Gary McCreadie continues his conversation with Tim De Stasio, the owner and president of Comfort Science Solutions. In Part 2, he takes a closer look at the issues in HVAC caused by profit-focused decisions instead of customer care. He also discusses how company culture and investor pressure can affect service quality and ethical standards in the industry. Tim explains here in the part how some technicians are pressured to sell rather than fix real customer problems. He points out how this approach harms both the industry and customers in the long run. Tim emphasizes the need to focus on quality service instead of quick profits to create a more honest and sustainable business. Tim highlights the need to move away from profit-driven sales tactics in HVAC. He advocates for a culture that values technical skills and real problem-solving. He explores how ethical business practices can improve service quality and strengthen a company's reputation. Expect to Learn: How company culture influences HVAC technicians' approach to sales and service. The impact of venture capital on ethical practices within HVAC companies. Strategies for HVAC companies to adopt more ethical sales practices. The role of technician training in promoting problem-solving over sales-first approaches. How the industry can shift towards more sustainable and customer-focused practices. Episode Highlights: [00:33] – Introduction to the Second Part of the Episode with Tim De Stasio [02:19] – Transitioning from Comfort Advisors to Sales Technicians [05:24] – Analysis of venture capital's role in shaping company culture and ethical dilemmas [11:46] – Exploring the balance between making profits and providing ethical HVAC services [18:00] – Tim's take on the real-world impacts of prioritizing sales over service [21:22] – Promoting Ethical Training and Diagnostics in HVAC This Episode is Kindly Sponsored by: Master: https://www.master.ca/ Cintas: https://www.cintas.com/ Supply House: https://www.supplyhouse.com/ Cool Air Products: https://www.coolairproducts.net/ Lambert Insurance Services: https://www.lambert-ins.com/ Follow the Guest Tim De Stasio on: LinkedIn: https://www.linkedin.com/in/tim-de-stasio-0618824a/ Facebook: https://www.facebook.com/timothy.destasio Instagram: https://www.instagram.com/timdestasiohvac/ YouTube: https://www.youtube.com/@timdestasiohvac Comfort Science LP: https://www.instagram.com/comfortsciencehvac/ Follow the Host: LinkedIn: https://www.linkedin.com/in/gary-mccreadie-38217a77/ Website: https://www.hvacknowitall.com Facebook: https://www.facebook.com/people/HVAC-Know-It-All-2/61569643061429/ Instagram: https://www.instagram.com/hvacknowitall1/

Доклады: Goodbye GIL: Exploring the Free-threaded mode in Python 3.13 - Adarsh Divakaran (https://youtu.be/7NvgI3jDprg) Unlocking Concurrency and Performance in Python with ASGI and Async I/O - Allen Y, M Aswin Kishore (https://youtu.be/s5UGRvdrb_Q) Quantifying Nebraska - Adam Harvey (https://youtu.be/vH9xOxryqW8) Error Culture - Ryan Cheley (https://youtu.be/FBMg2Bp4I-Q) Mono-repositories in Python - Avik Basu (https://youtu.be/VIlcodf9Wrg) You Should Build a Robot (MicroPython) (https://youtu.be/UygK5W3txTM) As easy as breathing: manage your workflows with Airflow! - Madison Swain-Bowden (https://youtu.be/dWZSVY79-SM) Optimal Performance Over Basic as a Perfectionist with Deadlines - Velda Kiara (https://youtu.be/dvxzJDk6x9Q) Нас можно найти: 1. Telegram: https://t.me/proConf 2. Youtube: https://www.youtube.com/c/proconf 3. SoundCloud: https://soundcloud.com/proconf 4. Itunes: https://podcasts.apple.com/by/podcast/podcast-proconf/id1455023466 5. Spotify: https://open.spotify.com/show/77BSWwGavfnMKGIg5TDnLz

Join me, Tony Mormino, as I delve into the groundbreaking world of airflow control technology at Antec Controls. In this episode, I'm at the AHR Expo in Orlando, sharing insights from my experience at the Antec booth. Curtis, an expert from Antec, joins me to discuss how their advanced control valves are transforming critical healthcare spaces. We'll explore why these systems are vital for maintaining sterility and safety, from isolation rooms to clean labs, and how they differ significantly from traditional VAV boxes. If you're interested in the intersection of HVAC technology and healthcare safety, this episode will equip you with the knowledge of cutting-edge solutions that ensure cleaner, safer environments where health and wellness advancements are made. Tune in to discover how precise airflow control can make a significant difference in protecting both patients and healthcare workers.

In this episode of HVAC Know It All Podcast, host Gary McCreadie welcomes Dr. Mark Modera, The Inventor of Aeroseal, Professor at the University of California, Davis, and Visiting Faculty at Berkeley Lab and Former Vice President at Carrier HVAC. They talk about why sealing ducts is important for HVAC performance, how new methods like Aeroseal, the invention of Dr. Mark Modera, is better than old ones, and why fixing duct leaks saves energy and improves comfort. Dr. Mark Modera also explains the science behind duct leaks, how they affect system performance, and how modern sealing technology makes the job easier. This discussion gives HVAC professionals useful tips on improving airflow, making homes more effective, and using better duct sealing methods.Dr. Mark Modera talks about the problems caused by duct leaks in HVAC systems and why old sealing methods don't work as well as new solutions like Aeroseal. He explains why it's important to check and measure duct leaks, the need for ongoing learning in building science, and how technology is making duct sealing better for improved system performance. They also discuss how clear communication, better diagnostics, and advanced sealing techniques can help HVAC professionals improve performance and reduce energy waste.This episode is packed with practical HVAC tips, industry challenges, and real solutions to help technicians learn about duct leaks, boost system performance, and use better sealing methods for improved performance.Expect to Learn:Why duct leakage is a major issue and how it impacts HVAC system performance.The limitations of traditional duct sealing methods and the benefits of Aeroseal.How verifying and measuring duct leakage can improve energy efficiency.Common misconceptions about duct sealing and their impact on home comfort.How modern technology is transforming the way HVAC professionals approach duct sealing.Episode Highlights: [00:00] – Introduction to Dr. Mark Modera[01:30] – Understanding Aeroseal: How It Works & How It Differs from Air Barrier Sealing[03:46] – The Impact of Duct Leakage on Energy Bills, Airflow & Home Comfort [07:24] – The Invention of Aeroseal: Dr. Mark Modera's Breakthrough & Impact on Duct Sealing & Energy Savings  [11:12] – The Evolution of Heat Pump Technology & the Need for Better Duct Sealing Solutions [14:11] – How Aeroseal Was Developed & Its Impact on Basement Duct Leakage and Air Distribution  [15:56] – Why Aeroseal is a Game-Changer for Hard-to-Reach Duct Leaks  [18:01] – How Long Does Aeroseal Take? Setup, Application & Real-Time Leakage MonitoringThis Episode is Kindly Sponsored by:Master: https://www.master.ca/ Cintas: https://www.cintas.com/ Supply House: https://www.supplyhouse.com/ Cool Air Products: https://www.coolairproducts.net/ Lambert Insurance Services: https://www.lambert-ins.com/ Follow the Guest Dr. Mark Modera on: LinkedIn: https://www.linkedin.com/in/mark-modera-94432212/ Aeroseal: https://www.linkedin.com/company/aeroseal-llc/about/ University of California: https://www.linkedin.com/school/uc-davis/ Berkeley Lab: https://www.linkedin.com/company/lawrence-berkeley-national-laboratory/ Carrier HVAC: https://www.linkedin.com/company/carrierhvac/ Website: Aeroseal: https://aeroseal.com/ Carrier HVAC: https://www.carrier.com/carrier/en/worldwide/   Follow the Host:LinkedIn: https://www.linkedin.com/in/gary-mccreadie-38217a77/ Website: https://www.hvacknowitall.com Facebook: https://www.facebook.com/people/HVAC-Know-It-All-2/61569643061429/  Instagram: https://www.instagram.com/hvacknowitall1/ 

In this podcast episode, we talked with Adrian Brudaru about ​the past, present and future of data engineering.About the speaker:Adrian Brudaru studied economics in Romania but soon got bored with how creative the industry was, and chose to go instead for the more factual side. He ended up in Berlin at the age of 25 and started a role as a business analyst. At the age of 30, he had enough of startups and decided to join a corporation, but quickly found out that it did not provide the challenge he wanted.As going back to startups was not a desirable option either, he decided to postpone his decision by taking freelance work and has never looked back since. Five years later, he co-founded a company in the data space to try new things. This company is also looking to release open source tools to help democratize data engineering.0:00 Introduction to DataTalks.Club1:05 Discussing trends in data engineering with Adrian2:03 Adrian's background and journey into data engineering5:04 Growth and updates on Adrian's company, DLT Hub9:05 Challenges and specialization in data engineering today13:00 Opportunities for data engineers entering the field15:00 The "Modern Data Stack" and its evolution17:25 Emerging trends: AI integration and Iceberg technology27:40 DuckDB and the emergence of portable, cost-effective data stacks32:14 The rise and impact of dbt in data engineering34:08 Alternatives to dbt: SQLMesh and others35:25 Workflow orchestration tools: Airflow, Dagster, Prefect, and GitHub Actions37:20 Audience questions: Career focus in data roles and AI engineering overlaps39:00 The role of semantics in data and AI workflows41:11 Focusing on learning concepts over tools when entering the field 45:15 Transitioning from backend to data engineering: challenges and opportunities 47:48 Current state of the data engineering job market in Europe and beyond 49:05 Introduction to Apache Iceberg, Delta, and Hudi file formats 50:40 Suitability of these formats for batch and streaming workloads 52:29 Tools for streaming: Kafka, SQS, and related trends 58:07 Building AI agents and enabling intelligent data applications 59:09Closing discussion on the place of tools like DBT in the ecosystem

Claude Plays Pokémon - A Conversation with the Creator // MLOps Podcast #294 with Alexa Griffith, Senior Software Engineer at Bloomberg.Join the Community: https://go.mlops.community/YTJoinIn Get the newsletter: https://go.mlops.community/YTNewsletter // AbstractAlexa shares her journey into software engineering, from early struggles with Airflow and Kubernetes to leading open-source projects like the Envoy AI Gateway. She and Demetrios discuss AI model deployment, tooling differences across tech roles, and the importance of abstraction. They highlight aligning technical work with business goals and improving cross-team communication, offering key insights into MLOps and AI infrastructure.// BioAlexa Griffith is a Senior Software Engineer at Bloomberg, where she builds scalable inference platforms for machine learning workflows and contributes to open-source projects like KServe. She began her career at Bluecore working in data science infrastructure, and holds an honors degree in Chemistry from the University of Tennessee, Knoxville. She shares her insights through her podcast, Alexa's Input (AI), technical blogs, and active engagement with the tech community at conferences and meetups.// Related LinksWebsite: https://alexagriffith.com/Kubecon Keynote about Envoy AI Gateway https://www.youtube.com/watch?v=do1viOk8nok~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExploreJoin our slack community [https://go.mlops.community/slack]Follow us on X/Twitter [@mlopscommunity][https://x.com/mlopscommunity] or LinkedIn [https://go.mlops.community/linkedin] Sign up for the next meetup: [https://go.mlops.community/register]MLOps Swag/Merch: [https://shop.mlops.community/]Connect with Demetrios on LinkedIn: /dpbrinkmConnect with Alexa on LinkedIn: /alexa-griffith

In this episode of the Aging Well Podcast, Dr. Jeff Armstrong and Corbin Bruton explore the trending topic of mouth taping and its efficacy in managing obstructive sleep apnea. They discuss recent research findings from Brigham and Women's Hospital and Harvard Medical School, revealing that mouth taping might worsen the condition for some individuals. The conversation underscores the complexity of managing sleep apnea, emphasizing personalized approaches and professional medical advice. Corbin shares his personal journey with sleep apnea and the benefits of using a CPAP machine while highlighting lifestyle changes that can improve sleep quality. This episode serves as a critical guide for those dealing with sleep apnea or considering viral trends for sleep solutions.https://www.medpagetoday.com/pulmonology/sleepdisorders/112246?xid=nl_mpt_DHE_2024-10-03&mh=b4bce701259919425f7ab5e844f1878e&utm_source=Sailthru&utm_medium=email&utm_campaign=Daily%20Headlines%20Evening%202024-10-03&utm_term=NL_Daily_DHE_dual-gmail-definiMouth Closure and Airflow in Patients With Obstructive Sleep Apnea: A Nonrandomized Clinical Trial Should Mouth Taping and Obstructive Sleep Apnea Therapies Be Regulated?

In this episode of theHVAC Know It All Podcast, Host Gary McCreadie sits down with Adam Mufich, an Expert in airflow diagnostics and technical trainer at theNational Comfort Institute (NCI). They will discuss deep into the critical role of airflow in HVAC systems, why static pressure doesn't equal airflow, and how technicians can improve system performance with better diagnostics.Adam shares insights on the TrueFlow Grid, a Revolutionary tool for measuring airflow accurately, and explains how it integrates with MeasureQuick and NCI workflows to help technicians troubleshoot and optimize HVAC systems more efficiently. They also discuss common airflow mistakes, the importance of proper system sizing, and the impact of filter selection on performance.Expect to Learn:1. Why airflow is the backbone of HVAC system performance.2. How the TrueFlow Grid simplifies airflow measurement.3. The difference between static pressure and airflow and why it matters.4. How improper system sizing leads to airflow issues.5. Why deeper pleated filters outperform one-inch filters.Episode Highlights:[00:33] – Introduction to the Episode with Adam Mufich[02:23] – How Important Is Airflow? Adam Explains Why it's a 10/10[03:35] – Right Way to Sell HVAC Services: Solution-Based Selling & the Role of Airflow Measurement.[06:19] – The TrueFlow Grid: Accurate Airflow Measurement Beyond Ductwork Limitations.[10:56] – Static Pressure vs. Airflow Understanding the key differences[13:29] – TrueFlow Grid & NCI: Optimizing Airflow with Fan Law 2.[21:28] – Undersized Ducts or Oversized Equipment? The Key to Proper Airflow.[26:03] – The Deep Pleat Filter Advantage, More surface area = better airflow[29:25] – Can Better Filtration Reduce White Slime?[31:45] – UV Lights, Drain Pans & Biofilm, Do UV lights really help?[33:38] – Final Thoughts: How to Improve Your Airflow Game.This Episode is Kindly Sponsored by:Master:https://www.master.ca/Cintas:https://www.cintas.com/Supply House:https://www.supplyhouse.comCool Air Products:https://www.coolairproducts.netLambert Insurance Services:https://www.lambert-ins.com Follow the Adam Mufich on:LinkedIn:https://www.linkedin.com/in/adam-mufich-5225055a/National Comfort Institute:https://www.linkedin.com/company/national-comfort-institute/ Master HVAC diagnostics with Measure Quick & True Flow Grid!

Did you know that adding a simple Code Interpreter took o3 from 9.2% to 32% on FrontierMath? The Latent Space crew is hosting a hack night Feb 11th in San Francisco focused on CodeGen use cases, co-hosted with E2B and Edge AGI; watch E2B's new workshop and RSVP here!We're happy to announce that today's guest Samuel Colvin will be teaching his very first Pydantic AI workshop at the newly announced AI Engineer NYC Workshops day on Feb 22! 25 tickets left.If you're a Python developer, it's very likely that you've heard of Pydantic. Every month, it's downloaded >300,000,000 times, making it one of the top 25 PyPi packages. OpenAI uses it in its SDK for structured outputs, it's at the core of FastAPI, and if you've followed our AI Engineer Summit conference, Jason Liu of Instructor has given two great talks about it: “Pydantic is all you need” and “Pydantic is STILL all you need”. Now, Samuel Colvin has raised $17M from Sequoia to turn Pydantic from an open source project to a full stack AI engineer platform with Logfire, their observability platform, and PydanticAI, their new agent framework.Logfire: bringing OTEL to AIOpenTelemetry recently merged Semantic Conventions for LLM workloads which provides standard definitions to track performance like gen_ai.server.time_per_output_token. In Sam's view at least 80% of new apps being built today have some sort of LLM usage in them, and just like web observability platform got replaced by cloud-first ones in the 2010s, Logfire wants to do the same for AI-first apps. If you're interested in the technical details, Logfire migrated away from Clickhouse to Datafusion for their backend. We spent some time on the importance of picking open source tools you understand and that you can actually contribute to upstream, rather than the more popular ones; listen in ~43:19 for that part.Agents are the killer app for graphsPydantic AI is their attempt at taking a lot of the learnings that LangChain and the other early LLM frameworks had, and putting Python best practices into it. At an API level, it's very similar to the other libraries: you can call LLMs, create agents, do function calling, do evals, etc.They define an “Agent” as a container with a system prompt, tools, structured result, and an LLM. Under the hood, each Agent is now a graph of function calls that can orchestrate multi-step LLM interactions. You can start simple, then move toward fully dynamic graph-based control flow if needed.“We were compelled enough by graphs once we got them right that our agent implementation [...] is now actually a graph under the hood.”Why Graphs?* More natural for complex or multi-step AI workflows.* Easy to visualize and debug with mermaid diagrams.* Potential for distributed runs, or “waiting days” between steps in certain flows.In parallel, you see folks like Emil Eifrem of Neo4j talk about GraphRAG as another place where graphs fit really well in the AI stack, so it might be time for more people to take them seriously.Full Video EpisodeLike and subscribe!Chapters* 00:00:00 Introductions* 00:00:24 Origins of Pydantic* 00:05:28 Pydantic's AI moment * 00:08:05 Why build a new agents framework?* 00:10:17 Overview of Pydantic AI* 00:12:33 Becoming a believer in graphs* 00:24:02 God Model vs Compound AI Systems* 00:28:13 Why not build an LLM gateway?* 00:31:39 Programmatic testing vs live evals* 00:35:51 Using OpenTelemetry for AI traces* 00:43:19 Why they don't use Clickhouse* 00:48:34 Competing in the observability space* 00:50:41 Licensing decisions for Pydantic and LogFire* 00:51:48 Building Pydantic.run* 00:55:24 Marimo and the future of Jupyter notebooks* 00:57:44 London's AI sceneShow Notes* Sam Colvin* Pydantic* Pydantic AI* Logfire* Pydantic.run* Zod* E2B* Arize* Langsmith* Marimo* Prefect* GLA (Google Generative Language API)* OpenTelemetry* Jason Liu* Sebastian Ramirez* Bogomil Balkansky* Hood Chatham* Jeremy Howard* Andrew LambTranscriptAlessio [00:00:03]: Hey, everyone. Welcome to the Latent Space podcast. This is Alessio, partner and CTO at Decibel Partners, and I'm joined by my co-host Swyx, founder of Smol AI.Swyx [00:00:12]: Good morning. And today we're very excited to have Sam Colvin join us from Pydantic AI. Welcome. Sam, I heard that Pydantic is all we need. Is that true?Samuel [00:00:24]: I would say you might need Pydantic AI and Logfire as well, but it gets you a long way, that's for sure.Swyx [00:00:29]: Pydantic almost basically needs no introduction. It's almost 300 million downloads in December. And obviously, in the previous podcasts and discussions we've had with Jason Liu, he's been a big fan and promoter of Pydantic and AI.Samuel [00:00:45]: Yeah, it's weird because obviously I didn't create Pydantic originally for uses in AI, it predates LLMs. But it's like we've been lucky that it's been picked up by that community and used so widely.Swyx [00:00:58]: Actually, maybe we'll hear it. Right from you, what is Pydantic and maybe a little bit of the origin story?Samuel [00:01:04]: The best name for it, which is not quite right, is a validation library. And we get some tension around that name because it doesn't just do validation, it will do coercion by default. We now have strict mode, so you can disable that coercion. But by default, if you say you want an integer field and you get in a string of 1, 2, 3, it will convert it to 123 and a bunch of other sensible conversions. And as you can imagine, the semantics around it. Exactly when you convert and when you don't, it's complicated, but because of that, it's more than just validation. Back in 2017, when I first started it, the different thing it was doing was using type hints to define your schema. That was controversial at the time. It was genuinely disapproved of by some people. I think the success of Pydantic and libraries like FastAPI that build on top of it means that today that's no longer controversial in Python. And indeed, lots of other people have copied that route, but yeah, it's a data validation library. It uses type hints for the for the most part and obviously does all the other stuff you want, like serialization on top of that. But yeah, that's the core.Alessio [00:02:06]: Do you have any fun stories on how JSON schemas ended up being kind of like the structure output standard for LLMs? And were you involved in any of these discussions? Because I know OpenAI was, you know, one of the early adopters. So did they reach out to you? Was there kind of like a structure output console in open source that people were talking about or was it just a random?Samuel [00:02:26]: No, very much not. So I originally. Didn't implement JSON schema inside Pydantic and then Sebastian, Sebastian Ramirez, FastAPI came along and like the first I ever heard of him was over a weekend. I got like 50 emails from him or 50 like emails as he was committing to Pydantic, adding JSON schema long pre version one. So the reason it was added was for OpenAPI, which is obviously closely akin to JSON schema. And then, yeah, I don't know why it was JSON that got picked up and used by OpenAI. It was obviously very convenient for us. That's because it meant that not only can you do the validation, but because Pydantic will generate you the JSON schema, it will it kind of can be one source of source of truth for structured outputs and tools.Swyx [00:03:09]: Before we dive in further on the on the AI side of things, something I'm mildly curious about, obviously, there's Zod in JavaScript land. Every now and then there is a new sort of in vogue validation library that that takes over for quite a few years and then maybe like some something else comes along. Is Pydantic? Is it done like the core Pydantic?Samuel [00:03:30]: I've just come off a call where we were redesigning some of the internal bits. There will be a v3 at some point, which will not break people's code half as much as v2 as in v2 was the was the massive rewrite into Rust, but also fixing all the stuff that was broken back from like version zero point something that we didn't fix in v1 because it was a side project. We have plans to move some of the basically store the data in Rust types after validation. Not completely. So we're still working to design the Pythonic version of it, in order for it to be able to convert into Python types. So then if you were doing like validation and then serialization, you would never have to go via a Python type we reckon that can give us somewhere between three and five times another three to five times speed up. That's probably the biggest thing. Also, like changing how easy it is to basically extend Pydantic and define how particular types, like for example, NumPy arrays are validated and serialized. But there's also stuff going on. And for example, Jitter, the JSON library in Rust that does the JSON parsing, has SIMD implementation at the moment only for AMD64. So we can add that. We need to go and add SIMD for other instruction sets. So there's a bunch more we can do on performance. I don't think we're going to go and revolutionize Pydantic, but it's going to continue to get faster, continue, hopefully, to allow people to do more advanced things. We might add a binary format like CBOR for serialization for when you'll just want to put the data into a database and probably load it again from Pydantic. So there are some things that will come along, but for the most part, it should just get faster and cleaner.Alessio [00:05:04]: From a focus perspective, I guess, as a founder too, how did you think about the AI interest rising? And then how do you kind of prioritize, okay, this is worth going into more, and we'll talk about Pydantic AI and all of that. What was maybe your early experience with LLAMP, and when did you figure out, okay, this is something we should take seriously and focus more resources on it?Samuel [00:05:28]: I'll answer that, but I'll answer what I think is a kind of parallel question, which is Pydantic's weird, because Pydantic existed, obviously, before I was starting a company. I was working on it in my spare time, and then beginning of 22, I started working on the rewrite in Rust. And I worked on it full-time for a year and a half, and then once we started the company, people came and joined. And it was a weird project, because that would never go away. You can't get signed off inside a startup. Like, we're going to go off and three engineers are going to work full-on for a year in Python and Rust, writing like 30,000 lines of Rust just to release open-source-free Python library. The result of that has been excellent for us as a company, right? As in, it's made us remain entirely relevant. And it's like, Pydantic is not just used in the SDKs of all of the AI libraries, but I can't say which one, but one of the big foundational model companies, when they upgraded from Pydantic v1 to v2, their number one internal model... The metric of performance is time to first token. That went down by 20%. So you think about all of the actual AI going on inside, and yet at least 20% of the CPU, or at least the latency inside requests was actually Pydantic, which shows like how widely it's used. So we've benefited from doing that work, although it didn't, it would have never have made financial sense in most companies. In answer to your question about like, how do we prioritize AI, I mean, the honest truth is we've spent a lot of the last year and a half building. Good general purpose observability inside LogFire and making Pydantic good for general purpose use cases. And the AI has kind of come to us. Like we just, not that we want to get away from it, but like the appetite, uh, both in Pydantic and in LogFire to go and build with AI is enormous because it kind of makes sense, right? Like if you're starting a new greenfield project in Python today, what's the chance that you're using GenAI 80%, let's say, globally, obviously it's like a hundred percent in California, but even worldwide, it's probably 80%. Yeah. And so everyone needs that stuff. And there's so much yet to be figured out so much like space to do things better in the ecosystem in a way that like to go and implement a database that's better than Postgres is a like Sisyphean task. Whereas building, uh, tools that are better for GenAI than some of the stuff that's about now is not very difficult. Putting the actual models themselves to one side.Alessio [00:07:40]: And then at the same time, then you released Pydantic AI recently, which is, uh, um, you know, agent framework and early on, I would say everybody like, you know, Langchain and like, uh, Pydantic kind of like a first class support, a lot of these frameworks, we're trying to use you to be better. What was the decision behind we should do our own framework? Were there any design decisions that you disagree with any workloads that you think people didn't support? Well,Samuel [00:08:05]: it wasn't so much like design and workflow, although I think there were some, some things we've done differently. Yeah. I think looking in general at the ecosystem of agent frameworks, the engineering quality is far below that of the rest of the Python ecosystem. There's a bunch of stuff that we have learned how to do over the last 20 years of building Python libraries and writing Python code that seems to be abandoned by people when they build agent frameworks. Now I can kind of respect that, particularly in the very first agent frameworks, like Langchain, where they were literally figuring out how to go and do this stuff. It's completely understandable that you would like basically skip some stuff.Samuel [00:08:42]: I'm shocked by the like quality of some of the agent frameworks that have come out recently from like well-respected names, which it just seems to be opportunism and I have little time for that, but like the early ones, like I think they were just figuring out how to do stuff and just as lots of people have learned from Pydantic, we were able to learn a bit from them. I think from like the gap we saw and the thing we were frustrated by was the production readiness. And that means things like type checking, even if type checking makes it hard. Like Pydantic AI, I will put my hand up now and say it has a lot of generics and you need to, it's probably easier to use it if you've written a bit of Rust and you really understand generics, but like, and that is, we're not claiming that that makes it the easiest thing to use in all cases, we think it makes it good for production applications in big systems where type checking is a no-brainer in Python. But there are also a bunch of stuff we've learned from maintaining Pydantic over the years that we've gone and done. So every single example in Pydantic AI's documentation is run on Python. As part of tests and every single print output within an example is checked during tests. So it will always be up to date. And then a bunch of things that, like I say, are standard best practice within the rest of the Python ecosystem, but I'm not followed surprisingly by some AI libraries like coverage, linting, type checking, et cetera, et cetera, where I think these are no-brainers, but like weirdly they're not followed by some of the other libraries.Alessio [00:10:04]: And can you just give an overview of the framework itself? I think there's kind of like the. LLM calling frameworks, there are the multi-agent frameworks, there's the workflow frameworks, like what does Pydantic AI do?Samuel [00:10:17]: I glaze over a bit when I hear all of the different sorts of frameworks, but I like, and I will tell you when I built Pydantic, when I built Logfire and when I built Pydantic AI, my methodology is not to go and like research and review all of the other things. I kind of work out what I want and I go and build it and then feedback comes and we adjust. So the fundamental building block of Pydantic AI is agents. The exact definition of agents and how you want to define them. is obviously ambiguous and our things are probably sort of agent-lit, not that we would want to go and rename them to agent-lit, but like the point is you probably build them together to build something and most people will call an agent. So an agent in our case has, you know, things like a prompt, like system prompt and some tools and a structured return type if you want it, that covers the vast majority of cases. There are situations where you want to go further and the most complex workflows where you want graphs and I resisted graphs for quite a while. I was sort of of the opinion you didn't need them and you could use standard like Python flow control to do all of that stuff. I had a few arguments with people, but I basically came around to, yeah, I can totally see why graphs are useful. But then we have the problem that by default, they're not type safe because if you have a like add edge method where you give the names of two different edges, there's no type checking, right? Even if you go and do some, I'm not, not all the graph libraries are AI specific. So there's a, there's a graph library called, but it allows, it does like a basic runtime type checking. Ironically using Pydantic to try and make up for the fact that like fundamentally that graphs are not typed type safe. Well, I like Pydantic, but it did, that's not a real solution to have to go and run the code to see if it's safe. There's a reason that starting type checking is so powerful. And so we kind of, from a lot of iteration eventually came up with a system of using normally data classes to define nodes where you return the next node you want to call and where we're able to go and introspect the return type of a node to basically build the graph. And so the graph is. Yeah. Inherently type safe. And once we got that right, I, I wasn't, I'm incredibly excited about graphs. I think there's like masses of use cases for them, both in gen AI and other development, but also software's all going to have interact with gen AI, right? It's going to be like web. There's no longer be like a web department in a company is that there's just like all the developers are building for web building with databases. The same is going to be true for gen AI.Alessio [00:12:33]: Yeah. I see on your docs, you call an agent, a container that contains a system prompt function. Tools, structure, result, dependency type model, and then model settings. Are the graphs in your mind, different agents? Are they different prompts for the same agent? What are like the structures in your mind?Samuel [00:12:52]: So we were compelled enough by graphs once we got them right, that we actually merged the PR this morning. That means our agent implementation without changing its API at all is now actually a graph under the hood as it is built using our graph library. So graphs are basically a lower level tool that allow you to build these complex workflows. Our agents are technically one of the many graphs you could go and build. And we just happened to build that one for you because it's a very common, commonplace one. But obviously there are cases where you need more complex workflows where the current agent assumptions don't work. And that's where you can then go and use graphs to build more complex things.Swyx [00:13:29]: You said you were cynical about graphs. What changed your mind specifically?Samuel [00:13:33]: I guess people kept giving me examples of things that they wanted to use graphs for. And my like, yeah, but you could do that in standard flow control in Python became a like less and less compelling argument to me because I've maintained those systems that end up with like spaghetti code. And I could see the appeal of this like structured way of defining the workflow of my code. And it's really neat that like just from your code, just from your type hints, you can get out a mermaid diagram that defines exactly what can go and happen.Swyx [00:14:00]: Right. Yeah. You do have very neat implementation of sort of inferring the graph from type hints, I guess. Yeah. Is what I would call it. Yeah. I think the question always is I have gone back and forth. I used to work at Temporal where we would actually spend a lot of time complaining about graph based workflow solutions like AWS step functions. And we would actually say that we were better because you could use normal control flow that you already knew and worked with. Yours, I guess, is like a little bit of a nice compromise. Like it looks like normal Pythonic code. But you just have to keep in mind what the type hints actually mean. And that's what we do with the quote unquote magic that the graph construction does.Samuel [00:14:42]: Yeah, exactly. And if you look at the internal logic of actually running a graph, it's incredibly simple. It's basically call a node, get a node back, call that node, get a node back, call that node. If you get an end, you're done. We will add in soon support for, well, basically storage so that you can store the state between each node that's run. And then the idea is you can then distribute the graph and run it across computers. And also, I mean, the other weird, the other bit that's really valuable is across time. Because it's all very well if you look at like lots of the graph examples that like Claude will give you. If it gives you an example, it gives you this lovely enormous mermaid chart of like the workflow, for example, managing returns if you're an e-commerce company. But what you realize is some of those lines are literally one function calls another function. And some of those lines are wait six days for the customer to print their like piece of paper and put it in the post. And if you're writing like your demo. Project or your like proof of concept, that's fine because you can just say, and now we call this function. But when you're building when you're in real in real life, that doesn't work. And now how do we manage that concept to basically be able to start somewhere else in the in our code? Well, this graph implementation makes it incredibly easy because you just pass the node that is the start point for carrying on the graph and it continues to run. So it's things like that where I was like, yeah, I can just imagine how things I've done in the past would be fundamentally easier to understand if we had done them with graphs.Swyx [00:16:07]: You say imagine, but like right now, this pedantic AI actually resume, you know, six days later, like you said, or is this just like a theoretical thing we can go someday?Samuel [00:16:16]: I think it's basically Q&A. So there's an AI that's asking the user a question and effectively you then call the CLI again to continue the conversation. And it basically instantiates the node and calls the graph with that node again. Now, we don't have the logic yet for effectively storing state in the database between individual nodes that we're going to add soon. But like the rest of it is basically there.Swyx [00:16:37]: It does make me think that not only are you competing with Langchain now and obviously Instructor, and now you're going into sort of the more like orchestrated things like Airflow, Prefect, Daxter, those guys.Samuel [00:16:52]: Yeah, I mean, we're good friends with the Prefect guys and Temporal have the same investors as us. And I'm sure that my investor Bogomol would not be too happy if I was like, oh, yeah, by the way, as well as trying to take on Datadog. We're also going off and trying to take on Temporal and everyone else doing that. Obviously, we're not doing all of the infrastructure of deploying that right yet, at least. We're, you know, we're just building a Python library. And like what's crazy about our graph implementation is, sure, there's a bit of magic in like introspecting the return type, you know, extracting things from unions, stuff like that. But like the actual calls, as I say, is literally call a function and get back a thing and call that. It's like incredibly simple and therefore easy to maintain. The question is, how useful is it? Well, I don't know yet. I think we have to go and find out. We have a whole. We've had a slew of people joining our Slack over the last few days and saying, tell me how good Pydantic AI is. How good is Pydantic AI versus Langchain? And I refuse to answer. That's your job to go and find that out. Not mine. We built a thing. I'm compelled by it, but I'm obviously biased. The ecosystem will work out what the useful tools are.Swyx [00:17:52]: Bogomol was my board member when I was at Temporal. And I think I think just generally also having been a workflow engine investor and participant in this space, it's a big space. Like everyone needs different functions. I think the one thing that I would say like yours, you know, as a library, you don't have that much control of it over the infrastructure. I do like the idea that each new agents or whatever or unit of work, whatever you call that should spin up in this sort of isolated boundaries. Whereas yours, I think around everything runs in the same process. But you ideally want to sort of spin out its own little container of things.Samuel [00:18:30]: I agree with you a hundred percent. And we will. It would work now. Right. As in theory, you're just like as long as you can serialize the calls to the next node, you just have to all of the different containers basically have to have the same the same code. I mean, I'm super excited about Cloudflare workers running Python and being able to install dependencies. And if Cloudflare could only give me my invitation to the private beta of that, we would be exploring that right now because I'm super excited about that as a like compute level for some of this stuff where exactly what you're saying, basically. You can run everything as an individual. Like worker function and distribute it. And it's resilient to failure, et cetera, et cetera.Swyx [00:19:08]: And it spins up like a thousand instances simultaneously. You know, you want it to be sort of truly serverless at once. Actually, I know we have some Cloudflare friends who are listening, so hopefully they'll get in front of the line. Especially.Samuel [00:19:19]: I was in Cloudflare's office last week shouting at them about other things that frustrate me. I have a love-hate relationship with Cloudflare. Their tech is awesome. But because I use it the whole time, I then get frustrated. So, yeah, I'm sure I will. I will. I will get there soon.Swyx [00:19:32]: There's a side tangent on Cloudflare. Is Python supported at full? I actually wasn't fully aware of what the status of that thing is.Samuel [00:19:39]: Yeah. So Pyodide, which is Python running inside the browser in scripting, is supported now by Cloudflare. They basically, they're having some struggles working out how to manage, ironically, dependencies that have binaries, in particular, Pydantic. Because these workers where you can have thousands of them on a given metal machine, you don't want to have a difference. You basically want to be able to have a share. Shared memory for all the different Pydantic installations, effectively. That's the thing they work out. They're working out. But Hood, who's my friend, who is the primary maintainer of Pyodide, works for Cloudflare. And that's basically what he's doing, is working out how to get Python running on Cloudflare's network.Swyx [00:20:19]: I mean, the nice thing is that your binary is really written in Rust, right? Yeah. Which also compiles the WebAssembly. Yeah. So maybe there's a way that you'd build... You have just a different build of Pydantic and that ships with whatever your distro for Cloudflare workers is.Samuel [00:20:36]: Yes, that's exactly what... So Pyodide has builds for Pydantic Core and for things like NumPy and basically all of the popular binary libraries. Yeah. It's just basic. And you're doing exactly that, right? You're using Rust to compile the WebAssembly and then you're calling that shared library from Python. And it's unbelievably complicated, but it works. Okay.Swyx [00:20:57]: Staying on graphs a little bit more, and then I wanted to go to some of the other features that you have in Pydantic AI. I see in your docs, there are sort of four levels of agents. There's single agents, there's agent delegation, programmatic agent handoff. That seems to be what OpenAI swarms would be like. And then the last one, graph-based control flow. Would you say that those are sort of the mental hierarchy of how these things go?Samuel [00:21:21]: Yeah, roughly. Okay.Swyx [00:21:22]: You had some expression around OpenAI swarms. Well.Samuel [00:21:25]: And indeed, OpenAI have got in touch with me and basically, maybe I'm not supposed to say this, but basically said that Pydantic AI looks like what swarms would become if it was production ready. So, yeah. I mean, like, yeah, which makes sense. Awesome. Yeah. I mean, in fact, it was specifically saying, how can we give people the same feeling that they were getting from swarms that led us to go and implement graphs? Because my, like, just call the next agent with Python code was not a satisfactory answer to people. So it was like, okay, we've got to go and have a better answer for that. It's not like, let us to get to graphs. Yeah.Swyx [00:21:56]: I mean, it's a minimal viable graph in some sense. What are the shapes of graphs that people should know? So the way that I would phrase this is I think Anthropic did a very good public service and also kind of surprisingly influential blog post, I would say, when they wrote Building Effective Agents. We actually have the authors coming to speak at my conference in New York, which I think you're giving a workshop at. Yeah.Samuel [00:22:24]: I'm trying to work it out. But yes, I think so.Swyx [00:22:26]: Tell me if you're not. yeah, I mean, like, that was the first, I think, authoritative view of, like, what kinds of graphs exist in agents and let's give each of them a name so that everyone is on the same page. So I'm just kind of curious if you have community names or top five patterns of graphs.Samuel [00:22:44]: I don't have top five patterns of graphs. I would love to see what people are building with them. But like, it's been it's only been a couple of weeks. And of course, there's a point is that. Because they're relatively unopinionated about what you can go and do with them. They don't suit them. Like, you can go and do lots of lots of things with them, but they don't have the structure to go and have like specific names as much as perhaps like some other systems do. I think what our agents are, which have a name and I can't remember what it is, but this basically system of like, decide what tool to call, go back to the center, decide what tool to call, go back to the center and then exit. One form of graph, which, as I say, like our agents are effectively one implementation of a graph, which is why under the hood they are now using graphs. And it'll be interesting to see over the next few years whether we end up with these like predefined graph names or graph structures or whether it's just like, yep, I built a graph or whether graphs just turn out not to match people's mental image of what they want and die away. We'll see.Swyx [00:23:38]: I think there is always appeal. Every developer eventually gets graph religion and goes, oh, yeah, everything's a graph. And then they probably over rotate and go go too far into graphs. And then they have to learn a whole bunch of DSLs. And then they're like, actually, I didn't need that. I need this. And they scale back a little bit.Samuel [00:23:55]: I'm at the beginning of that process. I'm currently a graph maximalist, although I haven't actually put any into production yet. But yeah.Swyx [00:24:02]: This has a lot of philosophical connections with other work coming out of UC Berkeley on compounding AI systems. I don't know if you know of or care. This is the Gartner world of things where they need some kind of industry terminology to sell it to enterprises. I don't know if you know about any of that.Samuel [00:24:24]: I haven't. I probably should. I should probably do it because I should probably get better at selling to enterprises. But no, no, I don't. Not right now.Swyx [00:24:29]: This is really the argument is that instead of putting everything in one model, you have more control and more maybe observability to if you break everything out into composing little models and changing them together. And obviously, then you need an orchestration framework to do that. Yeah.Samuel [00:24:47]: And it makes complete sense. And one of the things we've seen with agents is they work well when they work well. But when they. Even if you have the observability through log five that you can see what was going on, if you don't have a nice hook point to say, hang on, this is all gone wrong. You have a relatively blunt instrument of basically erroring when you exceed some kind of limit. But like what you need to be able to do is effectively iterate through these runs so that you can have your own control flow where you're like, OK, we've gone too far. And that's where one of the neat things about our graph implementation is you can basically call next in a loop rather than just running the full graph. And therefore, you have this opportunity to to break out of it. But yeah, basically, it's the same point, which is like if you have two bigger unit of work to some extent, whether or not it involves gen AI. But obviously, it's particularly problematic in gen AI. You only find out afterwards when you've spent quite a lot of time and or money when it's gone off and done done the wrong thing.Swyx [00:25:39]: Oh, drop on this. We're not going to resolve this here, but I'll drop this and then we can move on to the next thing. This is the common way that we we developers talk about this. And then the machine learning researchers look at us. And laugh and say, that's cute. And then they just train a bigger model and they wipe us out in the next training run. So I think there's a certain amount of we are fighting the bitter lesson here. We're fighting AGI. And, you know, when AGI arrives, this will all go away. Obviously, on Latent Space, we don't really discuss that because I think AGI is kind of this hand wavy concept that isn't super relevant. But I think we have to respect that. For example, you could do a chain of thoughts with graphs and you could manually orchestrate a nice little graph that does like. Reflect, think about if you need more, more inference time, compute, you know, that's the hot term now. And then think again and, you know, scale that up. Or you could train Strawberry and DeepSeq R1. Right.Samuel [00:26:32]: I saw someone saying recently, oh, they were really optimistic about agents because models are getting faster exponentially. And I like took a certain amount of self-control not to describe that it wasn't exponential. But my main point was. If models are getting faster as quickly as you say they are, then we don't need agents and we don't really need any of these abstraction layers. We can just give our model and, you know, access to the Internet, cross our fingers and hope for the best. Agents, agent frameworks, graphs, all of this stuff is basically making up for the fact that right now the models are not that clever. In the same way that if you're running a customer service business and you have loads of people sitting answering telephones, the less well trained they are, the less that you trust them, the more that you need to give them a script to go through. Whereas, you know, so if you're running a bank and you have lots of customer service people who you don't trust that much, then you tell them exactly what to say. If you're doing high net worth banking, you just employ people who you think are going to be charming to other rich people and set them off to go and have coffee with people. Right. And the same is true of models. The more intelligent they are, the less we need to tell them, like structure what they go and do and constrain the routes in which they take.Swyx [00:27:42]: Yeah. Yeah. Agree with that. So I'm happy to move on. So the other parts of Pydantic AI that are worth commenting on, and this is like my last rant, I promise. So obviously, every framework needs to do its sort of model adapter layer, which is, oh, you can easily swap from OpenAI to Cloud to Grok. You also have, which I didn't know about, Google GLA, which I didn't really know about until I saw this in your docs, which is generative language API. I assume that's AI Studio? Yes.Samuel [00:28:13]: Google don't have good names for it. So Vertex is very clear. That seems to be the API that like some of the things use, although it returns 503 about 20% of the time. So... Vertex? No. Vertex, fine. But the... Oh, oh. GLA. Yeah. Yeah.Swyx [00:28:28]: I agree with that.Samuel [00:28:29]: So we have, again, another example of like, well, I think we go the extra mile in terms of engineering is we run on every commit, at least commit to main, we run tests against the live models. Not lots of tests, but like a handful of them. Oh, okay. And we had a point last week where, yeah, GLA is a little bit better. GLA1 was failing every single run. One of their tests would fail. And we, I think we might even have commented out that one at the moment. So like all of the models fail more often than you might expect, but like that one seems to be particularly likely to fail. But Vertex is the same API, but much more reliable.Swyx [00:29:01]: My rant here is that, you know, versions of this appear in Langchain and every single framework has to have its own little thing, a version of that. I would put to you, and then, you know, this is, this can be agree to disagree. This is not needed in Pydantic AI. I would much rather you adopt a layer like Lite LLM or what's the other one in JavaScript port key. And that's their job. They focus on that one thing and they, they normalize APIs for you. All new models are automatically added and you don't have to duplicate this inside of your framework. So for example, if I wanted to use deep seek, I'm out of luck because Pydantic AI doesn't have deep seek yet.Samuel [00:29:38]: Yeah, it does.Swyx [00:29:39]: Oh, it does. Okay. I'm sorry. But you know what I mean? Should this live in your code or should it live in a layer that's kind of your API gateway that's a defined piece of infrastructure that people have?Samuel [00:29:49]: And I think if a company who are well known, who are respected by everyone had come along and done this at the right time, maybe we should have done it a year and a half ago and said, we're going to be the universal AI layer. That would have been a credible thing to do. I've heard varying reports of Lite LLM is the truth. And it didn't seem to have exactly the type safety that we needed. Also, as I understand it, and again, I haven't looked into it in great detail. Part of their business model is proxying the request through their, through their own system to do the generalization. That would be an enormous put off to an awful lot of people. Honestly, the truth is I don't think it is that much work unifying the model. I get where you're coming from. I kind of see your point. I think the truth is that everyone is centralizing around open AIs. Open AI's API is the one to do. So DeepSeq support that. Grok with OK support that. Ollama also does it. I mean, if there is that library right now, it's more or less the open AI SDK. And it's very high quality. It's well type checked. It uses Pydantic. So I'm biased. But I mean, I think it's pretty well respected anyway.Swyx [00:30:57]: There's different ways to do this. Because also, it's not just about normalizing the APIs. You have to do secret management and all that stuff.Samuel [00:31:05]: Yeah. And there's also. There's Vertex and Bedrock, which to one extent or another, effectively, they host multiple models, but they don't unify the API. But they do unify the auth, as I understand it. Although we're halfway through doing Bedrock. So I don't know about it that well. But they're kind of weird hybrids because they support multiple models. But like I say, the auth is centralized.Swyx [00:31:28]: Yeah, I'm surprised they don't unify the API. That seems like something that I would do. You know, we can discuss all this all day. There's a lot of APIs. I agree.Samuel [00:31:36]: It would be nice if there was a universal one that we didn't have to go and build.Alessio [00:31:39]: And I guess the other side of, you know, routing model and picking models like evals. How do you actually figure out which one you should be using? I know you have one. First of all, you have very good support for mocking in unit tests, which is something that a lot of other frameworks don't do. So, you know, my favorite Ruby library is VCR because it just, you know, it just lets me store the HTTP requests and replay them. That part I'll kind of skip. I think you are busy like this test model. We're like just through Python. You try and figure out what the model might respond without actually calling the model. And then you have the function model where people can kind of customize outputs. Any other fun stories maybe from there? Or is it just what you see is what you get, so to speak?Samuel [00:32:18]: On those two, I think what you see is what you get. On the evals, I think watch this space. I think it's something that like, again, I was somewhat cynical about for some time. Still have my cynicism about some of the well, it's unfortunate that so many different things are called evals. It would be nice if we could agree. What they are and what they're not. But look, I think it's a really important space. I think it's something that we're going to be working on soon, both in Pydantic AI and in LogFire to try and support better because it's like it's an unsolved problem.Alessio [00:32:45]: Yeah, you do say in your doc that anyone who claims to know for sure exactly how your eval should be defined can safely be ignored.Samuel [00:32:52]: We'll delete that sentence when we tell people how to do their evals.Alessio [00:32:56]: Exactly. I was like, we need we need a snapshot of this today. And so let's talk about eval. So there's kind of like the vibe. Yeah. So you have evals, which is what you do when you're building. Right. Because you cannot really like test it that many times to get statistical significance. And then there's the production eval. So you also have LogFire, which is kind of like your observability product, which I tried before. It's very nice. What are some of the learnings you've had from building an observability tool for LEMPs? And yeah, as people think about evals, even like what are the right things to measure? What are like the right number of samples that you need to actually start making decisions?Samuel [00:33:33]: I'm not the best person to answer that is the truth. So I'm not going to come in here and tell you that I think I know the answer on the exact number. I mean, we can do some back of the envelope statistics calculations to work out that like having 30 probably gets you most of the statistical value of having 200 for, you know, by definition, 15% of the work. But the exact like how many examples do you need? For example, that's a much harder question to answer because it's, you know, it's deep within the how models operate in terms of LogFire. One of the reasons we built LogFire the way we have and we allow you to write SQL directly against your data and we're trying to build the like powerful fundamentals of observability is precisely because we know we don't know the answers. And so allowing people to go and innovate on how they're going to consume that stuff and how they're going to process it is we think that's valuable. Because even if we come along and offer you an evals framework on top of LogFire, it won't be right in all regards. And we want people to be able to go and innovate and being able to write their own SQL connected to the API. And effectively query the data like it's a database with SQL allows people to innovate on that stuff. And that's what allows us to do it as well. I mean, we do a bunch of like testing what's possible by basically writing SQL directly against LogFire as any user could. I think the other the other really interesting bit that's going on in observability is OpenTelemetry is centralizing around semantic attributes for GenAI. So it's a relatively new project. A lot of it's still being added at the moment. But basically the idea that like. They unify how both SDKs and or agent frameworks send observability data to to any OpenTelemetry endpoint. And so, again, we can go and having that unification allows us to go and like basically compare different libraries, compare different models much better. That stuff's in a very like early stage of development. One of the things we're going to be working on pretty soon is basically, I suspect, GenAI will be the first agent framework that implements those semantic attributes properly. Because, again, we control and we can say this is important for observability, whereas most of the other agent frameworks are not maintained by people who are trying to do observability. With the exception of Langchain, where they have the observability platform, but they chose not to go down the OpenTelemetry route. So they're like plowing their own furrow. And, you know, they're a lot they're even further away from standardization.Alessio [00:35:51]: Can you maybe just give a quick overview of how OTEL ties into the AI workflows? There's kind of like the question of is, you know, a trace. And a span like a LLM call. Is it the agent? It's kind of like the broader thing you're tracking. How should people think about it?Samuel [00:36:06]: Yeah, so they have a PR that I think may have now been merged from someone at IBM talking about remote agents and trying to support this concept of remote agents within GenAI. I'm not particularly compelled by that because I don't think that like that's actually by any means the common use case. But like, I suppose it's fine for it to be there. The majority of the stuff in OTEL is basically defining how you would instrument. A given call to an LLM. So basically the actual LLM call, what data you would send to your telemetry provider, how you would structure that. Apart from this slightly odd stuff on remote agents, most of the like agent level consideration is not yet implemented in is not yet decided effectively. And so there's a bit of ambiguity. Obviously, what's good about OTEL is you can in the end send whatever attributes you like. But yeah, there's quite a lot of churn in that space and exactly how we store the data. I think that one of the most interesting things, though, is that if you think about observability. Traditionally, it was sure everyone would say our observability data is very important. We must keep it safe. But actually, companies work very hard to basically not have anything that sensitive in their observability data. So if you're a doctor in a hospital and you search for a drug for an STI, the sequel might be sent to the observability provider. But none of the parameters would. It wouldn't have the patient number or their name or the drug. With GenAI, that distinction doesn't exist because it's all just messed up in the text. If you have that same patient asking an LLM how to. What drug they should take or how to stop smoking. You can't extract the PII and not send it to the observability platform. So the sensitivity of the data that's going to end up in observability platforms is going to be like basically different order of magnitude to what's in what you would normally send to Datadog. Of course, you can make a mistake and send someone's password or their card number to Datadog. But that would be seen as a as a like mistake. Whereas in GenAI, a lot of data is going to be sent. And I think that's why companies like Langsmith and are trying hard to offer observability. On prem, because there's a bunch of companies who are happy for Datadog to be cloud hosted, but want self-hosted self-hosting for this observability stuff with GenAI.Alessio [00:38:09]: And are you doing any of that today? Because I know in each of the spans you have like the number of tokens, you have the context, you're just storing everything. And then you're going to offer kind of like a self-hosting for the platform, basically. Yeah. Yeah.Samuel [00:38:23]: So we have scrubbing roughly equivalent to what the other observability platforms have. So if we, you know, if we see password as the key, we won't send the value. But like, like I said, that doesn't really work in GenAI. So we're accepting we're going to have to store a lot of data and then we'll offer self-hosting for those people who can afford it and who need it.Alessio [00:38:42]: And then this is, I think, the first time that most of the workloads performance is depending on a third party. You know, like if you're looking at Datadog data, usually it's your app that is driving the latency and like the memory usage and all of that. Here you're going to have spans that maybe take a long time to perform because the GLA API is not working or because OpenAI is kind of like overwhelmed. Do you do anything there since like the provider is almost like the same across customers? You know, like, are you trying to surface these things for people and say, hey, this was like a very slow span, but actually all customers using OpenAI right now are seeing the same thing. So maybe don't worry about it or.Samuel [00:39:20]: Not yet. We do a few things that people don't generally do in OTA. So we send. We send information at the beginning. At the beginning of a trace as well as sorry, at the beginning of a span, as well as when it finishes. By default, OTA only sends you data when the span finishes. So if you think about a request which might take like 20 seconds, even if some of the intermediate spans finished earlier, you can't basically place them on the page until you get the top level span. And so if you're using standard OTA, you can't show anything until those requests are finished. When those requests are taking a few hundred milliseconds, it doesn't really matter. But when you're doing Gen AI calls or when you're like running a batch job that might take 30 minutes. That like latency of not being able to see the span is like crippling to understanding your application. And so we've we do a bunch of slightly complex stuff to basically send data about a span as it starts, which is closely related. Yeah.Alessio [00:40:09]: Any thoughts on all the other people trying to build on top of OpenTelemetry in different languages, too? There's like the OpenLEmetry project, which doesn't really roll off the tongue. But how do you see the future of these kind of tools? Is everybody going to have to build? Why does everybody want to build? They want to build their own open source observability thing to then sell?Samuel [00:40:29]: I mean, we are not going off and trying to instrument the likes of the OpenAI SDK with the new semantic attributes, because at some point that's going to happen and it's going to live inside OTEL and we might help with it. But we're a tiny team. We don't have time to go and do all of that work. So OpenLEmetry, like interesting project. But I suspect eventually most of those semantic like that instrumentation of the big of the SDKs will live, like I say, inside the main OpenTelemetry report. I suppose. What happens to the agent frameworks? What data you basically need at the framework level to get the context is kind of unclear. I don't think we know the answer yet. But I mean, I was on the, I guess this is kind of semi-public, because I was on the call with the OpenTelemetry call last week talking about GenAI. And there was someone from Arize talking about the challenges they have trying to get OpenTelemetry data out of Langchain, where it's not like natively implemented. And obviously they're having quite a tough time. And I was realizing, hadn't really realized this before, but how lucky we are to primarily be talking about our own agent framework, where we have the control rather than trying to go and instrument other people's.Swyx [00:41:36]: Sorry, I actually didn't know about this semantic conventions thing. It looks like, yeah, it's merged into main OTel. What should people know about this? I had never heard of it before.Samuel [00:41:45]: Yeah, I think it looks like a great start. I think there's some unknowns around how you send the messages that go back and forth, which is kind of the most important part. It's the most important thing of all. And that is moved out of attributes and into OTel events. OTel events in turn are moving from being on a span to being their own top-level API where you send data. So there's a bunch of churn still going on. I'm impressed by how fast the OTel community is moving on this project. I guess they, like everyone else, get that this is important, and it's something that people are crying out to get instrumentation off. So I'm kind of pleasantly surprised at how fast they're moving, but it makes sense.Swyx [00:42:25]: I'm just kind of browsing through the specification. I can already see that this basically bakes in whatever the previous paradigm was. So now they have genai.usage.prompt tokens and genai.usage.completion tokens. And obviously now we have reasoning tokens as well. And then only one form of sampling, which is top-p. You're basically baking in or sort of reifying things that you think are important today, but it's not a super foolproof way of doing this for the future. Yeah.Samuel [00:42:54]: I mean, that's what's neat about OTel is you can always go and send another attribute and that's fine. It's just there are a bunch that are agreed on. But I would say, you know, to come back to your previous point about whether or not we should be relying on one centralized abstraction layer, this stuff is moving so fast that if you start relying on someone else's standard, you risk basically falling behind because you're relying on someone else to keep things up to date.Swyx [00:43:14]: Or you fall behind because you've got other things going on.Samuel [00:43:17]: Yeah, yeah. That's fair. That's fair.Swyx [00:43:19]: Any other observations just about building LogFire, actually? Let's just talk about this. So you announced LogFire. I was kind of only familiar with LogFire because of your Series A announcement. I actually thought you were making a separate company. I remember some amount of confusion with you when that came out. So to be clear, it's Pydantic LogFire and the company is one company that has kind of two products, an open source thing and an observability thing, correct? Yeah. I was just kind of curious, like any learnings building LogFire? So classic question is, do you use ClickHouse? Is this like the standard persistence layer? Any learnings doing that?Samuel [00:43:54]: We don't use ClickHouse. We started building our database with ClickHouse, moved off ClickHouse onto Timescale, which is a Postgres extension to do analytical databases. Wow. And then moved off Timescale onto DataFusion. And we're basically now building, it's DataFusion, but it's kind of our own database. Bogomil is not entirely happy that we went through three databases before we chose one. I'll say that. But like, we've got to the right one in the end. I think we could have realized that Timescale wasn't right. I think ClickHouse. They both taught us a lot and we're in a great place now. But like, yeah, it's been a real journey on the database in particular.Swyx [00:44:28]: Okay. So, you know, as a database nerd, I have to like double click on this, right? So ClickHouse is supposed to be the ideal backend for anything like this. And then moving from ClickHouse to Timescale is another counterintuitive move that I didn't expect because, you know, Timescale is like an extension on top of Postgres. Not super meant for like high volume logging. But like, yeah, tell us those decisions.Samuel [00:44:50]: So at the time, ClickHouse did not have good support for JSON. I was speaking to someone yesterday and said ClickHouse doesn't have good support for JSON and got roundly stepped on because apparently it does now. So they've obviously gone and built their proper JSON support. But like back when we were trying to use it, I guess a year ago or a bit more than a year ago, everything happened to be a map and maps are a pain to try and do like looking up JSON type data. And obviously all these attributes, everything you're talking about there in terms of the GenAI stuff. You can choose to make them top level columns if you want. But the simplest thing is just to put them all into a big JSON pile. And that was a problem with ClickHouse. Also, ClickHouse had some really ugly edge cases like by default, or at least until I complained about it a lot, ClickHouse thought that two nanoseconds was longer than one second because they compared intervals just by the number, not the unit. And I complained about that a lot. And then they caused it to raise an error and just say you have to have the same unit. Then I complained a bit more. And I think as I understand it now, they have some. They convert between units. But like stuff like that, when all you're looking at is when a lot of what you're doing is comparing the duration of spans was really painful. Also things like you can't subtract two date times to get an interval. You have to use the date sub function. But like the fundamental thing is because we want our end users to write SQL, the like quality of the SQL, how easy it is to write, matters way more to us than if you're building like a platform on top where your developers are going to write the SQL. And once it's written and it's working, you don't mind too much. So I think that's like one of the fundamental differences. The other problem that I have with the ClickHouse and Impact Timescale is that like the ultimate architecture, the like snowflake architecture of binary data in object store queried with some kind of cache from nearby. They both have it, but it's closed sourced and you only get it if you go and use their hosted versions. And so even if we had got through all the problems with Timescale or ClickHouse, we would end up like, you know, they would want to be taking their 80% margin. And then we would be wanting to take that would basically leave us less space for margin. Whereas data fusion. Properly open source, all of that same tooling is open source. And for us as a team of people with a lot of Rust expertise, data fusion, which is implemented in Rust, we can literally dive into it and go and change it. So, for example, I found that there were some slowdowns in data fusion's string comparison kernel for doing like string contains. And it's just Rust code. And I could go and rewrite the string comparison kernel to be faster. Or, for example, data fusion, when we started using it, didn't have JSON support. Obviously, as I've said, it's something we can do. It's something we needed. I was able to go and implement that in a weekend using our JSON parser that we built for Pydantic Core. So it's the fact that like data fusion is like for us the perfect mixture of a toolbox to build a database with, not a database. And we can go and implement stuff on top of it in a way that like if you were trying to do that in Postgres or in ClickHouse. I mean, ClickHouse would be easier because it's C++, relatively modern C++. But like as a team of people who are not C++ experts, that's much scarier than data fusion for us.Swyx [00:47:47]: Yeah, that's a beautiful rant.Alessio [00:47:49]: That's funny. Most people don't think they have agency on these projects. They're kind of like, oh, I should use this or I should use that. They're not really like, what should I pick so that I contribute the most back to it? You know, so but I think you obviously have an open source first mindset. So that makes a lot of sense.Samuel [00:48:05]: I think if we were probably better as a startup, a better startup and faster moving and just like headlong determined to get in front of customers as fast as possible, we should have just started with ClickHouse. I hope that long term we're in a better place for having worked with data fusion. We like we're quite engaged now with the data fusion community. Andrew Lam, who maintains data fusion, is an advisor to us. We're in a really good place now. But yeah, it's definitely slowed us down relative to just like building on ClickHouse and moving as fast as we can.Swyx [00:48:34]: OK, we're about to zoom out and do Pydantic run and all the other stuff. But, you know, my last question on LogFire is really, you know, at some point you run out sort of community goodwill just because like, oh, I use Pydantic. I love Pydantic. I'm going to use LogFire. OK, then you start entering the territory of the Datadogs, the Sentrys and the honeycombs. Yeah. So where are you going to really spike here? What differentiator here?Samuel [00:48:59]: I wasn't writing code in 2001, but I'm assuming that there were people talking about like web observability and then web observability stopped being a thing, not because the web stopped being a thing, but because all observability had to do web. If you were talking to people in 2010 or 2012, they would have talked about cloud observability. Now that's not a term because all observability is cloud first. The same is going to happen to gen AI. And so whether or not you're trying to compete with Datadog or with Arise and Langsmith, you've got to do first class. You've got to do general purpose observability with first class support for AI. And as far as I know, we're the only people really trying to do that. I mean, I think Datadog is starting in that direction. And to be honest, I think Datadog is a much like scarier company to compete with than the AI specific observability platforms. Because in my opinion, and I've also heard this from lots of customers, AI specific observability where you don't see everything else going on in your app is not actually that useful. Our hope is that we can build the first general purpose observability platform with first class support for AI. And that we have this open source heritage of putting developer experience first that other companies haven't done. For all I'm a fan of Datadog and what they've done. If you search Datadog logging Python. And you just try as a like a non-observability expert to get something up and running with Datadog and Python. It's not trivial, right? That's something Sentry have done amazingly well. But like there's enormous space in most of observability to do DX better.Alessio [00:50:27]: Since you mentioned Sentry, I'm curious how you thought about licensing and all of that. Obviously, your MIT license, you don't have any rolling license like Sentry has where you can only use an open source, like the one year old version of it. Was that a hard decision?Samuel [00:50:41]: So to be clear, LogFire is co-sourced. So Pydantic and Pydantic AI are MIT licensed and like properly open source. And then LogFire for now is completely closed source. And in fact, the struggles that Sentry have had with licensing and the like weird pushback the community gives when they take something that's closed source and make it source available just meant that we just avoided that whole subject matter. I think the other way to look at it is like in terms of either headcount or revenue or dollars in the bank. The amount of open source we do as a company is we've got to be open source. We're up there with the most prolific open source companies, like I say, per head. And so we didn't feel like we were morally obligated to make LogFire open source. We have Pydantic. Pydantic is a foundational library in Python. That and now Pydantic AI are our contribution to open source. And then LogFire is like openly for profit, right? As in we're not claiming otherwise. We're not sort of trying to walk a line if it's open source. But really, we want to make it hard to deploy. So you probably want to pay us. We're trying to be straight. That it's to pay for. We could change that at some point in the future, but it's not an immediate plan.Alessio [00:51:48]: All right. So the first one I saw this new I don't know if it's like a product you're building the Pydantic that run, which is a Python browser sandbox. What was the inspiration behind that? We talk a lot about code interpreter for lamps. I'm an investor in a company called E2B, which is a code sandbox as a service for remote execution. Yeah. What's the Pydantic that run story?Samuel [00:52:09]: So Pydantic that run is again completely open source. I have no interest in making it into a product. We just needed a sandbox to be able to demo LogFire in particular, but also Pydantic AI. So it doesn't have it yet, but I'm going to add basically a proxy to OpenAI and the other models so that you can run Pydantic AI in the browser. See how it works. Tweak the prompt, et cetera, et cetera. And we'll have some kind of limit per day of what you can spend on it or like what the spend is. The other thing we wanted to b

Static pressure is the ballooning effect of a duct system and it's measured with a dual port manometer. Airflow is the measurement of air velocity (air speed) in the duct. Velocity is then converted to air flow using duct dimensions. Check out Jobber and all they have to offer. getjobber.com/hvacknowitall

Join Mark Rittman in this special end-of-year episode as he speaks with Noel Gomez, co-founder of DataCoves about the challenges and opportunities of orchestrating dbt and other tools within the open-source Modern Data Stack, navigating the evolving semantic layer landscape and the future of modular, vendor-agnostic data solutions.Datacoves Platform OverviewBuild vs Buy Analytics Platform: Hosting Open-Source ToolsScale the benefits of Core with dbt CloudDagster vs. Airflow

In this episode, join us at the Roadshow as we explore the cutting-edge world of HVAC technology, focusing on Greenheck's control dampers. We delve into the specifics of various damper designs, including the robust Galvanized Steel Airfoil Blade, the versatile Extruded Aluminum Frame and Blade, and the specialized Thermally Broken Frame and Blade for enhanced thermal insulation. Discover how Greenheck is pushing the boundaries of airflow management with their innovative Variable Size Blade technology. Tune in to gain expert insights into optimizing air control systems for various applications.

Picture this: Your organization's data infrastructure resembles a busy kitchen with too many cooks. You're juggling Kafka for messaging, Flink for processing, Spark for analytics, Airflow for orchestration, and various Lambda functions scattered about. Each tool excellent at its job, but together they've created a complex feast of integration challenges. Your data teams are spending more time managing tools than extracting value from data. InfinyOn reimagines this chaos with a radically simple approach: a unified system for data streaming that runs everywhere. Unlike traditional solutions that struggle at the edge, InfinyOn gracefully handles data streams from IoT devices to cloud servers. And instead of cobbling together different tools, developers can build complete data pipelines using their preferred languages - be it Rust, Python, or SQL - with built-in state management. At the heart of InfinyOn is Fluvio, a Rust-based data streaming platform that's fast, reliable, and easy to use.

Last year, we talked with Alex LeBlanc about starting Calibration Coffee Lab in Greenville, South Carolina (CRAFTED ep #26). Today, Alex is back to update us on how it's going, what he's been learning, how his thinking about coffee has evolved, and how he's going about trying to build a brand that people will love.And if you'd like to check out Alex's coffee, CRAFTED listeners can get 15% off by using the code BLISTER at calibrationcoffeelab.comRELATED LINKS:Become a BLISTER+ MemberCheck out the Blister Craft CollectiveCRAFTED ep #26: Calibration Coffee LabTOPICS & TIMES:Backstory of Calibration Coffee Lab (2:53)3rd Wave Coffee (9:32)1st & 2nd Crack (14:18)Alex's Philosophy of Roasting (16:46)Espresso (19:30)Roasting Temperature & Airflow (25:47)Catering to Customers' Tastes (27:06)Coffee, Wine, & Beer Comparisons (33:08)‘Single Origin' Coffees vs Blends (35:10)How Long to “Rest” after Roasting (36:53)Natural vs Washed (45:48)Brand Building (51:03)SEE OUR OTHER PODCASTS:Blister CinematicBikes & Big IdeasGEAR:30Blister Podcast Hosted on Acast. See acast.com/privacy for more information.

In this episode, microgreens grower Vincent Cuneo talks about improving their microgreens' quality by improving air flow in their growing system.  Get time and labor-saving farm tools and microgreen seeds at shop.modern grower.co Listen to other podcasts on the Modern Grower Podcast Network: Farm Small, Farm Smart Farm Small, Farm Smart Daily The Growing Microgreens Podcast Carrot Cashflow Podcast In Search of Soil Check out Diego's book Sell Everything You Grow on Amazon. https://www.amazon.com/Sell-Everything-You-Grow-Homestead-ebook/dp/B0CJC9NTZF

The expression “Less is More” applies to many things but not attic airflow. In this episode of Airing it Out with Air Vent, we examine the benefits of using the 1/150 airflow ratio (more) instead of the 1/300 (less) backed by third-party research. Have a suggestion for a future Podcast topic? Send us your ideas and feedback to pscelsi@gibraltar1.com. 

Get on the Supermarket Academy waitlist now! New program to supercharge your supermarket refrigeration expertise launching soon. BOOK A CALL with Trevor to learn more about refrigeration training programs. In this conversation, we're talking with Aidan Lucey, Refrigeration Mechanic at RAC Services/The Articom Group, about getting into supermarket refrigeration and taking on service calls as a new refrigeration technician. Aidan has taken a number of Refrigeration Mentor courses and here, shares some valuable tips for building confidence and experience, what to look for on service calls, how to diagnose root causes of issues, and how to build trust with store owners and managers. He also shares technical tips and examples of troubleshooting common issues in supermarkets. In this conversation, we cover: -Importance of understanding refrigeration basics -Tips for managing on-calls  -Building relationships with your coworkers -How to better prioritize jobs when on-call -Building relationships with store owners and managers -Being assertive and decisive as a technician -How to build confidence taking service calls -Compressor and electrical checks -The role of superheat in diagnostics -Understanding system pressures and temperatures -Creating a checklist for service calls -Airflow and humidity considerations -Distinguishing causes vs symptoms of service call issues  -Providing added value to your customers -Key measurements for technicians -The importance of detailed service tickets Helpful Links & Resources:   Aidan on LinkedIn The Articom Group: https://thearcticomgroup.com/  Episode 217. Compressor Inspections and Identifying Common Failures with Dean Steliga of Bitzer Canada Episode 099: Controlling CO2 HPV & FGBV with Micro Thermo    Upcoming Servicing Compressors, Supermarket and CO2 Trainings: Learn More Here Learn More About Refrigeration Mentor: https://refrigerationmentor.com/ Get your FREE Service & Compressor Troubleshooting Guide: Access Here Refrigeration Mentor on Instagram Refrigeration Mentor YouTube Channel

Have you ever been driving and suddenly come up with a brilliant solution to an HVACR industry challenge? What happens next? Many innovative tools and techniques in our field come from technicians in the field and industry experts who use their creativity to develop practical solutions. In this episode, Don Prather joins us to share how he tackled a common problem in zoning systems, especially in low-load scenarios, and turned it into both a product and a training initiative.

In this episode of the HVAC podcast, Bryan and Max Johnson from Kalos discuss the critical role of a startup and commissioning technician in the HVAC industry. Max, who has experience in both residential and commercial HVAC, shares his insights on the importance of understanding the scope of work, equipment specifications, and code requirements. One of the key responsibilities of a startup and commissioning technician is to prevent any costly issues that may arise during the installation process. This includes identifying and addressing potential problems with ductwork, refrigerant charge, electrical wiring, and airflow. A comprehensive checklist ensures that no crucial steps are overlooked, such as setting up communicating equipment properly, ensuring the correct accessories are installed, and verifying the drain system is functioning correctly. Proper electrical work is another critical aspect of the startup and commissioning process. Max highlights the importance of using the right connectors and wire sizes to prevent issues like loose connections or overloaded circuits, which can pose fire hazards. Additionally, he stresses the importance of verifying the voltage is within the acceptable range for the equipment, as over-voltage can lead to premature failures. Airflow is another crucial factor that the startup and commissioning technician must address. Setting the correct airflow before charging the system is essential, as it ensures the equipment operates efficiently and effectively removes the necessary amount of latent heat. He recommends using tools like the TrueFlow grid and DG8 manometer to accurately measure and validate the airflow. Follow the manufacturer's charging recommendations closely, as each piece of equipment may have unique requirements. Use a comprehensive calculator, such as the one available on the HVAC School website, to determine the proper charge based on factors like line set length and size. Key Topics Covered: ·        Understanding the role and importance of a startup and commissioning technician ·        Developing a comprehensive checklist to ensure no critical steps are missed ·        Addressing potential issues with ductwork, accessories, and drain systems ·        Proper electrical work, including connector selection and voltage verification ·        Importance of setting the correct airflow before charging the system ·        Following manufacturer guidelines for refrigerant charging   Have a question that you want us to answer on the podcast? Submit your questions at https://www.speakpipe.com/hvacschool.  Purchase your tickets or learn more about the 6th Annual HVACR Training Symposium at https://hvacrschool.com/symposium. Subscribe to our podcast on your iPhone or Android.   Subscribe to our YouTube channel.  Check out our handy calculators here or on the HVAC School Mobile App for Apple and Android.  

In this short podcast, Bryan talks about how to pay close attention to airflow issues and use your "spidey sense" when you're doing a visual inspection or commissioning a system. He also covers some causes of common airflow problems and some services and upgrades you can offer to your customers. The skill of being able to use your senses and notice when something isn't quite right is a valuable one, especially when you're getting ready to set the charge. Not every technician has access to the tools to do a comprehensive airflow assessment, but every tech can use their senses to determine when something is wrong with the system airflow. Keep an ear out for whistling or other strange noises, and watch out for cabinet shaking, which may indicate an airflow problem.  Airflow restrictions are also significant issues. Filter cleanliness (or lack thereof) and improper filter selection are very common causes of airflow issues, including high static pressure drop. Most filters should also not be doubled up (in series). Watch out for furniture blocking vents and registers that are partially (or fully) closed; shutting off registers is NOT a good strategy. Air movement throughout the building is also important, including the presence or absence of returns, open doors, etc., and these things affect MAD-AIR. Watch out for things like leakage as well, which can be around the platform, in ducts around the equipment, and around vents or recessed lighting.    Have a question that you want us to answer on the podcast? Submit your questions at https://www.speakpipe.com/hvacschool.  Purchase your tickets or learn more about the 6th Annual HVACR Training Symposium at https://hvacrschool.com/symposium. Subscribe to our podcast on your iPhone or Android.   Subscribe to our YouTube channel.  Check out our handy calculators here or on the HVAC School Mobile App for Apple and Android.

Hey all you Gardeners, welcome to the latest episode of the Grow Hour podcast.  Together Mr Weedman and Big Earl talk about all things home grow, from genetics to breeding, from soil to bud, and everything in between.  They often have guests on the show, for a deep dive into specific gardening topics.  In this episode, Big Earl is tokin' Drunk Rider #1 and some Stanky Glue #10, while Mr WM is puffing on Jack Frost, both from their personal gardens.  Together the duo discusses building out your grow space - your home garden.  Airflow, hygrometers, water, lights, temperature, and so much more. Learn to recognize when you're ready to get growing and know when & how to do a trial run, along with more tips and tricks from Big Earl, who's a licensed Michigan Medical Caregiver. Thanks for listening and as always, hit us up...---IG: @earl217 and @iamtheregalbeagleEmail: ThatRegalBegal@gmail.com---IG: @weedman420chronicles2.0Twitter: @weedman420podYouTube: Weedman420 ChroniclesEmail: weedman420chronicles@gmail.com---Swag/Shop: https://eightdecades.comIG: @eightdecadesEmail: eightdecadesinfo@gmail.com---#High #Cannabis #StomptheStigma #FreethePlant #CannabisEducation  #CannabisResearch #Weed #Marijuana #LegalizeIt #CannabisNews #CBD #Terpenes  #CannabisPodcast #Podcast #eightdecades #Homegrow #Cultivation #BigEarl #Weedman420Chronicles #GrowHour #seeds #genetics #nutrients #IPM #Burpinthebag #LED #Lights #Atmosphere #TheRegalBegalBeanCo #Autoflower #autos #regs #photos #feminized #terps #plantmedicine #holistichealing #holistic  #seedbreeder #seedbank #beans #forage #chemisty #science #plants #hash #collabCOPYRIGHT 2021 Weedman420Chronicles© 

Collaboration: Enhancing Efficiency Through Industry Partnerships Welcome to this week's edition of Scaling UP! H2O, where we explore the critical role of water treatment in optimizing industrial processes. Today, we are privileged to hear from two distinguished guests: Tony Mormino and Justin Lynch. Tony is Technical Sales and Marketing Director for Insight Partners and host of the The Engineers HVAC Podcast specializing in education, while Justin focuses on cooling tower Reconstruction Specialists. Together, they share invaluable insights into collaborative strategies that ensure the best and most cost-effective solutions for cooling towers and closed loop systems. Their discussion focused on the importance of collaboration, cost efficiency, and proactive maintenance in the field of water treatment. Tony and Justin's insights provide a roadmap for water treaters to enhance client outcomes and operational efficiency through strategic partnerships and informed decision-making. What Are the Cost and Efficiency Benefits of Proper Water Treatment? Cost efficiency emerges as a significant topic. Tony Mormino underscores the financial benefits of proper water treatment, citing examples where a modest investment in water treatment can yield substantial savings. "According to the Department of Energy, 40% of a commercial building's energy consumption goes to HVAC systems," explains Tony. "Simply improving water quality can lead to 5-10% savings in energy costs. It's a quick win for green building initiatives." How Do You Prevent Vibrations in Cooling Towers? Bad vibrations in cooling towers can be a significant issue if not addressed early. Justin Lynch highlights the importance of monitoring biological buildup and evaporative salts on the fans. "It's very difficult to do that if you don't catch it early. Let's say we go to a facility with an old tower and an old fan—there's going to be a little bit of biology on top, which is not a big deal. You can brush that off, do a light pressure washing, and it's not going to hurt it," explains Justin. However, the real issue arises when scale develops unevenly on each blade. "At that point, the fan may look horrible, but the tower still operates without vibration. If you clean five out of six blades well but can't get the scale off one blade, you just created a vibration, leading to other issues in the tower." Justin advises that while chemical treatments are effective, they should be done with caution and under professional guidance to avoid exacerbating the problem. This proactive maintenance is less of a concern for newer towers that have had chemical treatment from the start. How Does Air in Closed Loop Chilled Water Systems Affect Performance? Tony Mormino highlights a critical yet often overlooked issue in water treatment: Air in closed loop chilled water systems. This issue not only leads to rust and oxidation but also significantly impacts the system efficiency and longevity. Studies and practical examples underscore the importance of air removal systems: Removing air from the chill water system can result in substantial benefits: Increase in Tonnage Output: Youngstown State University reported a 16% increase in tonnage output, equivalent to 400 additional tons. Improvement in Delta T: From 8.5-10°, enhancing heat transfer efficiency across chiller barrels. Enhanced Building Discharge Air Temperatures: Temperatures improved from 65° to 55°, optimizing HVAC system performance. Reduction in Pump Energy Consumption: A notable 37% reduction in annual KWH requirements due to cleaner water and improved system operation. Moreover, practical cases like at Waukesha Memorial Hospital in Wisconsin showed a 22% reduction in Variable Frequency Drive (VFD) speed, leading to an 85% decrease in corrosion preventative chemical usage. These examples illustrate the direct correlation between air removal and energy savings, reinforcing the significant impact of proper water treatment practices on operational efficiency and cost savings in commercial HVAC systems. How Important is Passivation for Equipment Longevity and Performance? Justin Lynch highlights the critical role of passivation in maintaining equipment longevity, particularly in galvanized towers. "Passivation is essential to prevent corrosion and ensure optimal performance," Justin explains. "For instance, following Marley's guidelines for pH and calcium hardness during passivation can extend the life of galvanized towers significantly." Conclusion In the fast-evolving landscape of industrial water treatment and HVAC systems, collaboration and continuous learning are paramount. Justin Lynch's closing thoughts encapsulate this spirit perfectly: “Don't be afraid to call, don't be afraid to collaborate. You are the expert in your field; I'm supposed to be the expert in mine. There's too much going on in this industry. It's growing too fast for everyone to really understand everything. So, if you don't know, ask questions and learn together. When you can do that together, you build a good network, and customers trust you and respect you after that.” Embracing this collaborative approach not only enhances our expertise but also ensures that we provide the best possible solutions for our customers, fostering trust and respect in our professional relationships. Timestamps 01:00 - Free Legionella Awareness Month and Industrial Water Week resources can be found on our website 09:10 - Interview with Tony Mormino and Justin Lynch 50:00 - Closing thoughts about the power of collaboration with Trace 54:30 - Upcoming Events for Water Treatment Professionals 56:42 - Evaporative Salts, Scale, and using the correct language with clients 59:00 - Drop by Drop With James McDonald Quotes “Downtime is lost profit.” - Justin Lynch “Water quality is key. It's crucial for maintaining a tower's expected lifespan, and without it, customers could face significant costs." - Justin Lynch “I consider the water the lifeblood of the system because it touches every component.” - Tony Mormino “In our industry, collaboration is essential. As experts in our respective fields, we have a responsibility to work together, share knowledge, and tackle challenges as a unified front." - shares Justin Lynch “The best way to market is to give away good, free content.” - Tony Mormino Connect with Justin Lynch Phone: 919.602.1658 Email: jlynch@insightusa.com LinkedIn: linkedin.com/in/justin-lynch-0355458b Read or Download Tony and Justin's Press Release HERE Connect with Tony Mormino Phone: 828.712.4769 Email: tmormino@insightusa.com Website: www.insightusa.com LinkedIn: linkedin.com/in/tony-mormino linkedin.com/company/insightusa YouTube: @InsightPartnersHVACTV Podcast: The Engineers HVAC Podcast Resources Mentioned All Cooling Tower resources can be found on our Free Industrial Water Week Page HERE in the Cooling Wednesday Tab All Legionella Resources can be found on our Free Legionella Page HERE Check out our Scaling UP! H2O Events Calendar where we've listed every event Water Treaters should be aware of by clicking HERE. Water Cake Recipe

Pusher Intakes joins us today to talk intake manifolds! They tell us how they started on Cummins 5.9's, and how it progressed to the first CARB tested manifold for the 6.7L Powerstroke. We were shocked how much airflow was improved. Learn more about your ad choices. Visit megaphone.fm/adchoices

Standard 310 is a technical workflow created by ACCA, ResNet, and ANSI for grading the installation of HVAC systems, typically in new home construction. It plays a crucial role in obtaining Energy Star certification, which can qualify homeowners for tax credits under the Inflation Reduction Act. The five steps of Standard 310 are design review, duct leakage test, total system airflow, blower fan watt draw, and refrigerant charge verification. In this podcast episode, host Bryan Orr is joined by guests Chris Hughes and Eric Kaiser to discuss Standard 310 and its implications for HVAC contractors. The standard aims to ensure that HVAC systems are installed correctly and operate as designed. The process involves a third-party HERS rater conducting various tests and measurements, which contractors need to be prepared for. Proper duct sealing, airflow settings, and refrigerant charging are critical for passing the assessments. One of the challenging aspects highlighted is the refrigerant charge verification step. The standard requires either non-invasive testing (which has temperature limitations) or weigh-in verification with geotagged photos. Chris Hughes suggests manufacturers could develop more consistent commissioning protocols to streamline this process. Topics covered in the podcast: Overview of Standard 310 and its five steps Importance for Energy Star certification and tax credits Role of HERS raters and HVAC contractors Duct leakage testing and proper sealing Airflow measurement methods Blower fan watt draw challenges Refrigerant charge verification options Need for consistent commissioning protocols Coordination and documentation required Future improvements to the standard   Have a question that you want us to answer on the podcast? Submit your questions at https://www.speakpipe.com/hvacschool.  Purchase your virtual tickets for the 5th Annual HVACR Training Symposium at https://hvacrschool.com/Symposium24.  Subscribe to our podcast on your iPhone or Android.   Subscribe to our YouTube channel.  Check out our handy calculators here or on the HVAC School Mobile App for Apple and Android.

Discovering the science behind airflow and temperature for better sleep on the newest episode on Deep Into Sleep Podcast. Eugene Alletto shares insights on optimizing sleep environments for quality rest with BEDGEAR!Watch out for the COUPON code that will be given away during the episode! Let's join Dr. Yishan and Eugene in exploring the impact of breathable materials and modular sleep systems on sleep quality.Show Notes: deepintosleep.co/episode/bedgearRESOURCESAre you so sleepy that you cannot focus? Are you tired of getting through the day drinking coffee? Are you worried how your poor sleep may impact your health?Checkout Dr. Yishan Xu's Insomnia Treatment Course! Connect with Dr. YishanInstagram: @dr.yishanTwitter: @dryishanFacebook:@dr.yishanConnect with Eugene AllettoWebsiteFREE Coupon Code to purchase at https://www.bedgear.com/:DEEPINTOSLEEP15Newsletter and Download Free Sleep Guidence E-Book:https://www.mindbodygarden.com/sleepCBT-I Courses:English: https://www.deepintosleep.co/insomniaChinese: https://www.mindbodygarden.com/shimianPodcast Links:Apple Podcast: https://podcasts.apple.com/us/podcast/deep-into-sleep/id1475295840Google Podcast: https://podcasts.google.com/search/deepintosleepStitcher: https://www.stitcher.com/show/deep-into-sleepSpotify: https://open.spotify.com/show/2Vxyyj9Cswuk91OYztzcMSiHeartRadio: https://www.iheart.com/podcast/269-deep-into-sleep-47827108/Support our Podcast: https://www.buymeacoffee.com/dryishanLeave us a Rating: https://podcasts.apple.com/us/podcast/deep-into-sleep/id1475295840If you're interested in learning more about psychological testing and the services offered at the MindBodyGarden make sure to visit their website at mindbodygarden.com/AssessmentClinic.

If you've worked on data problems, you probably have heard of Airflow and Superset, two powerful tools that have cemented their place in the data ecosystem. Building successful open-source software is no easy feat, and even fewer engineers have done this back to back. In part 2 of the conversation, we talk about Max's journey in open source. Segments:    (00:03:27) “Project-Community Fit” in Open Source    (00:08:31) Fostering Relationships in Open Source    (00:10:58) Dealing with Trolls    (00:13:40) Attributes of Good Open Source Contributors    (00:20:01) How to Get Started with Contributing    (00:27:58) Origin Stories of Airflow and Superset    (00:33:27) Biggest Surprise since Founding a VC-backed Company?    (00:38:47) Picking What to Work On    (00:41:46) Advice to Engineers for Building the Next Airflow/Superset?    (00:42:35) The 2 New Open Source Projects that Max is Starting    (00:52:10) Challenges of Being a Founder    (00:57:38) Open Sourcing Ideas Show Notes: Part 1 of our conversation: https://softwaremisadventures.com/p/maxime-beauchemin-llm-ready Max on LinkedIn: https://www.linkedin.com/in/maximebeauchemin/ SQL All Stars: https://github.com/preset-io/allstars Governator: https://github.com/mistercrunch/governator Stay in touch:

Brian Johnson, the visionary CEO of Senergy360, is at the forefront of redefining healthy living by constructing homes that embody holistic principles for today's evolving world incorporating modern cutting edge technologies using proven practices for multigenerational homes. With over two decades of experience as a licensed general contractor and a solid background in the lumber industry, Brian's expertise is unparalleled. His commitment to excellence is further demonstrated by his triple certifications from the Building Biology Institute, a testament to his dedication to health, performance, wellness, and longevity. Under Brian's leadership, SENERGY360 is on a mission to democratize access to advanced technologies and systems for creating holistic living spaces. The firm offers top-tier services, including healthy home building and land development, environmental assessments, healthy home specifications and project management for all types of construction , serving clients across the United States and internationally.   Senergy360 Website: www.senergy360.com   Work With Me: Mineral Balancing HTMA Consultation: https://www.integrativethoughts.com/category/all-products  My Instagram: @integrativematt My Website: Integrativethoughts.com   Advertisements:   Valence Nutraceuticals: Use code ITP20 for 20% off https://valencenutraceuticals.myshopify.com/   Zeolite Labs Zeocharge: Use Code ITP for 10% off https://www.zeolitelabs.com/product-page/zeocharge?ref=ITP Magnesium Breakthrough: Use Code integrativethoughts10 for 10% OFF https://bioptimizers.com/shop/products/magnesium-breakthrough Just Thrive: Use Code ITP15 for 15% off https://justthrivehealth.com/discount/ITP15 Therasage: Use Code Coffman10 for 10% off https://www.therasage.com/discount/COFFMAN10?rfsn=6763480.4aed7f&utm_source=refersion&utm_medium=affiliate&utm_campaign=6763480.4aed7f   Chapters:   00:00 Introduction and Background 02:54 From Building to Health 06:01 The Importance of Building Materials 08:06 Protecting Against Toxic Exposure 11:35 The Lifelong Process of Detoxification 23:46 Building Harmonious and Healthy Homes 25:44 Being in Tune with Nature in Location Selection 28:14 Preventing Mold Growth in New Builds 35:41 Auto Shut-off Valves for Water Leaks 47:18 The Presence of VOCs in New Builds 52:04 Choosing Low or Non-VOC Materials 52:56 Creating a Healthy Home: Non-VOC Materials and Natural Building 55:09 The Importance of Ventilation and Airflow in Building Design 56:24 The Role of Negative and Positive Ions in a Healthy Living Environment 59:47 Air Filtration Systems: Energy Recovery Ventilators and HEPA Filters 01:08:06 The Cost of Building a Healthy Home and the Potential for Affordability   Takeaways:   Building homes that are resistant to mold and other toxins is crucial for maintaining a healthy living environment. Toxic exposure, such as mold and chemicals, can have a significant impact on health and should be addressed. Considering the geographic landscape and harmonizing the energy of the environment is important when building homes. Working with building biologists and architects can help create harmonious and healthy living spaces. Being in tune with nature is important when selecting a location for a home. Proper inspection and drying of lumber is crucial to prevent mold growth. New builds often contain volatile organic compounds (VOCs) that can be harmful. Choosing low or non-VOC materials is important for a healthier indoor environment. Building a healthy home involves using non-VOC materials, proper ventilation, and natural building materials. Negative ions, which are found in nature, help create a grounding and balanced atmosphere. Air filtration systems, such as energy recovery ventilators (ERVs) and HEPA filters, are essential for maintaining clean indoor air. The cost of building a healthy home can range from 10% to 30% more than a standard home, but as more people adopt these practices, the cost may decrease. Collaboration with architects, builders, and manufacturers is crucial in promoting and implementing healthy home practices.   Summary:   Brian discusses his background in building healthy homes and how he got into the field. He shares his experience with mold exposure and the importance of creating homes that are resistant to mold and other toxins. He also talks about the impact of toxic exposure on health and the need for detoxification. Brian emphasizes the importance of considering the geographic landscape and harmonizing the energy of the environment when building homes. He highlights the role of building biologists and architects in creating harmonious and healthy living spaces. In this part of the conversation, Brian and Matthew discuss the importance of being in tune with nature when selecting a location for a home. They also talk about the prevalence of mold in new builds and the use of moldy lumber. Brian emphasizes the need for proper inspection and drying of lumber to prevent mold growth. They also discuss the presence of volatile organic compounds (VOCs) in new builds and the importance of choosing low or non-VOC materials. In this conversation, Brian from SENERGY360 discusses the importance of building a healthy home and the various factors that contribute to a healthy living environment. He emphasizes the use of non-VOC materials, proper ventilation, and natural building materials. Brian also touches on the significance of negative and positive ions in creating a balanced and grounding atmosphere. He explains the role of air filtration systems, the cost of building a healthy home, and the potential for future affordability as more people adopt these practices.   Keywords: building healthy homes, mold resistance, toxic exposure, detoxification, geographic landscape, harmonizing energy, building biologists, architects, nature, location selection, home building, mold, moldy lumber, inspection, drying, VOCs, new builds, low VOC materials, healthy home, non-VOC materials, ventilation, natural building materials, negative ions, positive ions, air filtration systems, cost of building, affordability

Ketan Umare is Co-Founder & CEO of Union AI, the scalable MLOps platform focused on AI orchestration based on the flyte open source project. Union AI has raised $29M from investors including NEA & Nava Ventures. In this episode, we dig into the differences between Union AI and Airflow, what's unique about orchestrating AI workloads, bringing software engineering practices to AI & more!

Maggie, Linus, Geoffrey, and the LS crew are reuniting for our second annual AI UX demo day in SF on Apr 28. Sign up to demo here! And don't forget tickets for the AI Engineer World's Fair — for early birds who join before keynote announcements!It's become fashionable for many AI startups to project themselves as “the next Google” - while the search engine is so 2000s, both Perplexity and Exa referred to themselves as a “research engine” or “answer engine” in our NeurIPS pod. However these searches tend to be relatively shallow, and it is challenging to zoom up and down the ladders of abstraction to garner insights. For serious researchers, this level of simple one-off search will not cut it.We've commented in our Jan 2024 Recap that Flow Engineering (simply; multi-turn processes over many-shot single prompts) seems to offer far more performance, control and reliability for a given cost budget. Our experiments with Devin and our understanding of what the new Elicit Notebooks offer a glimpse into the potential for very deep, open ended, thoughtful human-AI collaboration at scale.It starts with promptsWhen ChatGPT exploded in popularity in November 2022 everyone was turned into a prompt engineer. While generative models were good at "vibe based" outcomes (tell me a joke, write a poem, etc) with basic prompts, they struggled with more complex questions, especially in symbolic fields like math, logic, etc. Two of the most important "tricks" that people picked up on were:* Chain of Thought prompting strategy proposed by Wei et al in the “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models”. Rather than doing traditional few-shot prompting with just question and answers, adding the thinking process that led to the answer resulted in much better outcomes.* Adding "Let's think step by step" to the prompt as a way to boost zero-shot reasoning, which was popularized by Kojima et al in the Large Language Models are Zero-Shot Reasoners paper from NeurIPS 2022. This bumped accuracy from 17% to 79% compared to zero-shot.Nowadays, prompts include everything from promises of monetary rewards to… whatever the Nous folks are doing to turn a model into a world simulator. At the end of the day, the goal of prompt engineering is increasing accuracy, structure, and repeatability in the generation of a model.From prompts to agentsAs prompt engineering got more and more popular, agents (see “The Anatomy of Autonomy”) took over Twitter with cool demos and AutoGPT became the fastest growing repo in Github history. The thing about AutoGPT that fascinated people was the ability to simply put in an objective without worrying about explaining HOW to achieve it, or having to write very sophisticated prompts. The system would create an execution plan on its own, and then loop through each task. The problem with open-ended agents like AutoGPT is that 1) it's hard to replicate the same workflow over and over again 2) there isn't a way to hard-code specific steps that the agent should take without actually coding them yourself, which isn't what most people want from a product. From agents to productsPrompt engineering and open-ended agents were great in the experimentation phase, but this year more and more of these workflows are starting to become polished products. Today's guests are Andreas Stuhlmüller and Jungwon Byun of Elicit (previously Ought), an AI research assistant that they think of as “the best place to understand what is known”. Ought was a non-profit, but last September, Elicit spun off into a PBC with a $9m seed round. It is hard to quantify how much a workflow can be improved, but Elicit boasts some impressive numbers for research assistants:Just four months after launch, Elicit crossed $1M ARR, which shows how much interest there is for AI products that just work.One of the main takeaways we had from the episode is how teams should focus on supervising the process, not the output. Their philosophy at Elicit isn't to train general models, but to train models that are extremely good at focusing processes. This allows them to have pre-created steps that the user can add to their workflow (like classifying certain features that are specific to their research field) without having to write a prompt for it. And for Hamel Husain's happiness, they always show you the underlying prompt. Elicit recently announced notebooks as a new interface to interact with their products: (fun fact, they tried to implement this 4 times before they landed on the right UX! We discuss this ~33:00 in the podcast)The reasons why they picked notebooks as a UX all tie back to process:* They are systematic; once you have a instruction/prompt that works on a paper, you can run hundreds of papers through the same workflow by creating a column. Notebooks can also be edited and exported at any point during the flow.* They are transparent - Many papers include an opaque literature review as perfunctory context before getting to their novel contribution. But PDFs are “dead” and it is difficult to follow the thought process and exact research flow of the authors. Sharing “living” Elicit Notebooks opens up this process.* They are unbounded - Research is an endless stream of rabbit holes. So it must be easy to dive deeper and follow up with extra steps, without losing the ability to surface for air. We had a lot of fun recording this, and hope you have as much fun listening!AI UX in SFLong time Latent Spacenauts might remember our first AI UX meetup with Linus Lee, Geoffrey Litt, and Maggie Appleton last year. Well, Maggie has since joined Elicit, and they are all returning at the end of this month! Sign up here: https://lu.ma/aiuxAnd submit demos here! https://forms.gle/iSwiesgBkn8oo4SS8We expect the 200 seats to “sell out” fast. Attendees with demos will be prioritized.Show Notes* Elicit* Ought (their previous non-profit)* “Pivoting” with GPT-4* Elicit notebooks launch* Charlie* Andreas' BlogTimestamps* [00:00:00] Introductions* [00:07:45] How Johan and Andreas Joined Forces to Create Elicit* [00:10:26] Why Products > Research* [00:15:49] The Evolution of Elicit's Product* [00:19:44] Automating Literature Review Workflow* [00:22:48] How GPT-3 to GPT-4 Changed Things* [00:25:37] Managing LLM Pricing and Performance* [00:31:07] Open vs. Closed: Elicit's Approach to Model Selection* [00:31:56] Moving to Notebooks* [00:39:11] Elicit's Budget for Model Queries and Evaluations* [00:41:44] Impact of Long Context Windows* [00:47:19] Underrated Features and Surprising Applications* [00:51:35] Driving Systematic and Efficient Research* [00:53:00] Elicit's Team Growth and Transition to a Public Benefit Corporation* [00:55:22] Building AI for GoodFull Interview on YouTubeAs always, a plug for our youtube version for the 80% of communication that is nonverbal:TranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space Podcast. This is Alessio, partner and CTO at Residence at Decibel Partners, and I'm joined by my co-host Swyx, founder of Smol AI.Swyx [00:00:15]: Hey, and today we are back in the studio with Andreas and Jungwon from Elicit. Welcome.Jungwon [00:00:20]: Thanks guys.Andreas [00:00:21]: It's great to be here.Swyx [00:00:22]: Yeah. So I'll introduce you separately, but also, you know, we'd love to learn a little bit more about you personally. So Andreas, it looks like you started Elicit first, Jungwon joined later.Andreas [00:00:32]: That's right. For all intents and purposes, the Elicit and also the Ought that existed before then were very different from what I started. So I think it's like fair to say that you co-founded it.Swyx [00:00:43]: Got it. And Jungwon, you're a co-founder and COO of Elicit now.Jungwon [00:00:46]: Yeah, that's right.Swyx [00:00:47]: So there's a little bit of a history to this. I'm not super aware of like the sort of journey. I was aware of OTT and Elicit as sort of a nonprofit type situation. And recently you turned into like a B Corp, Public Benefit Corporation. So yeah, maybe if you want, you could take us through that journey of finding the problem. You know, obviously you're working together now. So like, how do you get together to decide to leave your startup career to join him?Andreas [00:01:10]: Yeah, it's truly a very long journey. I guess truly, it kind of started in Germany when I was born. So even as a kid, I was always interested in AI, like I kind of went to the library. There were books about how to write programs in QBasic and like some of them talked about how to implement chatbots.Jungwon [00:01:27]: To be clear, he grew up in like a tiny village on the outskirts of Munich called Dinkelschirben, where it's like a very, very idyllic German village.Andreas [00:01:36]: Yeah, important to the story. So basically, the main thing is I've kind of always been thinking about AI my entire life and been thinking about, well, at some point, this is going to be a huge deal. It's going to be transformative. How can I work on it? And was thinking about it from when I was a teenager, after high school did a year where I started a startup with the intention to become rich. And then once I'm rich, I can affect the trajectory of AI. Did not become rich, decided to go back to college and study cognitive science there, which was like the closest thing I could find at the time to AI. In the last year of college, moved to the US to do a PhD at MIT, working on broadly kind of new programming languages for AI because it kind of seemed like the existing languages were not great at expressing world models and learning world models doing Bayesian inference. Was always thinking about, well, ultimately, the goal is to actually build tools that help people reason more clearly, ask and answer better questions and make better decisions. But for a long time, it seemed like the technology to put reasoning in machines just wasn't there. Initially, at the end of my postdoc at Stanford, I was thinking about, well, what to do? I think the standard path is you become an academic and do research. But it's really hard to actually build interesting tools as an academic. You can't really hire great engineers. Everything is kind of on a paper-to-paper timeline. And so I was like, well, maybe I should start a startup, pursued that for a little bit. But it seemed like it was too early because you could have tried to do an AI startup, but probably would not have been this kind of AI startup we're seeing now. So then decided to just start a nonprofit research lab that's going to do research for a while until we better figure out how to do thinking in machines. And that was odd. And then over time, it became clear how to actually build actual tools for reasoning. And only over time, we developed a better way to... I'll let you fill in some of the details here.Jungwon [00:03:26]: Yeah. So I guess my story maybe starts around 2015. I kind of wanted to be a founder for a long time, and I wanted to work on an idea that stood the test of time for me, like an idea that stuck with me for a long time. And starting in 2015, actually, originally, I became interested in AI-based tools from the perspective of mental health. So there are a bunch of people around me who are really struggling. One really close friend in particular is really struggling with mental health and didn't have any support, and it didn't feel like there was anything before kind of like getting hospitalized that could just help her. And so luckily, she came and stayed with me for a while, and we were just able to talk through some things. But it seemed like lots of people might not have that resource, and something maybe AI-enabled could be much more scalable. I didn't feel ready to start a company then, that's 2015. And I also didn't feel like the technology was ready. So then I went into FinTech and kind of learned how to do the tech thing. And then in 2019, I felt like it was time for me to just jump in and build something on my own I really wanted to create. And at the time, I looked around at tech and felt like not super inspired by the options. I didn't want to have a tech career ladder, or I didn't want to climb the career ladder. There are two kind of interesting technologies at the time, there was AI and there was crypto. And I was like, well, the AI people seem like a little bit more nice, maybe like slightly more trustworthy, both super exciting, but threw my bet in on the AI side. And then I got connected to Andreas. And actually, the way he was thinking about pursuing the research agenda at OTT was really compatible with what I had envisioned for an ideal AI product, something that helps kind of take down really complex thinking, overwhelming thoughts and breaks it down into small pieces. And then this kind of mission that we need AI to help us figure out what we ought to do was really inspiring, right? Yeah, because I think it was clear that we were building the most powerful optimizer of our time. But as a society, we hadn't figured out how to direct that optimization potential. And if you kind of direct tremendous amounts of optimization potential at the wrong thing, that's really disastrous. So the goal of OTT was make sure that if we build the most transformative technology of our lifetime, it can be used for something really impactful, like good reasoning, like not just generating ads. My background was in marketing, but like, so I was like, I want to do more than generate ads with this. But also if these AI systems get to be super intelligent enough that they are doing this really complex reasoning, that we can trust them, that they are aligned with us and we have ways of evaluating that they're doing the right thing. So that's what OTT did. We did a lot of experiments, you know, like I just said, before foundation models really like took off. A lot of the issues we were seeing were more in reinforcement learning, but we saw a future where AI would be able to do more kind of logical reasoning, not just kind of extrapolate from numerical trends. We actually kind of set up experiments with people where kind of people stood in as super intelligent systems and we effectively gave them context windows. So they would have to like read a bunch of text and one person would get less text and one person would get all the texts and the person with less text would have to evaluate the work of the person who could read much more. So like in a world we were basically simulating, like in 2018, 2019, a world where an AI system could read significantly more than you and you as the person who couldn't read that much had to evaluate the work of the AI system. Yeah. So there's a lot of the work we did. And from that, we kind of iterated on the idea of breaking complex tasks down into smaller tasks, like complex tasks, like open-ended reasoning, logical reasoning into smaller tasks so that it's easier to train AI systems on them. And also so that it's easier to evaluate the work of the AI system when it's done. And then also kind of, you know, really pioneered this idea, the importance of supervising the process of AI systems, not just the outcomes. So a big part of how Elicit is built is we're very intentional about not just throwing a ton of data into a model and training it and then saying, cool, here's like scientific output. Like that's not at all what we do. Our approach is very much like, what are the steps that an expert human does or what is like an ideal process as granularly as possible, let's break that down and then train AI systems to perform each of those steps very robustly. When you train like that from the start, after the fact, it's much easier to evaluate, it's much easier to troubleshoot at each point. Like where did something break down? So yeah, we were working on those experiments for a while. And then at the start of 2021, decided to build a product.Swyx [00:07:45]: Do you mind if I, because I think you're about to go into more modern thought and Elicit. And I just wanted to, because I think a lot of people are in where you were like sort of 2018, 19, where you chose a partner to work with. Yeah. Right. And you didn't know him. Yeah. Yeah. You were just kind of cold introduced. A lot of people are cold introduced. Yeah. Never work with them. I assume you had a lot, a lot of other options, right? Like how do you advise people to make those choices?Jungwon [00:08:10]: We were not totally cold introduced. So one of our closest friends introduced us. And then Andreas had written a lot on the OTT website, a lot of blog posts, a lot of publications. And I just read it and I was like, wow, this sounds like my writing. And even other people, some of my closest friends I asked for advice from, they were like, oh, this sounds like your writing. But I think I also had some kind of like things I was looking for. I wanted someone with a complimentary skillset. I want someone who was very values aligned. And yeah, that was all a good fit.Andreas [00:08:38]: We also did a pretty lengthy mutual evaluation process where we had a Google doc where we had all kinds of questions for each other. And I think it ended up being around 50 pages or so of like various like questions and back and forth.Swyx [00:08:52]: Was it the YC list? There's some lists going around for co-founder questions.Andreas [00:08:55]: No, we just made our own questions. But I guess it's probably related in that you ask yourself, what are the values you care about? How would you approach various decisions and things like that?Jungwon [00:09:04]: I shared like all of my past performance reviews. Yeah. Yeah.Swyx [00:09:08]: And he never had any. No.Andreas [00:09:10]: Yeah.Swyx [00:09:11]: Sorry, I just had to, a lot of people are going through that phase and you kind of skipped over it. I was like, no, no, no, no. There's like an interesting story.Jungwon [00:09:20]: Yeah.Alessio [00:09:21]: Yeah. Before we jump into what a list it is today, the history is a bit counterintuitive. So you start with figuring out, oh, if we had a super powerful model, how would we align it? But then you were actually like, well, let's just build the product so that people can actually leverage it. And I think there are a lot of folks today that are now back to where you were maybe five years ago that are like, oh, what if this happens rather than focusing on actually building something useful with it? What clicked for you to like move into a list and then we can cover that story too.Andreas [00:09:49]: I think in many ways, the approach is still the same because the way we are building illicit is not let's train a foundation model to do more stuff. It's like, let's build a scaffolding such that we can deploy powerful models to good ends. I think it's different now in that we actually have like some of the models to plug in. But if in 2017, we had had the models, we could have run the same experiments we did run with humans back then, just with models. And so in many ways, our philosophy is always, let's think ahead to the future of what models are going to exist in one, two years or longer. And how can we make it so that they can actually be deployed in kind of transparent, controllableJungwon [00:10:26]: ways? I think motivationally, we both are kind of product people at heart. The research was really important and it didn't make sense to build a product at that time. But at the end of the day, the thing that always motivated us is imagining a world where high quality reasoning is really abundant and AI is a technology that's going to get us there. And there's a way to guide that technology with research, but we can have a more direct effect through product because with research, you publish the research and someone else has to implement that into the product and the product felt like a more direct path. And we wanted to concretely have an impact on people's lives. Yeah, I think the kind of personally, the motivation was we want to build for people.Swyx [00:11:03]: Yep. And then just to recap as well, like the models you were using back then were like, I don't know, would they like BERT type stuff or T5 or I don't know what timeframe we're talking about here.Andreas [00:11:14]: I guess to be clear, at the very beginning, we had humans do the work. And then I think the first models that kind of make sense were TPT-2 and TNLG and like Yeah, early generative models. We do also use like T5 based models even now started with TPT-2.Swyx [00:11:30]: Yeah, cool. I'm just kind of curious about like, how do you start so early? You know, like now it's obvious where to start, but back then it wasn't.Jungwon [00:11:37]: Yeah, I used to nag Andreas a lot. I was like, why are you talking to this? I don't know. I felt like TPT-2 is like clearly can't do anything. And I was like, Andreas, you're wasting your time, like playing with this toy. But yeah, he was right.Alessio [00:11:50]: So what's the history of what Elicit actually does as a product? You recently announced that after four months, you get to a million in revenue. Obviously, a lot of people use it, get a lot of value, but it would initially kind of like structured data extraction from papers. Then you had kind of like concept grouping. And today, it's maybe like a more full stack research enabler, kind of like paper understander platform. What's the definitive definition of what Elicit is? And how did you get here?Jungwon [00:12:15]: Yeah, we say Elicit is an AI research assistant. I think it will continue to evolve. That's part of why we're so excited about building and research, because there's just so much space. I think the current phase we're in right now, we talk about it as really trying to make Elicit the best place to understand what is known. So it's all a lot about like literature summarization. There's a ton of information that the world already knows. It's really hard to navigate, hard to make it relevant. So a lot of it is around document discovery and processing and analysis. I really kind of want to import some of the incredible productivity improvements we've seen in software engineering and data science and into research. So it's like, how can we make researchers like data scientists of text? That's why we're launching this new set of features called Notebooks. It's very much inspired by computational notebooks, like Jupyter Notebooks, you know, DeepNode or Colab, because they're so powerful and so flexible. And ultimately, when people are trying to get to an answer or understand insight, they're kind of like manipulating evidence and information. Today, that's all packaged in PDFs, which are super brittle. So with language models, we can decompose these PDFs into their underlying claims and evidence and insights, and then let researchers mash them up together, remix them and analyze them together. So yeah, I would say quite simply, overall, Elicit is an AI research assistant. Right now we're focused on text-based workflows, but long term, really want to kind of go further and further into reasoning and decision making.Alessio [00:13:35]: And when you say AI research assistant, this is kind of meta research. So researchers use Elicit as a research assistant. It's not a generic you-can-research-anything type of tool, or it could be, but like, what are people using it for today?Andreas [00:13:49]: Yeah. So specifically in science, a lot of people use human research assistants to do things. You tell your grad student, hey, here are a couple of papers. Can you look at all of these, see which of these have kind of sufficiently large populations and actually study the disease that I'm interested in, and then write out like, what are the experiments they did? What are the interventions they did? What are the outcomes? And kind of organize that for me. And the first phase of understanding what is known really focuses on automating that workflow because a lot of that work is pretty rote work. I think it's not the kind of thing that we need humans to do. Language models can do it. And then if language models can do it, you can obviously scale it up much more than a grad student or undergrad research assistant would be able to do.Jungwon [00:14:31]: Yeah. The use cases are pretty broad. So we do have a very large percent of our users are just using it personally or for a mix of personal and professional things. People who care a lot about health or biohacking or parents who have children with a kind of rare disease and want to understand the literature directly. So there is an individual kind of consumer use case. We're most focused on the power users. So that's where we're really excited to build. So Lissette was very much inspired by this workflow in literature called systematic reviews or meta-analysis, which is basically the human state of the art for summarizing scientific literature. And it typically involves like five people working together for over a year. And they kind of first start by trying to find the maximally comprehensive set of papers possible. So it's like 10,000 papers. And they kind of systematically narrow that down to like hundreds or 50 extract key details from every single paper. Usually have two people doing it, like a third person reviewing it. So it's like an incredibly laborious, time consuming process, but you see it in every single domain. So in science, in machine learning, in policy, because it's so structured and designed to be reproducible, it's really amenable to automation. So that's kind of the workflow that we want to automate first. And then you make that accessible for any question and make these really robust living summaries of science. So yeah, that's one of the workflows that we're starting with.Alessio [00:15:49]: Our previous guest, Mike Conover, he's building a new company called Brightwave, which is an AI research assistant for financial research. How do you see the future of these tools? Does everything converge to like a God researcher assistant, or is every domain going to have its own thing?Andreas [00:16:03]: I think that's a good and mostly open question. I do think there are some differences across domains. For example, some research is more quantitative data analysis, and other research is more high level cross domain thinking. And we definitely want to contribute to the broad generalist reasoning type space. Like if researchers are making discoveries often, it's like, hey, this thing in biology is actually analogous to like these equations in economics or something. And that's just fundamentally a thing that where you need to reason across domains. At least within research, I think there will be like one best platform more or less for this type of generalist research. I think there may still be like some particular tools like for genomics, like particular types of modules of genes and proteins and whatnot. But for a lot of the kind of high level reasoning that humans do, I think that is a more of a winner type all thing.Swyx [00:16:52]: I wanted to ask a little bit deeper about, I guess, the workflow that you mentioned. I like that phrase. I see that in your UI now, but that's as it is today. And I think you were about to tell us about how it was in 2021 and how it may be progressed. How has this workflow evolved over time?Jungwon [00:17:07]: Yeah. So the very first version of Elicit actually wasn't even a research assistant. It was a forecasting assistant. So we set out and we were thinking about, you know, what are some of the most impactful types of reasoning that if we could scale up, AI would really transform the world. We actually started with literature review, but we're like, oh, so many people are going to build literature review tools. So let's start there. So then we focused on geopolitical forecasting. So I don't know if you're familiar with like manifold or manifold markets. That kind of stuff. Before manifold. Yeah. Yeah. I'm not predicting relationships. We're predicting like, is China going to invade Taiwan?Swyx [00:17:38]: Markets for everything.Andreas [00:17:39]: Yeah. That's a relationship.Swyx [00:17:41]: Yeah.Jungwon [00:17:42]: Yeah. It's true. And then we worked on that for a while. And then after GPT-3 came out, I think by that time we realized that originally we were trying to help people convert their beliefs into probability distributions. And so take fuzzy beliefs, but like model them more concretely. And then after a few months of iterating on that, just realize, oh, the thing that's blocking people from making interesting predictions about important events in the world is less kind of on the probabilistic side and much more on the research side. And so that kind of combined with the very generalist capabilities of GPT-3 prompted us to make a more general research assistant. Then we spent a few months iterating on what even is a research assistant. So we would embed with different researchers. We built data labeling workflows in the beginning, kind of right off the bat. We built ways to find experts in a field and like ways to ask good research questions. So we just kind of iterated through a lot of workflows and no one else was really building at this time. And it was like very quick to just do some prompt engineering and see like what is a task that is at the intersection of what's technologically capable and like important for researchers. And we had like a very nondescript landing page. It said nothing. But somehow people were signing up and we had to sign a form that was like, why are you here? And everyone was like, I need help with literature review. And we're like, oh, literature review. That sounds so hard. I don't even know what that means. We're like, we don't want to work on it. But then eventually we were like, okay, everyone is saying literature review. It's overwhelmingly people want to-Swyx [00:19:02]: And all domains, not like medicine or physics or just all domains. Yeah.Jungwon [00:19:06]: And we also kind of personally knew literature review was hard. And if you look at the graphs for academic literature being published every single month, you guys know this in machine learning, it's like up into the right, like superhuman amounts of papers. So we're like, all right, let's just try it. I was really nervous, but Andreas was like, this is kind of like the right problem space to jump into, even if we don't know what we're doing. So my take was like, fine, this feels really scary, but let's just launch a feature every single week and double our user numbers every month. And if we can do that, we'll fail fast and we will find something. I was worried about like getting lost in the kind of academic white space. So the very first version was actually a weekend prototype that Andreas made. Do you want to explain how that worked?Andreas [00:19:44]: I mostly remember that it was really bad. The thing I remember is you entered a question and it would give you back a list of claims. So your question could be, I don't know, how does creatine affect cognition? It would give you back some claims that are to some extent based on papers, but they were often irrelevant. The papers were often irrelevant. And so we ended up soon just printing out a bunch of examples of results and putting them up on the wall so that we would kind of feel the constant shame of having such a bad product and would be incentivized to make it better. And I think over time it has gotten a lot better, but I think the initial version was like really very bad. Yeah.Jungwon [00:20:20]: But it was basically like a natural language summary of an abstract, like kind of a one sentence summary, and which we still have. And then as we learned kind of more about this systematic review workflow, we started expanding the capability so that you could extract a lot more data from the papers and do more with that.Swyx [00:20:33]: And were you using like embeddings and cosine similarity, that kind of stuff for retrieval, or was it keyword based?Andreas [00:20:40]: I think the very first version didn't even have its own search engine. I think the very first version probably used the Semantic Scholar or API or something similar. And only later when we discovered that API is not very semantic, we then built our own search engine that has helped a lot.Swyx [00:20:58]: And then we're going to go into like more recent products stuff, but like, you know, I think you seem the more sort of startup oriented business person and you seem sort of more ideologically like interested in research, obviously, because of your PhD. What kind of market sizing were you guys thinking? Right? Like, because you're here saying like, we have to double every month. And I'm like, I don't know how you make that conclusion from this, right? Especially also as a nonprofit at the time.Jungwon [00:21:22]: I mean, market size wise, I felt like in this space where so much was changing and it was very unclear what of today was actually going to be true tomorrow. We just like really rested a lot on very, very simple fundamental principles, which is like, if you can understand the truth, that is very economically beneficial and valuable. If you like know the truth.Swyx [00:21:42]: On principle.Jungwon [00:21:43]: Yeah. That's enough for you. Yeah. Research is the key to many breakthroughs that are very commercially valuable.Swyx [00:21:47]: Because my version of it is students are poor and they don't pay for anything. Right? But that's obviously not true. As you guys have found out. But you had to have some market insight for me to have believed that, but you skipped that.Andreas [00:21:58]: Yeah. I remember talking to VCs for our seed round. A lot of VCs were like, you know, researchers, they don't have any money. Why don't you build legal assistant? I think in some short sighted way, maybe that's true. But I think in the long run, R&D is such a big space of the economy. I think if you can substantially improve how quickly people find new discoveries or avoid controlled trials that don't go anywhere, I think that's just huge amounts of money. And there are a lot of questions obviously about between here and there. But I think as long as the fundamental principle is there, we were okay with that. And I guess we found some investors who also were. Yeah.Swyx [00:22:35]: Congrats. I mean, I'm sure we can cover the sort of flip later. I think you're about to start us on like GPT-3 and how that changed things for you. It's funny. I guess every major GPT version, you have some big insight. Yeah.Jungwon [00:22:48]: Yeah. I mean, what do you think?Andreas [00:22:51]: I think it's a little bit less true for us than for others, because we always believed that there will basically be human level machine work. And so it is definitely true that in practice for your product, as new models come out, your product starts working better, you can add some features that you couldn't add before. But I don't think we really ever had the moment where we were like, oh, wow, that is super unanticipated. We need to do something entirely different now from what was on the roadmap.Jungwon [00:23:21]: I think GPT-3 was a big change because it kind of said, oh, now is the time that we can use AI to build these tools. And then GPT-4 was maybe a little bit more of an extension of GPT-3. GPT-3 over GPT-2 was like qualitative level shift. And then GPT-4 was like, okay, great. Now it's like more accurate. We're more accurate on these things. We can answer harder questions. But the shape of the product had already taken place by that time.Swyx [00:23:44]: I kind of want to ask you about this sort of pivot that you've made. But I guess that was just a way to sell what you were doing, which is you're adding extra features on grouping by concepts. The GPT-4 pivot, quote unquote pivot that you-Jungwon [00:23:55]: Oh, yeah, yeah, exactly. Right, right, right. Yeah. Yeah. When we launched this workflow, now that GPT-4 was available, basically Elisa was at a place where we have very tabular interfaces. So given a table of papers, you can extract data across all the tables. But you kind of want to take the analysis a step further. Sometimes what you'd care about is not having a list of papers, but a list of arguments, a list of effects, a list of interventions, a list of techniques. And so that's one of the things we're working on is now that you've extracted this information in a more structured way, can you pivot it or group by whatever the information that you extracted to have more insight first information still supported by the academic literature?Swyx [00:24:33]: Yeah, that was a big revelation when I saw it. Basically, I think I'm very just impressed by how first principles, your ideas around what the workflow is. And I think that's why you're not as reliant on like the LLM improving, because it's actually just about improving the workflow that you would recommend to people. Today we might call it an agent, I don't know, but you're not relying on the LLM to drive it. It's relying on this is the way that Elicit does research. And this is what we think is most effective based on talking to our users.Jungwon [00:25:01]: The problem space is still huge. Like if it's like this big, we are all still operating at this tiny part, bit of it. So I think about this a lot in the context of moats, people are like, oh, what's your moat? What happens if GPT-5 comes out? It's like, if GPT-5 comes out, there's still like all of this other space that we can go into. So I think being really obsessed with the problem, which is very, very big, has helped us like stay robust and just kind of directly incorporate model improvements and they keep going.Swyx [00:25:26]: And then I first encountered you guys with Charlie, you can tell us about that project. Basically, yeah. Like how much did cost become a concern as you're working more and more with OpenAI? How do you manage that relationship?Jungwon [00:25:37]: Let me talk about who Charlie is. And then you can talk about the tech, because Charlie is a special character. So Charlie, when we found him was, had just finished his freshman year at the University of Warwick. And I think he had heard about us on some discord. And then he applied and we were like, wow, who is this freshman? And then we just saw that he had done so many incredible side projects. And we were actually on a team retreat in Barcelona visiting our head of engineering at that time. And everyone was talking about this wonder kid or like this kid. And then on our take home project, he had done like the best of anyone to that point. And so people were just like so excited to hire him. So we hired him as an intern and they were like, Charlie, what if you just dropped out of school? And so then we convinced him to take a year off. And he was just incredibly productive. And I think the thing you're referring to is at the start of 2023, Anthropic kind of launched their constitutional AI paper. And within a few days, I think four days, he had basically implemented that in production. And then we had it in app a week or so after that. And he has since kind of contributed to major improvements, like cutting costs down to a tenth of what they were really large scale. But yeah, you can talk about the technical stuff. Yeah.Andreas [00:26:39]: On the constitutional AI project, this was for abstract summarization, where in illicit, if you run a query, it'll return papers to you, and then it will summarize each paper with respect to your query for you on the fly. And that's a really important part of illicit because illicit does it so much. If you run a few searches, it'll have done it a few hundred times for you. And so we cared a lot about this both being fast, cheap, and also very low on hallucination. I think if illicit hallucinates something about the abstract, that's really not good. And so what Charlie did in that project was create a constitution that expressed what are the attributes of a good summary? Everything in the summary is reflected in the actual abstract, and it's like very concise, et cetera, et cetera. And then used RLHF with a model that was trained on the constitution to basically fine tune a better summarizer on an open source model. Yeah. I think that might still be in use.Jungwon [00:27:34]: Yeah. Yeah, definitely. Yeah. I think at the time, the models hadn't been trained at all to be faithful to a text. So they were just generating. So then when you ask them a question, they tried too hard to answer the question and didn't try hard enough to answer the question given the text or answer what the text said about the question. So we had to basically teach the models to do that specific task.Swyx [00:27:54]: How do you monitor the ongoing performance of your models? Not to get too LLM-opsy, but you are one of the larger, more well-known operations doing NLP at scale. I guess effectively, you have to monitor these things and nobody has a good answer that I talk to.Andreas [00:28:10]: I don't think we have a good answer yet. I think the answers are actually a little bit clearer on the just kind of basic robustness side of where you can import ideas from normal software engineering and normal kind of DevOps. You're like, well, you need to monitor kind of latencies and response times and uptime and whatnot.Swyx [00:28:27]: I think when we say performance, it's more about hallucination rate, isn't it?Andreas [00:28:30]: And then things like hallucination rate where I think there, the really important thing is training time. So we care a lot about having our own internal benchmarks for model development that reflect the distribution of user queries so that we can know ahead of time how well is the model going to perform on different types of tasks. So the tasks being summarization, question answering, given a paper, ranking. And for each of those, we want to know what's the distribution of things the model is going to see so that we can have well-calibrated predictions on how well the model is going to do in production. And I think, yeah, there's some chance that there's distribution shift and actually the things users enter are going to be different. But I think that's much less important than getting the kind of training right and having very high quality, well-vetted data sets at training time.Jungwon [00:29:18]: I think we also end up effectively monitoring by trying to evaluate new models as they come out. And so that kind of prompts us to go through our eval suite every couple of months. And every time a new model comes out, we have to see how is this performing relative to production and what we currently have.Swyx [00:29:32]: Yeah. I mean, since we're on this topic, any new models that have really caught your eye this year?Jungwon [00:29:37]: Like Claude came out with a bunch. Yeah. I think Claude is pretty, I think the team's pretty excited about Claude. Yeah.Andreas [00:29:41]: Specifically, Claude Haiku is like a good point on the kind of Pareto frontier. It's neither the cheapest model, nor is it the most accurate, most high quality model, but it's just like a really good trade-off between cost and accuracy.Swyx [00:29:57]: You apparently have to 10-shot it to make it good. I tried using Haiku for summarization, but zero-shot was not great. Then they were like, you know, it's a skill issue, you have to try harder.Jungwon [00:30:07]: I think GPT-4 unlocked tables for us, processing data from tables, which was huge. GPT-4 Vision.Andreas [00:30:13]: Yeah.Swyx [00:30:14]: Yeah. Did you try like Fuyu? I guess you can't try Fuyu because it's non-commercial. That's the adept model.Jungwon [00:30:19]: Yeah.Swyx [00:30:20]: We haven't tried that one. Yeah. Yeah. Yeah. But Claude is multimodal as well. Yeah. I think the interesting insight that we got from talking to David Luan, who is CEO of multimodality has effectively two different flavors. One is we recognize images from a camera in the outside natural world. And actually the more important multimodality for knowledge work is screenshots and PDFs and charts and graphs. So we need a new term for that kind of multimodality.Andreas [00:30:45]: But is the claim that current models are good at one or the other? Yeah.Swyx [00:30:50]: They're over-indexed because of the history of computer vision is Coco, right? So now we're like, oh, actually, you know, screens are more important, OCR, handwriting. You mentioned a lot of like closed model lab stuff, and then you also have like this open source model fine tuning stuff. Like what is your workload now between closed and open? It's a good question.Andreas [00:31:07]: I think- Is it half and half? It's a-Swyx [00:31:10]: Is that even a relevant question or not? Is this a nonsensical question?Andreas [00:31:13]: It depends a little bit on like how you index, whether you index by like computer cost or number of queries. I'd say like in terms of number of queries, it's maybe similar. In terms of like cost and compute, I think the closed models make up more of the budget since the main cases where you want to use closed models are cases where they're just smarter, where no existing open source models are quite smart enough.Jungwon [00:31:35]: Yeah. Yeah.Alessio [00:31:37]: We have a lot of interesting technical questions to go in, but just to wrap the kind of like UX evolution, now you have the notebooks. We talked a lot about how chatbots are not the final frontier, you know? How did you decide to get into notebooks, which is a very iterative kind of like interactive interface and yeah, maybe learnings from that.Jungwon [00:31:56]: Yeah. This is actually our fourth time trying to make this work. Okay. I think the first time was probably in early 2021. I think because we've always been obsessed with this idea of task decomposition and like branching, we always wanted a tool that could be kind of unbounded where you could keep going, could do a lot of branching where you could kind of apply language model operations or computations on other tasks. So in 2021, we had this thing called composite tasks where you could use GPT-3 to brainstorm a bunch of research questions and then take each research question and decompose those further into sub questions. This kind of, again, that like task decomposition tree type thing was always very exciting to us, but that was like, it didn't work and it was kind of overwhelming. Then at the end of 22, I think we tried again and at that point we were thinking, okay, we've done a lot with this literature review thing. We also want to start helping with kind of adjacent domains and different workflows. Like we want to help more with machine learning. What does that look like? And as we were thinking about it, we're like, well, there are so many research workflows. How do we not just build three new workflows into Elicit, but make Elicit really generic to lots of workflows? What is like a generic composable system with nice abstractions that can like scale to all these workflows? So we like iterated on that a bunch and then didn't quite narrow the problem space enough or like quite get to what we wanted. And then I think it was at the beginning of 2023 where we're like, wow, computational notebooks kind of enable this, where they have a lot of flexibility, but kind of robust primitives such that you can extend the workflow and it's not limited. It's not like you ask a query, you get an answer, you're done. You can just constantly keep building on top of that. And each little step seems like a really good unit of work for the language model. And also there was just like really helpful to have a bit more preexisting work to emulate. Yeah, that's kind of how we ended up at computational notebooks for Elicit.Andreas [00:33:44]: Maybe one thing that's worth making explicit is the difference between computational notebooks and chat, because on the surface, they seem pretty similar. It's kind of this iterative interaction where you add stuff. In both cases, you have a back and forth between you enter stuff and then you get some output and then you enter stuff. But the important difference in our minds is with notebooks, you can define a process. So in data science, you can be like, here's like my data analysis process that takes in a CSV and then does some extraction and then generates a figure at the end. And you can prototype it using a small CSV and then you can run it over a much larger CSV later. And similarly, the vision for notebooks in our case is to not make it this like one-off chat interaction, but to allow you to then say, if you start and first you're like, okay, let me just analyze a few papers and see, do I get to the correct conclusions for those few papers? Can I then later go back and say, now let me run this over 10,000 papers now that I've debugged the process using a few papers. And that's an interaction that doesn't fit quite as well into the chat framework because that's more for kind of quick back and forth interaction.Alessio [00:34:49]: Do you think in notebooks, it's kind of like structure, editable chain of thought, basically step by step? Like, is that kind of where you see this going? And then are people going to reuse notebooks as like templates? And maybe in traditional notebooks, it's like cookbooks, right? You share a cookbook, you can start from there. Is this similar in Elizit?Andreas [00:35:06]: Yeah, that's exactly right. So that's our hope that people will build templates, share them with other people. I think chain of thought is maybe still like kind of one level lower on the abstraction hierarchy than we would think of notebooks. I think we'll probably want to think about more semantic pieces like a building block is more like a paper search or an extraction or a list of concepts. And then the model's detailed reasoning will probably often be one level down. You always want to be able to see it, but you don't always want it to be front and center.Alessio [00:35:36]: Yeah, what's the difference between a notebook and an agent? Since everybody always asks me, what's an agent? Like how do you think about where the line is?Andreas [00:35:44]: Yeah, it's an interesting question. In the notebook world, I would generally think of the human as the agent in the first iteration. So you have the notebook and the human kind of adds little action steps. And then the next point on this kind of progress gradient is, okay, now you can use language models to predict which action would you take as a human. And at some point, you're probably going to be very good at this, you'll be like, okay, in some cases I can, with 99.9% accuracy, predict what you do. And then you might as well just execute it, like why wait for the human? And eventually, as you get better at this, that will just look more and more like agents taking actions as opposed to you doing the thing. I think templates are a specific case of this where you're like, okay, well, there's just particular sequences of actions that you often want to chunk and have available as primitives, just like in normal programming. And those, you can view them as action sequences of agents, or you can view them as more normal programming language abstraction thing. And I think those are two valid views. Yeah.Alessio [00:36:40]: How do you see this change as, like you said, the models get better and you need less and less human actual interfacing with the model, you just get the results? Like how does the UX and the way people perceive it change?Jungwon [00:36:52]: Yeah, I think this kind of interaction paradigms for evaluation is not really something the internet has encountered yet, because up to now, the internet has all been about getting data and work from people. So increasingly, I really want kind of evaluation, both from an interface perspective and from like a technical perspective and operation perspective to be a superpower for Elicit, because I think over time, models will do more and more of the work, and people will have to do more and more of the evaluation. So I think, yeah, in terms of the interface, some of the things we have today, you know, for every kind of language model generation, there's some citation back, and we kind of try to highlight the ground truth in the paper that is most relevant to whatever Elicit said, and make it super easy so that you can click on it and quickly see in context and validate whether the text actually supports the answer that Elicit gave. So I think we'd probably want to scale things up like that, like the ability to kind of spot check the model's work super quickly, scale up interfaces like that. And-Swyx [00:37:44]: Who would spot check? The user?Jungwon [00:37:46]: Yeah, to start, it would be the user. One of the other things we do is also kind of flag the model's uncertainty. So we have models report out, how confident are you that this was the sample size of this study? The model's not sure, we throw a flag. And so the user knows to prioritize checking that. So again, we can kind of scale that up. So when the model's like, well, I searched this on Google, I'm not sure if that was the right thing. I have an uncertainty flag, and the user can go and be like, oh, okay, that was actually the right thing to do or not.Swyx [00:38:10]: I've tried to do uncertainty readings from models. I don't know if you have this live. You do? Yeah. Because I just didn't find them reliable because they just hallucinated their own uncertainty. I would love to base it on log probs or something more native within the model rather than generated. But okay, it sounds like they scale properly for you. Yeah.Jungwon [00:38:30]: We found it to be pretty calibrated. It varies on the model.Andreas [00:38:32]: I think in some cases, we also use two different models for the uncertainty estimates than for the question answering. So one model would say, here's my chain of thought, here's my answer. And then a different type of model. Let's say the first model is Llama, and let's say the second model is GPT-3.5. And then the second model just looks over the results and is like, okay, how confident are you in this? And I think sometimes using a different model can be better than using the same model. Yeah.Swyx [00:38:58]: On the topic of models, evaluating models, obviously you can do that all day long. What's your budget? Because your queries fan out a lot. And then you have models evaluating models. One person typing in a question can lead to a thousand calls.Andreas [00:39:11]: It depends on the project. So if the project is basically a systematic review that otherwise human research assistants would do, then the project is basically a human equivalent spend. And the spend can get quite large for those projects. I don't know, let's say $100,000. In those cases, you're happier to spend compute then in the kind of shallow search case where someone just enters a question because, I don't know, maybe I heard about creatine. What's it about? Probably don't want to spend a lot of compute on that. This sort of being able to invest more or less compute into getting more or less accurate answers is I think one of the core things we care about. And that I think is currently undervalued in the AI space. I think currently you can choose which model you want and you can sometimes, I don't know, you'll tip it and it'll try harder or you can try various things to get it to work harder. But you don't have great ways of converting willingness to spend into better answers. And we really want to build a product that has this sort of unbounded flavor where if you care about it a lot, you should be able to get really high quality answers, really double checked in every way.Alessio [00:40:14]: And you have a credits-based pricing. So unlike most products, it's not a fixed monthly fee.Jungwon [00:40:19]: Right, exactly. So some of the higher costs are tiered. So for most casual users, they'll just get the abstract summary, which is kind of an open source model. Then you can add more columns, which have more extractions and these uncertainty features. And then you can also add the same columns in high accuracy mode, which also parses the table. So we kind of stack the complexity on the calls.Swyx [00:40:39]: You know, the fun thing you can do with a credit system, which is data for data, basically you can give people more credits if they give data back to you. I don't know if you've already done that. We've thought about something like this.Jungwon [00:40:49]: It's like if you don't have money, but you have time, how do you exchange that?Swyx [00:40:54]: It's a fair trade.Jungwon [00:40:55]: I think it's interesting. We haven't quite operationalized it. And then, you know, there's been some kind of like adverse selection. Like, you know, for example, it would be really valuable to get feedback on our model. So maybe if you were willing to give more robust feedback on our results, we could give you credits or something like that. But then there's kind of this, will people take it seriously? And you want the good people. Exactly.Swyx [00:41:11]: Can you tell who are the good people? Not right now.Jungwon [00:41:13]: But yeah, maybe at the point where we can, we can offer it. We can offer it up to them.Swyx [00:41:16]: The perplexity of questions asked, you know, if it's higher perplexity, these are the smarterJungwon [00:41:20]: people. Yeah, maybe.Andreas [00:41:23]: If you put typos in your queries, you're not going to get off the stage.Swyx [00:41:28]: Negative social credit. It's very topical right now to think about the threat of long context windows. All these models that we're talking about these days, all like a million token plus. Is that relevant for you? Can you make use of that? Is that just prohibitively expensive because you're just paying for all those tokens or you're just doing rag?Andreas [00:41:44]: It's definitely relevant. And when we think about search, as many people do, we think about kind of a staged pipeline of retrieval where first you use semantic search database with embeddings, get like the, in our case, maybe 400 or so most relevant papers. And then, then you still need to rank those. And I think at that point it becomes pretty interesting to use larger models. So specifically in the past, I think a lot of ranking was kind of per item ranking where you would score each individual item, maybe using increasingly expensive scoring methods and then rank based on the scores. But I think list-wise re-ranking where you have a model that can see all the elements is a lot more powerful because often you can only really tell how good a thing is in comparison to other things and what things should come first. It really depends on like, well, what other things that are available, maybe you even care about diversity in your results. You don't want to show 10 very similar papers as the first 10 results. So I think a long context models are quite interesting there. And especially for our case where we care more about power users who are perhaps a little bit more willing to wait a little bit longer to get higher quality results relative to people who just quickly check out things because why not? And I think being able to spend more on longer contexts is quite valuable.Jungwon [00:42:55]: Yeah. I think one thing the longer context models changed for us is maybe a focus from breaking down tasks to breaking down the evaluation. So before, you know, if we wanted to answer a question from the full text of a paper, we had to figure out how to chunk it and like find the relevant chunk and then answer based on that chunk. And the nice thing was then, you know, kind of which chunk the model used to answer the question. So if you want to help the user track it, yeah, you can be like, well, this was the chunk that the model got. And now if you put the whole text in the paper, you have to like kind of find the chunk like more retroactively basically. And so you need kind of like a different set of abilities and obviously like a different technology to figure out. You still want to point the user to the supporting quotes in the text, but then the interaction is a little different.Swyx [00:43:38]: You like scan through and find some rouge score floor.Andreas [00:43:41]: I think there's an interesting space of almost research problems here because you would ideally make causal claims like if this hadn't been in the text, the model wouldn't have said this thing. And maybe you can do expensive approximations to that where like, I don't know, you just throw out chunk of the paper and re-answer and see what happens. But hopefully there are better ways of doing that where you just get that kind of counterfactual information for free from the model.Alessio [00:44:06]: Do you think at all about the cost of maintaining REG versus just putting more tokens in the window? I think in software development, a lot of times people buy developer productivity things so that we don't have to worry about it. Context window is kind of the same, right? You have to maintain chunking and like REG retrieval and like re-ranking and all of this versus I just shove everything into the context and like it costs a little more, but at least I don't have to do all of that. Is that something you thought about?Jungwon [00:44:31]: I think we still like hit up against context limits enough that it's not really, do we still want to keep this REG around? It's like we do still need it for the scale of the work that we're doing, yeah.Andreas [00:44:41]: And I think there are different kinds of maintainability. In one sense, I think you're right that throw everything into the context window thing is easier to maintain because you just can swap out a model. In another sense, if things go wrong, it's harder to debug where like, if you know, here's the process that we go through to go from 200 million papers to an answer. And there are like little steps and you understand, okay, this is the step that finds the relevant paragraph or whatever it may be. You'll know which step breaks if the answers are bad, whereas if it's just like a new model version came out and now it suddenly doesn't find your needle in a haystack anymore, then you're like, okay, what can you do? You're kind of at a loss.Alessio [00:45:21]: Let's talk a bit about, yeah, needle in a haystack and like maybe the opposite of it, which is like hard grounding. I don't know if that's like the best name to think about it, but I was using one of these chatwitcher documents features and I put the AMD MI300 specs and the new Blackwell chips from NVIDIA and I was asking questions and does the AMD chip support NVLink? And the response was like, oh, it doesn't say in the specs. But if you ask GPD 4 without the docs, it would tell you no, because NVLink it's a NVIDIA technology.Swyx [00:45:49]: It just says in the thing.Alessio [00:45:53]: How do you think about that? Does using the context sometimes suppress the knowledge that the model has?Andreas [00:45:57]: It really depends on the task because I think sometimes that is exactly what you want. So imagine you're a researcher, you're writing the background section of your paper and you're trying to describe what these other papers say. You really don't want extra information to be introduced there. In other cases where you're just trying to figure out the truth and you're giving the documents because you think they will help the model figure out what the truth is. I think you do want, if the model has a hunch that there might be something that's not in the papers, you do want to surface that. I think ideally you still don't want the model to just tell you, probably the ideal thing looks a bit more like agent control where the model can issue a query that then is intended to surface documents that substantiate its hunch. That's maybe a reasonable middle ground between model just telling you and model being fully limited to the papers you give it.Jungwon [00:46:44]: Yeah, I would say it's, they're just kind of different tasks right now. And the task that Elicit is mostly focused on is what do these papers say? But there's another task which is like, just give me the best possible answer and that give me the best possible answer sometimes depends on what do these papers say, but it can also depend on other stuff that's not in the papers. So ideally we can do both and then kind of do this overall task for you more going forward.Alessio [00:47:08]: We see a lot of details, but just to zoom back out a little bit, what are maybe the most underrated features of Elicit and what is one thing that maybe the users surprise you the most by using it?Jungwon [00:47:19]: I think the most powerful feature of Elicit is the ability to extract, add columns to this table, which effectively extracts data from all of your papers at once. It's well used, but there are kind of many different extensions of that that I think users are still discovering. So one is we let you give a description of the column. We let you give instructions of a column. We let you create custom columns. So we have like 30 plus predefined fields that users can extract, like what were the methods? What were the main findings? How many people were studied? And we actually show you basically the prompts that we're using to

Join us in this insightful discussion as we delve into Phoenix Controls' core decision almost 40 years ago—not to measure airflow in their systems. Discover the reasons behind this decision and explore the impact of airflow measurement accuracy on critical spaces such as hospitals and chemistry labs. Learn about the limitations and challenges of traditional airflow measurement methods and the innovative approach of metering airflow instead. Gain valuable insights into the potential consequences of inaccurate airflow measurement in critical environments and understand the factors affecting the accuracy of pressure transducers and airflow control systems over time. In this thought-provoking video, dive deep into the world of HVAC controls and critical space management with Phoenix Controls. Here are the key points covered in this podcast: 1. The Founder's Decision: Explore why the founder of Phoenix Controls opted not to measure airflow and instead focused on a different methodology for controlling airflow in buildings. 2. Impact on Critical Spaces: Understand the implications of airflow measurement accuracy in critical environments such as hospitals and chemistry labs, where even a small error can have significant consequences. 3. Limitations of Airflow Measurement: Learn about the challenges and limitations associated with traditional airflow measurement methods, including issues with sensor installation, response speed, stability, and maintenance. 4. Metering vs. Measuring: Discover the concept of metering airflow rather than measuring it, and why Phoenix Controls adopted this innovative approach to improve control accuracy. 5. Consequences of Inaccuracy: Delve into the potential repercussions of inaccurate airflow measurement in critical spaces, including operational disruptions, energy inefficiency, and financial losses. 6. Factors Affecting Accuracy: Explore the impact of factors like lack of straight duct runs, system delays, and maintenance on the accuracy of pressure transducers and airflow control systems over time. The decision by Phoenix Controls not to measure airflow almost 40 years ago has paved the way for a new approach to HVAC control, focusing on metering airflow for improved accuracy and reliability in critical environments. By understanding the challenges and limitations of traditional airflow measurement methods, we can appreciate the importance of innovative solutions in optimizing airflow control systems. Careful attention to design is crucial for laboratory settings, including fume hood face velocity, fume hood monitoring and use, laboratory air recirculation, laboratory/building pressurization, laboratory airflow exchange rates, manifold exhaust systems, exhaust stack height, exhaust duct velocity, general air distribution guidelines, controls (pressure-independent and general), testing and monitoring, work practices, selection of specialty hoods, and sound levels in rooms. For critical environment Phoenix Controls valve support in North Carolina and South Carolina, please contact Insight Partners today! For more HVAC content, you can visit our YouTube channel here: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.youtube.com/@HVAC-TV⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ The Engineers HVAC Podcast: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://anchor.fm/engineers-hvac-podcast⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Insight Partners (Commercial HVAC Products and Controls in NC, SC, GA): Website: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.insightusa.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Hobbs & Associates, Inc. (Commercial HVAC Products and Controls in VA, TN, MD, AL): ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.hobbsassociates.com⁠

Dean takes listener calls and addresses concerns about: peeling granite countertop slabs, frozen coils, and heat pumps and how air flow works,  and restoring engineer wooden floors with scuffs.

Rachel Finn is a fearless, free spirit that everyone loves. After attending Yale University in graduate school, she followed her heart and began guiding up in the Adirondacks some 30 years ago. Rachel is also a wonderful artist, friend, and inspiration to never grow up and never stop chasing your passions.  Finn, a certified Federation of Fly Fishers Instructor, is a well-known presence in the Adirondack guide scene throughout the fishing season. Serving as the head guide at the Hungry Trout Fly Shop in Wilmington, New York, she accompanies clients on expeditions across the numerous rivers, streams, and ponds nestled within the breathtaking mountains. Additionally, during July and August, Rachel leads summer float trips in Alaska. She holds positions as a pro staff member for Scott Fly Rods, Airflow, Nautilus Reels, and Lund Boats, while also being enlisted by Patagonia as one of their fly fishing ambassadors. Her expertise has been showcased on ESPN's Great Outdoor Games and the Outdoor Life Network's Fly Fishing Masters.

No episódio de hoje, Mateus Oliveira entrevistam Franklin Ferreira (Arquiteto de Dados) e Vinicius Gasparaini (Engenheiro de Dados), ambos integrantes do time de dados da Clicksign.Arquitetura de Dados & Engenharia de Dados, são áreas que estão ganhando muita tração nos últimos anos, entender como elas funcionam dentro de uma empresas data-driven é, não só um dos melhores metódos de estudo de mercado, como também escolha de qual caminho seguir.Neste bate papo iremos falar sobre:Arquiteturas de DadosEngenharia de DadosEsse podcast tem como principal intuito entender melhor como criar e evoluir arquiteturas de dados para melhor atender o negócio e como a engenharia de dados é usada dentro das grandes empresas, indo além de tecnologias e falando de metodologias e processos.Linkedin do time ClicksignFranklin Ferreira (Arquiteto de dados): https://www.linkedin.com/in/franklinfs390/Vinicius Gasparini (Engenharia de Dados): https://www.linkedin.com/in/vngasp/ (editado)  Luan Moreno = https://www.linkedin.com/in/luanmoreno/