POPULARITY
Foundations of Amateur Radio The other day I was discussing with a fellow amateur the increased frustration my mobile phone provider was inflicting. We hit on the idea of figuring out if other providers would fit the bill and how we could determine if their coverage would suit our needs. Aside from using an old mobile phone, I suggested that using a $25 RTL-SDR dongle would provide a way to record mobile phone cell site beacons from the various mobile networks to map what signal levels we might find. To that end, I discovered a tool called LTE-Cell-Scanner by Xianjun BH1RXH. Forked from the original project by James Peroulas, it allows you to use simple hardware to scan for LTE Cells used by mobile phone networks. James points out on his site that this tool can also be used to calibrate an RTL-SDR receiver's oscillator, since an LTE downlink centre frequency is stable to within 50 Parts Per Billion, that's 10 times more stable than my Yaesu FT-857d using a TCXO. If this doesn't mean much, think of it as a local frequency reference standard that you can use in your shack with minimal effort and cost. The story gets better. I started building LTE-Cell-Scanner from source and in doing so discovered a directory on my computer named "uhrr". I didn't remember what it was for, so I looked online. The first search result, when I looked for "uhrr radio" was a repository by Oliver F4HTB, more on that in a bit. The second search result was something called "Universal Radio Hacker". I clicked on the link and discovered a mind boggling tool. There are times in your life when something flips, this was one of those times. It happened when I discovered "csdr" by Andras HA7ILM and again when I discovered "GNU Radio". Diving into "Universal Radio Hacker", by Dr. Johannes Pohl and Dr. Andreas Noack I was introduced to the art of decoding and generating digital radio signals. In 2018 it was presented for the first time during the USENIX Workshop on Offensive Technologies, or WOOT, as a tool to discover, decode and identify exploits of proprietary IoT devices scattered all over the planet. As an aside, USENIX, Users Of Unix, since 1975. Back to radio. Universal Radio Hacker allows you to dissect recorded radio signals using all manner of interactive processes. When you go looking for it, and you should, I recommend that you start by watching some videos. You'll find an introductory play list on my YouTube channel. By the time you've seen those, you'll likely share my excitement. To encourage you further, the Universal Radio Hacker is open source, written in Python, and runs on Linux, MacOS and Windows. So far there have been 94 releases of the software, so it's seen significant development in the years since it was released into the wild. When installing it I was surprised to discover that its acronym was "uhr", not "uhrr". This was a relief since I still didn't remember what "uhrr" was all about and I couldn't imagine having forgotten Universal Radio Hacker. It turns out that the last time I looked at "uhrr" was apparently in 2021 when I shared my experience in an article titled "The remote edge..."; "uhrr" or "Universal Ham Radio Remote" is a tool that allows you to use a web browser to access a radio remotely. My little journey into unexpected diversions, distractions and discovery has led me into a path where several puzzle pieces have come together. For example, Universal Radio Hacker and GNU Radio can talk to each other, they're both written in Python, they're both open source, have a history of development and have a community of users. The LTE-Cell-Scanner, also open source, will allow me to calibrate most if not all of my radio gear and I'm once again inspired to keep digging into yet another aspect of this wonderful hobby. I'm sure that there are more than a thousand different hobbies under this roof. Go forth, explore, discover, be amazed, and stay curious! I'm Onno VK6FLAB
Stories and narratives weave an inescapable prison for a researcher at Site 19... until they turn to the Serpent's Hand. Comments? Join our discord at https://discord.gg/mqbYZSxZHc. Email us at vaultveritas@gmail.com.
Theodore Ross and Helena Bottemiller Evich work through the tumultuous nomination process for Surgeon General. Donald Trump's first nominee withdrew (questions about her medical and anti-vaxx credentials) and the newest one, Casey Means, has been branded a “Marxist tree hugger” by Laura Loomer. (Questions also remain about her anti-vaxxness). Conversation addresses the split within the groups backing HHS Secretary Robert F. Kennedy, Jr. – anti-Big Food versus anti-vaccine – “the big questions” about government being posed by the Trump administration; and in a sign of hope – MAHA members meet with public health experts and don't hate each other.
Send us a textIn today's episode, I interview Sarah Goeke and Julia Sears, the writer and director of the web series "Forked," a story of a woman recovering from the purity culture of the Bible Belt through sobriety and dragon fantasy erotica.Listen to hear about Sarah trusting her director on the shoot for And Through the Portal We Go, keeping the cast of "Forked" very much in the family, and finding humor in some of life's most serious moments.Books mentioned in this episode include:The Lilies by Quinn Diacon-FurtadoThe Chromatic Fantasy by H. A.Big Swiss by Jen BeaginWolfsong by TJ Klune Films and TV shows mentioned in this episode include:"Forked" directed by Julia Sears and Carolyn BraverAnd Through the Portal We Go directed by Mike HayhurstPractical Magic directed by Griffin DunneDrop Dead Gorgeous directed by Michael Patrick JannSpice World directed by Barnaby Thompson and Bob SpiersLittle Miss Sunshine directed by Jonathan Dayton and Valerie FarisSunshine Cleaning directed by Christine JeffsThe Big Lebowski directed by Joel CoenWaiting for Guffman directed by Christopher GuestSinners directed by Ryan CooglerSeverance (series)Wicked directed by Jon M. ChuFleabag (series)Follow Sarah on Instagram @sgerk, Julia @juliacsears and the series @forkedwebseries.Support the show
Paps puts Schoey to the test with 'Flag, Finals or Forked'! We also tackle the big footy news from around the country, including that tough debutant injury at Essendon and whether the Suns really have the ultimate home-ground advantage. Get bonus content on Patreon Hosted on Acast. See acast.com/privacy for more information.
The Hamlet Podcast - a weekly exploration of Shakespeare's King Lear. Act III Scene iv - Lear is still fascinated by Edgar, while the Fool still watches. Written and presented by Conor Hanratty
Welcome to an unhinged REGULAR episode. like whaaattttt?!? Yes, we read about a fork. Yes there are more books in this series that we may read. Yes, we are unhinged as always. Alsoooooo Krystal is talking on a regular episode? WHAT IS THIS MADNESS?!?But for realsies, enjoy our dive into cutlery. Our regularly scheduled wheel will be coming soon after we get our sh*t together
Is it possible that RFK Jr. believes autism research can be done so fast because he already thinks he knows what those causes of autism are? Other topics include: RFK Jr. “hitting his stride” after attending the funeral of a child who died of measles. How many people have been laid off at HHS and why doesn't anybody know? Bipartisan bonhomie on the issue of plant-based milk, in a Senate proposal that almost no one thinks will pass. MAHA anti-vaxxers would rather RFK Jr. forget about food.
Cop run over by an ATV, cop killer gets his, and another bad school teacher and much much more, come along for this ride see where it goes. Join the Patreon CLICK HERE Get you Motorcop Merch by CLICKING HERE Email me at motorcopchronicles@gmail.com Check out the Web Page www.motorcopchronicels.com BE THE LION
Join host Richard Hon on this episode of Hot Topics on the Edge of Show as we dive into the latest advancements in AI. Richard welcomes Addy Crezee, Founder & CEO /function1, FORKED, CREZEE and Victoria Neiman, Co-founder & COO, /function1 | FORKED | CREZEE to discuss Google's bold claims about Gemini 2.5, GitLab's latest insights on developers embracing AI, Amazon's Alexa Fund fueling AI startups, and a sneak peek at the upcoming Function One AI Conference in Dubai. Don't miss their take on the future of AI and its impact on industries across the board. Support us through our Sponsors! ☕
The premiere of FERN's newest podcast looks at how RKF Jr. is making waves on food policy.
Wes and Scott talk with Kevin Hou and Varun Mohan from Windsurf about the evolving landscape of AI in coding, and the future of software development. Show Notes 00:00 Welcome to Syntax! 00:50 The origins of Windsurf and Codeium Windsurf Codeium Vs Code Cursor 03:14 Rethinking IDE UX 05:45 Will Microsoft eventually implement these AI features in VS Code? 09:27 The "agentic" editor concept 17:58 The future of software development with AI 24:37 AI in large codebases 28:22 Brought to you by Sentry.io 28:46 How does AI stay current with frequent language/library updates? 33:07 Behind Windsurf's fresh design 35:23 Challenges with forking VS Code 38:47 AI and future innovations 43:04 How Windsurf approaches AI experimentation 45:11 Pricing and user segments 48:38 Will Windsurf ever run in the browser? 50:58 Sick Pick + Shameless Plugs Sick Picks Kevin: Ricoh GR IIIx Varun: Di2 Shifter Shameless Plugs Windsurf Hit us up on Socials! Syntax: X Instagram Tiktok LinkedIn Threads Wes: X Instagram Tiktok LinkedIn Threads Scott: X Instagram Tiktok LinkedIn Threads Randy: X Instagram YouTube Threads
Light Reading contributing editor Robert Clark and Ross O'Brien, analyst-in-chief at Delta Analysis, discuss SoftBank's big AI-RAN play, Samsung's rare stock buyback, and China's appeal for a unified 6G. Also, Michael Ackland, Vocus Group's GM for Federal Government & Strategic Projects, discusses Darwin's potential as a connectivity hub and why so much Asian Internet traffic is routed to the US through Australia. Hosted on Acast. See acast.com/privacy for more information.
Dan, Rob and Robin try out Forked River Brewing. They open up an IPA, a Red IPA and an imperial Stout.BREWERY:https://forkedriverbrewing.com
The Hoosiers come to town and properly dispense of the Spartans. We break down the game and look at the program moving forward. Then we prep for the basketball season to start. Finally, we take your Twitter questions. Join in the conversation next week @Spartan_Pod on Twitter and Instagram And watch again on YouTube at https://youtube.com/@spartan_pod
Ben Maller (produced by Danny G.) has a fun Friday for you! He talks: National Days, Demolished Tongue, Foodie Fun, Phrase of the Week, & more! ...Follow, rate & review "The Fifth Hour!" https://podcasts.apple.com/us/podcast/the-fifth-hour-with-ben-maller/id1478163837 #BenMallerSee omnystudio.com/listener for privacy information.
Guess who's back...back again...Did you miss us??? We missed you! Let's jump back into things with a fun episode all about this new sphere of romance that's been appearing on our Kindle Algorithms.Books/Authors we read:Forked by Ruth CardelloUnhinged by Vera ValentineJack by Layla FaeDeviled egg bookTriceratops and Bottoms by Lola FaustChris Tingle booksFantasy Lover by Sherrilyn KenyonAs always, you can email us at ragingromantics@nopl.org with any thoughts/questions/comments/concerns/recommendations. Thanks for coming back to us, and we hope you had an excellent summer!
Pushing down a hall, past two magically sealed doors they now have the sigil stone to access, the party confronts fish-like humanoid creatures blocking their path.Check out our Patreon https://patreon.com/TheShatterblightChroniclesFollow us on Instagram @shatterblightchroniclesCheck us out on Twitter @shatterblight
In this thrilling episode of Edge of NFT Podcast, sponsored by LAOS and BitLayer, we delve into the digital frontier. LAOS is a decentralized Layer 1 blockchain parachain on Polkadot, emphasizing sharding-based digital ownership and security. BitLayer is a Bitcoin Layer 2 solution boosting scalability, security, and EVM compatibility with Zero-Knowledge Rollups.On this episode, we're taking you on a journey through the blockchain revolution with some great folks we met at the Hong Kong Forked Conference and Bitcoin Asia Join Conan Li and Karen Cheng from Memeland, Eric Alexander from Native Capital, Danny Wilson, Illuvium's CFO and Shavrat Gas cofounder at Forked as they explore the latest in the Hong Kong Web3 ecosystem, unveiling groundbreaking projects, events, and collaborations shaping the future of this dynamic community.Support us through our Sponsors! ☕
We dive into the world of Spot Prawns! // We learn about Charlotte Restaurant & Lounge from Chef Jon Park // On Simple to Spectacular! we celebrate Chef Thierry by talking through one of his Rover’s spring recipes // We welcome Susan Feniger, Co-Owner, and Chef of Alice B., Socalo, Border Grill and BBQ Mexicana with Liz Lachman, Filmmaker and Screenwriter, to talk about her new documentary: “Suzan Feniger. Forked” // We finish up the show with Rub with Love Food for Thought Tasty Trivia!!
Happy Mothers Day to all the wonderful moms out there! This is part 2 of the series with Mike Sentell and Duke Turnage. On this episode we get into when Mike came back to Dyer County and met Duke and how together they share their hunting passions and implement them into The Forked Deer Longbeards club. Enjoy!
On todays episode we have special guest from the Forked Deer Longbeards, Mike Sentell and Duke Turnage. They share their knowledge of turkey hunting and how its changed. Mike gives us a history lesson on being drafted in the war to come back to Dyer County to fall in love with the outdoors. This is a two part series so be sure to tune into part two after this one. Enjoy!
At a recent Summit during the Sundance Film Festival, Food Tank and 360 Communications presented a day of programming focused on food, environment, and the arts. This episode of “Food Talk with Dani Nierenberg” features a panel from the event about the new documentary “Susan Feniger. FORKED.” The film follows award-winning Chef Susan Feniger's passionate struggle and quest to bring global street food under one roof in the form of a new LA restaurant: STREET. During the panel, Chef Feniger, Liz Lachman, the film's Writer, Director, and Producer; and Lisa Donmall-Reeve, Producer and Creative Director at LDR Creative LLC, discuss the male-dominated culinary industry that Chef Feniger navigated throughout her career; the friendship between Chef Feniger and Chef Mary Sue Milliken that is central to the documentary; and the story of how the film came to be. While you're listening, subscribe, rate, and review the show; it would mean the world to us to have your feedback. You can listen to “Food Talk with Dani Nierenberg” wherever you consume your podcasts.
@benedictinecollegelectures9315 America as a Theologico-Political Problem | D.C. Schindler Paul Vander Klay clips channel https://www.youtube.com/channel/UCX0jIcadtoxELSwehCh5QTg Bridges of Meaning Discord https://discord.gg/hMe26gkn https://www.meetup.com/sacramento-estuary/ My Substack https://paulvanderklay.substack.com/ Estuary Hub Link https://www.estuaryhub.com/ If you want to schedule a one-on-one conversation check here. https://paulvanderklay.me/2019/08/06/converzations-with-pvk/ There is a video version of this podcast on YouTube at http://www.youtube.com/paulvanderklay To listen to this on ITunes https://itunes.apple.com/us/podcast/paul-vanderklays-podcast/id1394314333 If you need the RSS feed for your podcast player https://paulvanderklay.podbean.com/feed/ All Amazon links here are part of the Amazon Affiliate Program. Amazon pays me a small commission at no additional cost to you if you buy through one of the product links here. This is is one (free to you) way to support my videos. https://paypal.me/paulvanderklay Blockchain backup on Lbry https://odysee.com/@paulvanderklay https://www.patreon.com/paulvanderklay Paul's Church Content at Living Stones Channel https://www.youtube.com/channel/UCh7bdktIALZ9Nq41oVCvW-A To support Paul's work by supporting his church give here. https://tithe.ly/give?c=2160640
GUEST: Emmy Award winning director Liz Lachman "Susan Feniger: Forked" is a verité documentary that chronicles the journey of award-winning celebrity chef Susan Feniger(Food Network/Master Chef) as she embarks on the venture of her first solo restaurant, STREET. The film captures her passionate struggle to bring global street food together under one roof in Los Angeles. Forked is headed to the 2024 Sundance Film Festival, and will be screened on January 20th at FOODLAB, to an invitation only event. Top celebrity chefs such as Bobby Flay, Wolfgang Puck and others are also featured in the documentary. Susan Feniger, an accomplished American chef, restaurateur, cookbook author, and media personality, is recognized for her roles in shows like "Too Hot Tamales" and "Tamales World Tour" on the Food Network, as well as appearances on "Iron Chef," "Top Chef Masters," and "Cooking with the Master Chefs."
Or Polecat's Fowl, Freddy Birmo, Split Branches, Kate's Hubby.
This is a recap of the top 10 posts on Hacker News on December 31st, 2023.This podcast was generated by wondercraft.ai(00:51): I forked SteamOS for my living room PCOriginal post: https://news.ycombinator.com/item?id=38823101&utm_source=wondercraft_ai(02:38): Bazzite – a SteamOS-like OCI image for desktop, living room, and handheld PCsOriginal post: https://news.ycombinator.com/item?id=38828040&utm_source=wondercraft_ai(04:49): Sony software updates breaks movie theater projectorsOriginal post: https://news.ycombinator.com/item?id=38825623&utm_source=wondercraft_ai(06:37): Bun, JavaScript, and TCOOriginal post: https://news.ycombinator.com/item?id=38823673&utm_source=wondercraft_ai(08:28): A 1690s Peanut is RebornOriginal post: https://news.ycombinator.com/item?id=38823304&utm_source=wondercraft_ai(10:04): Sweden Solar SystemOriginal post: https://news.ycombinator.com/item?id=38823482&utm_source=wondercraft_ai(10:55): Interesting double-poly latches inside AMD's vintage LANCE Ethernet chipOriginal post: https://news.ycombinator.com/item?id=38826187&utm_source=wondercraft_ai(12:33): Meshtastic: An open source, off-grid, decentralized, mesh networkOriginal post: https://news.ycombinator.com/item?id=38829448&utm_source=wondercraft_ai(14:18): I Vote on Plagiarism Cases at Harvard College. Gay's Getting Off EasyOriginal post: https://news.ycombinator.com/item?id=38828804&utm_source=wondercraft_aiThis is a third-party project, independent from HN and YC. Text and audio generated using AI, by wondercraft.ai. Create your own studio quality podcast with text as the only input in seconds at app.wondercraft.ai. Issues or feedback? We'd love to hear from you: team@wondercraft.ai
Hall of Fame Blown Off: Mandy & Liam Friday 12/1/23
Hall of Fame Blown Off: Mandy & Liam Friday 12/1/23
Susan Feniger and Liz Lachman pop. I first encountered their mutual hurricane of wit at the Del Mar Wine + Food Festival. They were setting up their table to cook. It looked like a movie set. Lachman immediately cordoned me, made me one of her own. Both of them struck me as whip-smart, funny, alive. James Beard Award–winning chef Feniger and Emmy-winning filmmaker Lachman join us this week on Happy Half Hour, our podcast exploring the world and people of food. They talk life and art and their new documentary film, Susan Feniger: Forked. They're in San Diego tomorrow to screen Forked at the Coronado Island Film Festival. They'll watch it with the crowd of food and film people, do a Q&A, cook some food, share some food, shoot the shit. They've been married for a long while, so Forked is Lachman capturing Feniger's life and creative process on film as only a partner could. All Feniger's defenses are dropped. We get to see one of the country's top chefs with her quirks and impulses laid out, vulnerable, as she takes on the maddening process of concepting a restaurant, then bringing it to life from scratch and begging the city to approve everything in a sane amount of time. Feniger has been to the mountain in the chef world. In the '80s, she was invited by her friend (and eventual restaurant partner) Mary Sue Milliken to not-so-casually break the gender barrier in a very fancy Chicago restaurant (the chef had told Milliken he didn't hire women in the kitchen, period—she proved him wrong and brought Feniger along). The duo left to open their own restaurant in LA, Border Grill, which would become very famous and catnippy for food lovers. The duo—who bicker and play beautifully—were among the early stars of Food Network, making more than 400 episodes of their TV show, Too Hot Tamales. Feniger worked under Wolfgang Puck when he was merely a free-jazzing, mellow-cool Austrian chef making waves in LA. One day, when Border Grill's buzz in the city was just heating up, Julia Child walked in. She and Feniger became friends. And then, after a long and fruitful working relationship with Milliken, Feniger decided it was time to do her own thing. She embarked on the seemingly endless, intricate, frustrating-as-hell road to opening another LA restaurant, Street, with a different creative partner. This is what Forked documents. It straps us to Feniger's back as she grits and hustles to execute a new dream. And she burns the salmon. Dear god, she burns the salmon. Chefs like her occasionally burn salmon. Susan Feinger: Forked will screen at Nov. 10 at 10 a.m. at the Coronado Island Film Festival.
Eyelash Vipers and more with Aaron Gerson! Brought to you by BlackBox Reptile Cages & Rack Systems → blackboxcages.com And Puget Sound Pythons → facebook.com/pugetsoundpythons Use the code THN @ checkout for 15% off - grab some swag! - https://fulviusapparel.com/ Buy the best coffee around! - https://coldbloodedcaffeine.com/?ref=kwc4jec0 Everything THN → https://linktr.ee/The_Herpetoculture_Network Support us on patreon! → https://www.patreon.com/theherpetoculturenetwork Join the Snakes & Stogies FB Group - https://www.facebook.com/groups/748337355909367 Follow Justin - palmettocoastexotics Follow Phil - knobtails.ig
On this episode of Taste Buds with Deb, host Debra Eckerling speaks with chef Susan Feniger and filmmaker Liz Lachman. Feniger is a chef, restaurateur, and the subject of the documentary “Susan Feniger: Forked,” produced and directed by her life partner, Lachman. Feniger talks about her culinary background, the evolution of food in media and her role as a trailblazer - along with Mary Sue Milliken (“Too Hot Tamales,” Border Grill). Plus, Feniger and Lachman discuss the film's focus (Feniger's The STREET restaurant), how the documentary - and the two of them - came together, their respective relationships with food, and more. They also share Feniger's recipe for Spiced Millet Puffs. Find the recipe and the highlights of the conversation at JewishJournal.com/podcasts. Learn more at ForkedtheFilm.com and follow @SusanFeniger and @LizLachman on Instagram. For more from Taste Buds, follow @TheDEBMethod on social media.
Snakes! They look like an alien species, and some of the things they're capable of will convince you they're not from this planet! They see in infrared, they shed their skin, and have you seen that weird-looking tongue? Snakes don't use their tongue like we do. Think about it: you really don't have time to taste something if you can only swallow food whole without chewing it. Instead of using it to taste, snakes smell with their tongues. That's why they always flicker it in and out – they want to catch nano-particles in the air that will tell them if their prey or some kind of danger is nearby. Learn more about your ad choices. Visit megaphone.fm/adchoices
All of the updates from a crazy day in Congress. Order and sanity reigns in Florida. A stupid gag order from a stupid judge. The gestapo comes to Massachusetts. And Tim Cook speaks with forked tongue.
This week catch up on the months of July and August 2023 Billings city council meetings. Parks district funding, garbage collection changes, and the ever present and persistant jib-jab. *Email us at thefridaypacket@gmail.com with comments, questions, concerns. *Go to https://www.patreon.com/thefridaypacket to “buy that for a dollar” and become a sustaining member of the podcast!!
This week, Jeff Draper from the American Forked podcast returns to the show. Curt puts forth a challenge to all listeners, and we thoroughly discuss camping logistics, podcasting, bodily functions, and the concept of acceptability. Voicemail/Text: 801-252-6069 Website: http://www.theweeklyinsalt.com Instagram: https://www.instagram.com/the_weekly_insalt TikTok: https://www.tiktok.com/@theweeklyinsalt
So much in one episode... Le Tour comes to a close, Sam's being mean (but it's funny), a strong case AGAINST bike packing, and some great recommendations in the new Packfiller Picks. Hosted on Acast. See acast.com/privacy for more information.
To learn more and for all show notes go to - https://thelanguagequestion.com/episode-12-speaking-a-forked-tongue-a-conversation-with-dr-roisin-costello
Thursday
The Book of James Part 7: The Real Deal - Forked Tongue Dionne Salmonds Original Air Date: 2023.05.28 If you have brothers or sisters, you understand the nature of the relationship and the ups and downs that come with it. We may not realize it, but Jesus had brothers and sisters... Mark 6:3 tells us, Is not this the carpenter, the son of Mary and brother of James and Joseph and Judas and Simon? And are not his sisters here with us?” And they took offense at him. We don't know much more about His family, but one brother in particular we can learn from is James. James' story is amazing, having gone from little brother and skeptic, to believer in Jesus as the Messiah and leader of the early church and writer of the book that bears his name. We invite you to join us – and James – as we learn more of his story and his teachings on the Christian life and church life. His instructions to believers and the church are amazingly on point for today, they are clear and leave no room for doubt. If you are not one to mince words with others, you'll love James! If you have missed a message or are viewing from home, you can catch weekend services on our Facebook page and YouTube by going to www.crossroads-ridgecrest.org or through the church app. We also have podcasts available by looking up Crossroads Community Church - available on several podcast apps. For questions or information, please contact us at: (760)384-3333 Wednesday – Friday 10am – 4pm, text (760)301-4840 or email ccc@ccc-rc.org
Dave Has A Forked What?
Tab and tutorial now available in the Breakthrough Banjo course http://clawhammerbanjo.net/coursetour
Latent Space is popping off! Welcome to the over 8500 latent space explorers who have joined us. Join us this month at various events in SF and NYC, or start your own!This post spent 22 hours at the top of Hacker News.As announced during their Developer Day celebrating their $100m fundraise following their Google partnership, Replit is now open sourcing its own state of the art code LLM: replit-code-v1-3b (model card, HF Space), which beats OpenAI's Codex model on the industry standard HumanEval benchmark when finetuned on Replit data (despite being 77% smaller) and more importantly passes AmjadEval (we'll explain!)We got an exclusive interview with Reza Shabani, Replit's Head of AI, to tell the story of Replit's journey into building a data platform, building GhostWriter, and now training their own LLM, for 22 million developers!8 minutes of this discussion go into a live demo discussing generated code samples - which is always awkward on audio. So we've again gone multimodal and put up a screen recording here where you can follow along on the code samples!Recorded in-person at the beautiful StudioPod studios in San Francisco.Full transcript is below the fold. We would really appreciate if you shared our pod with friends on Twitter, LinkedIn, Mastodon, Bluesky, or your social media poison of choice!Timestamps* [00:00:21] Introducing Reza* [00:01:49] Quantitative Finance and Data Engineering* [00:11:23] From Data to AI at Replit* [00:17:26] Replit GhostWriter* [00:20:31] Benchmarking Code LLMs* [00:23:06] AmjadEval live demo* [00:31:21] Aligning Models on Vibes* [00:33:04] Beyond Chat & Code Completion* [00:35:50] Ghostwriter Autonomous Agent* [00:38:47] Releasing Replit-code-v1-3b* [00:43:38] The YOLO training run* [00:49:49] Scaling Laws: from Kaplan to Chinchilla to LLaMA* [00:52:43] MosaicML* [00:55:36] Replit's Plans for the Future (and Hiring!)* [00:59:05] Lightning RoundShow Notes* Reza Shabani on Twitter and LinkedIn* also Michele Catasta and Madhav Singhal* Michele Catasta's thread on the release of replit-code-v1-3b* Intro to Replit Ghostwriter* Replit Ghostwriter Chat and Building Ghostwriter Chat* Reza on how to train your own LLMs (their top blog of all time)* Our Benchmarks 101 episode where we discussed HumanEval* AmjadEval live demo* Nat.dev* MosaicML CEO Naveen Rao on Replit's LLM* MosaicML Composer + FSDP code* Replit's AI team is hiring in North America timezone - Fullstack engineer, Applied AI/ML, and other roles!Transcript[00:00:00] Alessio Fanelli: Hey everyone. Welcome to the Latent Space podcast. This is Alessio, partner and CTO in residence at Decibel Partners. I'm joined by my co-host, swyx, writer and editor of Latent Space.[00:00:21] Introducing Reza[00:00:21] swyx: Hey and today we have Reza Shabani, Head of AI at Replit. Welcome to the studio. Thank you. Thank you for having me. So we try to introduce people's bios so you don't have to repeat yourself, but then also get a personal side of you.[00:00:34] You got your PhD in econ from Berkeley, and then you were a startup founder for a bit, and, and then you went into systematic equity trading at BlackRock in Wellington. And then something happened and you were now head of AI at Relet. What should people know about you that might not be apparent on LinkedIn?[00:00:50] One thing[00:00:51] Reza Shabani: that comes up pretty often is whether I know how to code. Yeah, you'd be shocked. A lot of people are kind of like, do you know how to code? When I was talking to Amjad about this role, I'd originally talked to him, I think about a product role and, and didn't get it. Then he was like, well, I know you've done a bunch of data and analytics stuff.[00:01:07] We need someone to work on that. And I was like, sure, I'll, I'll do it. And he was like, okay, but you might have to know how to code. And I was like, yeah, yeah, I, I know how to code. So I think that just kind of surprises people coming from like Ancon background. Yeah. Of people are always kind of like, wait, even when people join Relet, they're like, wait, does this guy actually know how to code?[00:01:28] Is he actually technical? Yeah.[00:01:30] swyx: You did a bunch of number crunching at top financial companies and it still wasn't[00:01:34] Reza Shabani: obvious. Yeah. Yeah. I mean, I, I think someone like in a software engineering background, cuz you think of finance and you think of like calling people to get the deal done and that type of thing.[00:01:43] No, it's, it's not that as, as you know, it's very very quantitative. Especially what I did in, in finance, very quantitative.[00:01:49] Quantitative Finance and Data Engineering[00:01:49] swyx: Yeah, so we can cover a little bit of that and then go into the rapid journey. So as, as you, as you know, I was also a quantitative trader on the sell side and the buy side. And yeah, I actually learned Python there.[00:02:01] I learned my, I wrote my own data pipelines there before airflow was a thing, and it was just me writing running notebooks and not version controlling them. And it was a complete mess, but we were managing a billion dollars on, on my crappy code. Yeah, yeah. What was it like for you?[00:02:17] Reza Shabani: I guess somewhat similar.[00:02:18] I, I started the journey during grad school, so during my PhD and my PhD was in economics and it was always on the more data intensive kind of applied economic side. And, and specifically financial economics. And so what I did for my dissertation I recorded cnbc, the Financial News Network for 10 hours a day, every day.[00:02:39] Extracted the close captions from the video files and then used that to create a second by second transcript of, of cmbc, merged that on with high frequency trading, quote data and then looked at, you know, went in and did some, some nlp, tagging the company names, and and then looked at the price response or the change in price and trading volume in the seconds after a company was mentioned.[00:03:01] And, and this was back in. 2009 that I was doing this. So before cloud, before, before a lot of Python actually. And, and definitely before any of these packages were available to make this stuff easy. And that's where, where I had to really learn to code, like outside of you know, any kind of like data programming languages.[00:03:21] That's when I had to learn Python and had to learn all, all of these other skills to work it with data at that, at that scale. So then, you know, I thought I wanted to do academia. I did terrible on the academic market because everyone looked at my dissertation. They're like, this is cool, but this isn't economics.[00:03:37] And everyone in the computer science department was actually way more interested in it. Like I, I hung out there more than in the econ department and You know, didn't get a single academic offer. Had two offer. I think I only applied to like two industry jobs and got offers from both of them.[00:03:53] They, they saw value in it. One of them was BlackRock and turned it down to, to do my own startup, and then went crawling back two and a half years later after the startup failed.[00:04:02] swyx: Something on your LinkedIn was like you're trading Chinese news tickers or something. Oh, yeah. I forget,[00:04:07] Reza Shabani: forget what that was.[00:04:08] Yeah, I mean oh. There, there was so much stuff. Honestly, like, so systematic active equity at, at BlackRock is, was such an amazing. Group and you just end up learning so much and the, and the possibilities there. Like when you, when you go in and you learn the types of things that they've been trading on for years you know, like a paper will come out in academia and they're like, did you know you can use like this data on searches to predict the price of cars?[00:04:33] And it's like, you go in and they've been trading on that for like eight years. Yeah. So they're, they're really ahead of the curve on, on all of that stuff. And the really interesting stuff that I, that I found when I went in was all like, related to NLP and ml a lot of like transcript data, a lot of like parsing through the types of things that companies talk about, whether an analyst reports, conference calls, earnings reports and the devil's really in the details about like how you make sense of, of that information in a way that, you know, gives you insight into what the company's doing and, and where the market is, is going.[00:05:08] I don't know if we can like nerd out on specific strategies. Yes. Let's go, let's go. What, so one of my favorite strategies that, because it never, I don't think we ended up trading on it, so I can probably talk about it. And it, it just kind of shows like the kind of work that you do around this data.[00:05:23] It was called emerging technologies. And so the whole idea is that there's always a new set of emerging technologies coming onto the market and the companies that are ahead of that curve and stay up to date on on the latest trends are gonna outperform their, their competitors.[00:05:38] And that's gonna reflect in the, in the stock price. So when you have a theory like that, how do you actually turn that into a trading strategy? So what we ended up doing is, well first you have to, to determine what are the emergent technologies, like what are the new up and coming technologies.[00:05:56] And so we actually went and pulled data on startups. And so there's like startups in Silicon Valley. You have all these descriptions of what they do, and you get that, that corpus of like when startups were getting funding. And then you can run non-negative matrix factorization on it and create these clusters of like what the various Emerging technologies are, and you have this all the way going back and you have like social media back in like 2008 when Facebook was, was blowing up.[00:06:21] And and you have things like mobile and digital advertising and and a lot of things actually outside of Silicon Valley. They, you know, like shale and oil cracking. Yeah. Like new technologies in, in all these different types of industries. And then and then you go and you look like, which publicly traded companies are actually talking about these things and and have exposure to these things.[00:06:42] And those are the companies that end up staying ahead of, of their competitors. And a lot of the the cases that came out of that made a ton of sense. Like when mobile was emerging, you had Walmart Labs. Walmart was really far ahead in terms of thinking about mobile and the impact of mobile.[00:06:59] And, and their, you know, Sears wasn't, and Walmart did well, and, and Sears didn't. So lots of different examples of of that, of like a company that talks about a new emerging trend. I can only imagine, like right now, all of the stuff with, with ai, there must be tons of companies talking about, yeah, how does this affect their[00:07:17] swyx: business?[00:07:18] And at some point you do, you do lose the signal. Because you get overwhelmed with noise by people slapping a on everything. Right? Which is, yeah. Yeah. That's what the Long Island Iced Tea Company slaps like blockchain on their name and, you know, their stock price like doubled or something.[00:07:32] Reza Shabani: Yeah, no, that, that's absolutely right.[00:07:35] And, and right now that's definitely the kind of strategy that would not be performing well right now because everyone would be talking about ai. And, and that's, as you know, like that's a lot of what you do in Quant is you, you try to weed out other possible explanations for for why this trend might be happening.[00:07:52] And in that particular case, I think we found that, like the companies, it wasn't, it wasn't like Sears and Walmart were both talking about mobile. It's that Walmart went out of their way to talk about mobile as like a future, mm-hmm. Trend. Whereas Sears just wouldn't bring it up. And then by the time an invest investors are asking you about it, you're probably late to the game.[00:08:12] So it was really identifying those companies that were. At the cutting edge of, of new technologies and, and staying ahead. I remember like Domino's was another big one. Like, I don't know, you[00:08:21] swyx: remember that? So for those who don't know, Domino's Pizza, I think for the run of most of the 2010s was a better performing stock than Amazon.[00:08:29] Yeah.[00:08:31] Reza Shabani: It's insane.[00:08:32] swyx: Yeah. Because of their investment in mobile. Mm-hmm. And, and just online commerce and, and all that. I it must have been fun picking that up. Yeah, that's[00:08:40] Reza Shabani: that's interesting. And I, and I think they had, I don't know if you, if you remember, they had like the pizza tracker, which was on, on mobile.[00:08:46] I use it[00:08:46] swyx: myself. It's a great, it's great app. Great app. I it's mostly faked. I think that[00:08:50] Reza Shabani: that's what I heard. I think it's gonna be like a, a huge I don't know. I'm waiting for like the New York Times article to drop that shows that the whole thing was fake. We all thought our pizzas were at those stages, but they weren't.[00:09:01] swyx: The, the challenge for me, so that so there's a, there's a great piece by Eric Falkenstein called Batesian Mimicry, where every signal essentially gets overwhelmed by noise because the people who wants, who create noise want to follow the, the signal makers. So that actually is why I left quant trading because there's just too much regime changing and like things that would access very well would test poorly out a sample.[00:09:25] And I'm sure you've like, had a little bit of that. And then there's what was the core uncertainty of like, okay, I have identified a factor that performs really well, but that's one factor out of. 500 other factors that could be going on. You have no idea. So anyway, that, that was my existential uncertainty plus the fact that it was a very highly stressful job.[00:09:43] Reza Shabani: Yeah. This is a bit of a tangent, but I, I think about this all the time and I used to have a, a great answer before chat came out, but do you think that AI will win at Quant ever?[00:09:54] swyx: I mean, what is Rentech doing? Whatever they're doing is working apparently. Yeah. But for, for most mortals, I. Like just waving your wand and saying AI doesn't make sense when your sample size is actually fairly low.[00:10:08] Yeah. Like we have maybe 40 years of financial history, if you're lucky. Mm-hmm. Times what, 4,000 listed equities. It's actually not a lot. Yeah, no, it's,[00:10:17] Reza Shabani: it's not a lot at all. And, and constantly changing market conditions and made laden variables and, and all of, all of that as well. Yeah. And then[00:10:24] swyx: retroactively you're like, oh, okay.[00:10:26] Someone will discover a giant factor that, that like explains retroactively everything that you've been doing that you thought was alpha, that you're like, Nope, actually you're just exposed to another factor that you're just, you just didn't think about everything was momentum in.[00:10:37] Yeah. And one piece that I really liked was Andrew Lo. I think he had from mit, I think he had a paper on bid as Spreads. And I think if you, if you just. Taken, took into account liquidity of markets that would account for a lot of active trading strategies, alpha. And that was systematically declined as interest rates declined.[00:10:56] And I mean, it was, it was just like after I looked at that, I was like, okay, I'm never gonna get this right.[00:11:01] Reza Shabani: Yeah. It's a, it's a crazy field and I you know, I, I always thought of like the, the adversarial aspect of it as being the, the part that AI would always have a pretty difficult time tackling.[00:11:13] Yeah. Just because, you know, there's, there's someone on the other end trying to out, out game you and, and AI can, can fail in a lot of those situations. Yeah.[00:11:23] swyx: Cool.[00:11:23] From Data to AI at Replit[00:11:23] Alessio Fanelli: Awesome. And now you've been a rep almost two years. What do you do there? Like what does the, the team do? Like, how has that evolved since you joined?[00:11:32] Especially since large language models are now top of mind, but, you know, two years ago it wasn't quite as mainstream. So how, how has that evolved?[00:11:40] Reza Shabani: Yeah, I, so when I joined, I joined a year and a half ago. We actually had to build out a lot of, of data pipelines.[00:11:45] And so I started doing a lot of data work. And we didn't have you know, there, there were like databases for production systems and, and whatnot, but we just didn't have the the infrastructure to query data at scale and to process that, that data at scale and replica has tons of users tons of data, just tons of ripples.[00:12:04] And I can get into, into some of those numbers, but like, if you wanted to answer the question, for example of what is the most. Forked rep, rep on rep, you couldn't answer that back then because it, the query would just completely time out. And so a lot of the work originally just went into building data infrastructure, like modernizing the data infrastructure in a way where you can answer questions like that, where you can you know, pull in data from any particular rep to process to make available for search.[00:12:34] And, and moving all of that data into a format where you can do all of this in minutes as opposed to, you know, days or weeks or months. That laid a lot of the groundwork for building anything in, in ai, at least in terms of training our own own models and then fine tuning them with, with replica data.[00:12:50] So then you know, we, we started a team last year recruited people from, you know from a team of, of zero or a team of one to, to the AI and data team today. We, we build. Everything related to, to ghostrider. So that means the various features like explain code, generate code, transform Code, and Ghostrider chat which is like a in context ide or a chat product within the, in the ide.[00:13:18] And then the code completion models, which are ghostwriter code complete, which was the, the very first version of, of ghostrider. Yeah. And we also support, you know, things like search and, and anything in terms of what creates, or anything that requires like large data scale or large scale processing of, of data for the site.[00:13:38] And, and various types of like ML algorithms for the site, for internal use of the site to do things like detect and stop abuse. Mm-hmm.[00:13:47] Alessio Fanelli: Yep. Sounds like a lot of the early stuff you worked on was more analytical, kind of like analyzing data, getting answers on these things. Obviously this has evolved now into some.[00:13:57] Production use case code lms, how is the team? And maybe like some of the skills changed. I know there's a lot of people wondering, oh, I was like a modern data stack expert, or whatever. It's like I was doing feature development, like, how's my job gonna change? Like,[00:14:12] Reza Shabani: yeah. It's a good question. I mean, I think that with with language models, the shift has kind of been from, or from traditional ml, a lot of the shift has gone towards more like nlp backed ml, I guess.[00:14:26] And so, you know, there, there's an entire skill set of applicants that I no longer see, at least for, for this role which are like people who know how to do time series and, and ML across time. Right. And, and you, yeah. Like you, you know, that exact feeling of how difficult it is to. You know, you have like some, some text or some variable and then all of a sudden you wanna track that over time.[00:14:50] The number of dimensions that it, that it introduces is just wild and it's a totally different skill set than what we do in a, for example, in in language models. And it's very it's a, it's a skill that is kind of you know, at, at least at rep not used much. And I'm sure in other places used a lot, but a lot of the, the kind of excitement about language models has pulled away attention from some of these other ML areas, which are extremely important and, and I think still going to be valuable.[00:15:21] So I would just recommend like anyone who is a, a data stack expert, like of course it's cool to work with NLP and text data and whatnot, but I do think at some point it's going to you know, having, having skills outside of that area and in more traditional aspects of ML will, will certainly be valuable as well.[00:15:39] swyx: Yeah. I, I'd like to spend a little bit of time on this data stack notion pitch. You were even, you were effectively the first data hire at rep. And I just spent the past year myself diving into data ecosystem. I think a lot of software engineers are actually. Completely unaware that basically every company now eventually evolves.[00:15:57] The data team and the data team does everything that you just mentioned. Yeah. All of us do exactly the same things, set up the same pipelines you know, shop at the same warehouses essentially. Yeah, yeah, yeah, yeah. So that they enable everyone else to query whatever they, whatever they want. And to, to find those insights that that can drive their business.[00:16:15] Because everyone wants to be data driven. They don't want to do the janitorial work that it comes, that comes to, yeah. Yeah. Hooking everything up. What like, so rep is that you think like 90 ish people now, and then you, you joined two years ago. Was it like 30 ish people? Yeah, exactly. We're 30 people where I joined.[00:16:30] So and I just wanna establish your founders. That is exactly when we hired our first data hire at Vilify as well. I think this is just a very common pattern that most founders should be aware of, that like, You start to build a data discipline at this point. And it's, and by the way, a lot of ex finance people very good at this because that's what we do at our finance job.[00:16:48] Reza Shabani: Yeah. Yeah. I was, I was actually gonna Good say that is that in, in some ways, you're kind of like the perfect first data hire because it, you know, you know how to build things in a reliable but fast way and, and how to build them in a way that, you know, it's, it scales over time and evolves over time because financial markets move so quickly that if you were to take all of your time building up these massive systems, like the trading opportunities gone.[00:17:14] So, yeah. Yeah, they're very good at it. Cool. Okay. Well,[00:17:18] swyx: I wanted to cover Ghost Writer as a standalone thing first. Okay. Yeah. And then go into code, you know, V1 or whatever you're calling it. Yeah. Okay. Okay. That sounds good. So order it[00:17:26] Replit GhostWriter[00:17:26] Reza Shabani: however you like. Sure. So the original version of, of Ghost Writer we shipped in August of, of last year.[00:17:33] Yeah. And so this was a. This was a code completion model similar to GitHub's co-pilot. And so, you know, you would have some text and then it would predict like, what, what comes next. And this was, the original version was actually based off of the cogen model. And so this was an open source model developed by Salesforce that was trained on, on tons of publicly available code data.[00:17:58] And so then we took their their model, one of the smaller ones, did some distillation some other kind of fancy tricks to, to make it much faster and and deployed that. And so the innovation there was really around how to reduce the model footprint in a, to, to a size where we could actually serve it to, to our users.[00:18:20] And so the original Ghost Rider You know, we leaned heavily on, on open source. And our, our friends at Salesforce obviously were huge in that, in, in developing these models. And, but, but it was game changing just because we were the first startup to actually put something like that into production.[00:18:38] And, and at the time, you know, if you wanted something like that, there was only one, one name and, and one place in town to, to get it. And and at the same time, I think I, I'm not sure if that's like when the image models were also becoming open sourced for the first time. And so the world went from this place where, you know, there was like literally one company that had all of these, these really advanced models to, oh wait, maybe these things will be everywhere.[00:19:04] And that's exactly what's happened in, in the last Year or so, as, as the models get more powerful and then you always kind of see like an open source version come out that someone else can, can build and put into production very quickly at, at, you know, a fraction of, of the cost. So yeah, that was the, the kind of code completion Go Strider was, was really just, just that we wanted to fine tune it a lot to kind of change the way that our users could interact with it.[00:19:31] So just to make it you know, more customizable for our use cases on, on Rep. And so people on Relet write a lot of, like jsx for example, which I don't think was in the original training set for, for cogen. And and they do specific things that are more Tuned to like html, like they might wanna run, right?[00:19:50] Like inline style or like inline CSS basically. Those types of things. And so we experimented with fine tuning cogen a bit here and there, and, and the results just kind of weren't, weren't there, they weren't where you know, we, we wanted the model to be. And, and then we just figured we should just build our own infrastructure to, you know, train these things from scratch.[00:20:11] Like, LMS aren't going anywhere. This world's not, you know, it's, it's not like we're not going back to that world of there's just one, one game in town. And and we had the skills infrastructure and the, and the team to do it. So we just started doing that. And you know, we'll be this week releasing our very first open source code model.[00:20:31] And,[00:20:31] Benchmarking Code LLMs[00:20:31] Alessio Fanelli: and when you say it was not where you wanted it to be, how were you benchmarking[00:20:36] Reza Shabani: it? In that particular case, we were actually, so, so we have really two sets of benchmarks that, that we use. One is human eval, so just the standard kind of benchmark for, for Python, where you can generate some code or you give you give the model a function definition with, with some string describing what it's supposed to do, and then you allow it to complete that function, and then you run a unit test against it and and see if what it generated passes the test.[00:21:02] So we, we always kind of, we would run this on the, on the model. The, the funny thing is the fine tuned versions of. Of Cogen actually did pretty well on, on that benchmark. But then when we, we then have something called instead of human eval. We call it Amjad eval, which is basically like, what does Amjad think?[00:21:22] Yeah, it's, it's exactly that. It's like testing the vibes of, of a model. And it's, it's cra like I've never seen him, I, I've never seen anyone test the model so thoroughly in such a short amount of time. He's, he's like, he knows exactly what to write and, and how to prompt the model to, to get you know, a very quick read on, on its quote unquote vibes.[00:21:43] And and we take that like really seriously. And I, I remember there was like one, one time where we trained a model that had really good you know, human eval scores. And the vibes were just terrible. Like, it just wouldn't, you know, it, it seemed overtrained. So so that's a lot of what we found is like we, we just couldn't get it to Pass the vibes test no matter how the, how[00:22:04] swyx: eval.[00:22:04] Well, can you formalize I'm jal because I, I actually have a problem. Slight discomfort with human eval. Effectively being the only code benchmark Yeah. That we have. Yeah. Isn't that[00:22:14] Reza Shabani: weird? It's bizarre. It's, it's, it's weird that we can't do better than that in some, some way. So, okay. If[00:22:21] swyx: I, if I asked you to formalize Mja, what does he look for that human eval doesn't do well on?[00:22:25] Reza Shabani: Ah, that is a, that's a great question. A lot of it is kind of a lot of it is contextual like deep within, within specific functions. Let me think about this.[00:22:38] swyx: Yeah, we, we can pause for. And if you need to pull up something.[00:22:41] Reza Shabani: Yeah, I, let me, let me pull up a few. This, this[00:22:43] swyx: is gold, this catnip for people.[00:22:45] Okay. Because we might actually influence a benchmark being evolved, right. So, yeah. Yeah. That would be,[00:22:50] Reza Shabani: that would be huge. This was, this was his original message when he said the vibes test with, with flying colors. And so you have some, some ghostrider comparisons ghost Rider on the left, and cogen is on the right.[00:23:06] AmjadEval live demo[00:23:06] Reza Shabani: So here's Ghostrider. Okay.[00:23:09] swyx: So basically, so if I, if I summarize it from a, for ghosting the, there's a, there's a, there's a bunch of comments talking about how you basically implement a clone. Process or to to c Clooney process. And it's describing a bunch of possible states that he might want to, to match.[00:23:25] And then it asks for a single line of code for defining what possible values of a name space it might be to initialize it in amjadi val With what model is this? Is this your, this is model. This is the one we're releasing. Yeah. Yeah. It actually defines constants which are human readable and nice.[00:23:42] And then in the other cogen Salesforce model, it just initializes it to zero because it reads that it starts of an int Yeah, exactly. So[00:23:51] Reza Shabani: interesting. Yeah. So you had a much better explanation of, of that than than I did. It's okay. So this is, yeah. Handle operation. This is on the left.[00:24:00] Okay.[00:24:00] swyx: So this is rep's version. Yeah. Where it's implementing a function and an in filling, is that what it's doing inside of a sum operation?[00:24:07] Reza Shabani: This, so this one doesn't actually do the infill, so that's the completion inside of the, of the sum operation. But it, it's not, it's, it, it's not taking into account context after this value, but[00:24:18] swyx: Right, right.[00:24:19] So it's writing an inline lambda function in Python. Okay.[00:24:21] Reza Shabani: Mm-hmm. Versus[00:24:24] swyx: this one is just passing in the nearest available variable. It's, it can find, yeah.[00:24:30] Reza Shabani: Okay. So so, okay. I'll, I'll get some really good ones in a, in a second. So, okay. Here's tokenize. So[00:24:37] swyx: this is an assertion on a value, and it's helping to basically complete the entire, I think it looks like an E s T that you're writing here.[00:24:46] Mm-hmm. That's good. That that's, that's good. And then what does Salesforce cogen do? This is Salesforce cogen here. So is that invalidism way or what, what are we supposed to do? It's just making up tokens. Oh, okay. Yeah, yeah, yeah. So it's just, it's just much better at context. Yeah. Okay.[00:25:04] Reza Shabani: And, and I guess to be fair, we have to show a case where co cogen does better.[00:25:09] Okay. All right. So here's, here's one on the left right, which[00:25:12] swyx: is another assertion where it's just saying that if you pass in a list, it's going to throw an exception saying in an expectedly list and Salesforce code, Jen says,[00:25:24] Reza Shabani: This is so, so ghost writer was sure that the first argument needs to be a list[00:25:30] swyx: here.[00:25:30] So it hallucinated that it wanted a list. Yeah. Even though you never said it was gonna be a list.[00:25:35] Reza Shabani: Yeah. And it's, it's a argument of that. Yeah. Mm-hmm. So, okay, here's a, here's a cooler quiz for you all, cuz I struggled with this one for a second. Okay. What is.[00:25:47] swyx: Okay, so this is a four loop example from Amjad.[00:25:50] And it's, it's sort of like a q and a context in a chat bot. And it's, and it asks, and Amjad is asking, what does this code log? And it just paste in some JavaScript code. The JavaScript code is a four loop with a set time out inside of it with a cons. The console logs out the iteration variable of the for loop and increasing numbers of of, of times.[00:26:10] So it's, it goes from zero to five and then it just increases the, the delay between the timeouts each, each time. Yeah.[00:26:15] Reza Shabani: So, okay. So this answer was provided by by Bard. Mm-hmm. And does it look correct to you? Well,[00:26:22] the[00:26:22] Alessio Fanelli: numbers too, but it's not one second. It's the time between them increases.[00:26:27] It's like the first one, then the one is one second apart, then it's two seconds, three seconds. So[00:26:32] Reza Shabani: it's not, well, well, so I, you know, when I saw this and, and the, the message and the thread was like, Our model's better than Bard at, at coding Uhhuh. This is the Bard answer Uhhuh that looks totally right to me.[00:26:46] Yeah. And this is our[00:26:47] swyx: answer. It logs 5 5 55, what is it? Log five 50. 55 oh oh. Because because it logs the state of I, which is five by the time that the log happens. Mm-hmm. Yeah.[00:27:01] Reza Shabani: Oh God. So like we, you know we were shocked. Like, and, and the Bard dancer looked totally right to, to me. Yeah. And then, and somehow our code completion model mind Jude, like this is not a conversational chat model.[00:27:14] Mm-hmm. Somehow gets this right. And and, you know, Bard obviously a much larger much more capable model with all this fancy transfer learning and, and and whatnot. Some somehow, you know, doesn't get it right. So, This is the kind of stuff that goes into, into mja eval that you, you won't find in any benchmark.[00:27:35] Good. And and, and it's, it's the kind of thing that, you know, makes something pass a, a vibe test at Rep.[00:27:42] swyx: Okay. Well, okay, so me, this is not a vibe, this is not so much a vibe test as the, these are just interview questions. Yeah, that's, we're straight up just asking interview questions[00:27:50] Reza Shabani: right now. Yeah, no, the, the vibe test, the reason why it's really difficult to kind of show screenshots that have a vibe test is because it really kind of depends on like how snappy the completion is, how what the latency feels like and if it gets, if it, if it feels like it's making you more productive.[00:28:08] And and a lot of the time, you know, like the, the mix of, of really low latency and actually helpful content and, and helpful completions is what makes up the, the vibe test. And I think part of it is also, is it. Is it returning to you or the, the lack of it returning to you things that may look right, but be completely wrong.[00:28:30] I think that also kind of affects Yeah. Yeah. The, the vibe test as well. Yeah. And so, yeah, th this is very much like a, like a interview question. Yeah.[00:28:39] swyx: The, the one with the number of processes that, that was definitely a vibe test. Like what kind of code style do you expect in this situation? Yeah.[00:28:47] Is this another example? Okay.[00:28:49] Reza Shabani: Yeah. This is another example with some more Okay. Explanations.[00:28:53] swyx: Should we look at the Bard one[00:28:54] Reza Shabani: first? Sure. These are, I think these are, yeah. This is original GT three with full size 175. Billion[00:29:03] swyx: parameters. Okay, so you asked GPC three, I'm a highly intelligent question answering bot.[00:29:07] If you ask me a question that is rooted in truth, I'll give you the answer. If you ask me a question that is nonsense I will respond with unknown. And then you ask it a question. What is the square root of a bananas banana? It answers nine. So complete hallucination and failed to follow the instruction that you gave it.[00:29:22] I wonder if it follows if one, if you use an instruction to inversion it might, yeah. Do what better?[00:29:28] Reza Shabani: On, on the original[00:29:29] swyx: GP T Yeah, because I like it. Just, you're, you're giving an instructions and it's not[00:29:33] Reza Shabani: instruction tuned. Now. Now the interesting thing though is our model here, which does follow the instructions this is not instruction tuned yet, and we still are planning to instruction tune.[00:29:43] Right? So it's like for like, yeah, yeah, exactly. So,[00:29:45] swyx: So this is a replica model. Same question. What is the square of bananas? Banana. And it answers unknown. And this being one of the, the thing that Amjad was talking about, which you guys are. Finding as a discovery, which is, it's better on pure natural language questions, even though you trained it on code.[00:30:02] Exactly. Yeah. Hmm. Is that because there's a lot of comments in,[00:30:07] Reza Shabani: No. I mean, I think part of it is that there's a lot of comments and there's also a lot of natural language in, in a lot of code right. In terms of documentation, you know, you have a lot of like markdowns and restructured text and there's also just a lot of web-based code on, on replica, and HTML tends to have a lot of natural language in it.[00:30:27] But I don't think the comments from code would help it reason in this way. And, you know, where you can answer questions like based on instructions, for example. Okay. But yeah, it's, I know that that's like one of the things. That really shocked us is the kind of the, the fact that like, it's really good at, at natural language reasoning, even though it was trained on, on code.[00:30:49] swyx: Was this the reason that you started running your model on hella swag and[00:30:53] Reza Shabani: all the other Yeah, exactly. Interesting. And the, yeah, it's, it's kind of funny. Like it's in some ways it kind of makes sense. I mean, a lot of like code involves a lot of reasoning and logic which language models need and need to develop and, and whatnot.[00:31:09] And so you know, we, we have this hunch that maybe that using that as part of the training beforehand and then training it on natural language above and beyond that really tends to help. Yeah,[00:31:21] Aligning Models on Vibes[00:31:21] Alessio Fanelli: this is so interesting. I, I'm trying to think, how do you align a model on vibes? You know, like Bard, Bard is not purposefully being bad, right?[00:31:30] Like, there's obviously something either in like the training data, like how you're running the process that like, makes it so that the vibes are better. It's like when it, when it fails this test, like how do you go back to the team and say, Hey, we need to get better[00:31:44] Reza Shabani: vibes. Yeah, let's do, yeah. Yeah. It's a, it's a great question.[00:31:49] It's a di it's very difficult to do. It's not you know, so much of what goes into these models in, in the same way that we have no idea how we can get that question right. The programming you know, quiz question. Right. Whereas Bard got it wrong. We, we also have no idea how to take certain things out and or, and to, you know, remove certain aspects of, of vibes.[00:32:13] Of course there's, there's things you can do to like scrub the model, but it's, it's very difficult to, to get it to be better at something. It's, it's almost like all you can do is, is give it the right type of, of data that you think will do well. And then and, and of course later do some fancy type of like, instruction tuning or, or whatever else.[00:32:33] But a lot of what we do is finding the right mix of optimal data that we want to, to feed into the model and then hoping that the, that the data that's fed in is sufficiently representative of, of the type of generations that we want to do coming out. That's really the best that, that you can do.[00:32:51] Either the model has. Vibes or, or it doesn't, you can't teach vibes. Like you can't sprinkle additional vibes in it. Yeah, yeah, yeah. Same in real life. Yeah, exactly right. Yeah, exactly. You[00:33:04] Beyond Code Completion[00:33:04] Alessio Fanelli: mentioned, you know, co being the only show in town when you started, now you have this, there's obviously a, a bunch of them, right.[00:33:10] Cody, which we had on the podcast used to be Tap nine, kite, all these different, all these different things. Like, do you think the vibes are gonna be the main you know, way to differentiate them? Like, how are you thinking about. What's gonna make Ghost Rider, like stand apart or like, do you just expect this to be like table stakes for any tool?[00:33:28] So like, it just gonna be there?[00:33:30] Reza Shabani: Yeah. I, I do think it's, it's going to be table stakes for sure. I, I think that if you don't if you don't have AI assisted technology, especially in, in coding it's, it's just going to feel pretty antiquated. But but I do think that Ghost Rider stands apart from some of, of these other tools for for specific reasons too.[00:33:51] So this is kind of the, one of, one of the things that these models haven't really done yet is Come outside of code completion and outside of, of just a, a single editor file, right? So what they're doing is they're, they're predicting like the text that can come next, but they're not helping with the development process quite, quite yet outside of just completing code in a, in a text file.[00:34:16] And so the types of things that we wanna do with Ghost Rider are enable it to, to help in the software development process not just editing particular files. And so so that means using a right mix of like the right model for for the task at hand. But but we want Ghost Rider to be able to, to create scaffolding for you for, for these projects.[00:34:38] And so imagine if you would like Terraform. But, but powered by Ghostrider, right? I want to, I put up this website, I'm starting to get a ton of traffic to it and and maybe like I need to, to create a backend database. And so we want that to come from ghostrider as well, so it can actually look at your traffic, look at your code, and create.[00:34:59] You know a, a schema for you that you can then deploy in, in Postgres or, or whatever else? You know, I, I know like doing anything in in cloud can be a nightmare as well. Like if you wanna create a new service account and you wanna deploy you know, nodes on and, and have that service account, kind of talk to those nodes and return some, some other information, like those are the types of things that currently we have to kind of go, go back, go look at some documentation for Google Cloud, go look at how our code base does it you know, ask around in Slack, kind of figure that out and, and create a pull request.[00:35:31] Those are the types of things that we think we can automate away with with more advanced uses of, of ghostwriter once we go past, like, here's what would come next in, in this file. So, so that's the real promise of it, is, is the ability to help you kind of generate software instead of just code in a, in a particular file.[00:35:50] Ghostwriter Autonomous Agent[00:35:50] Reza Shabani: Are[00:35:50] Alessio Fanelli: you giving REPL access to the model? Like not rep, like the actual rep. Like once the model generates some of this code, especially when it's in the background, it's not, the completion use case can actually run the code to see if it works. There's like a cool open source project called Walgreen that does something like that.[00:36:07] It's like self-healing software. Like it gives a REPL access and like keeps running until it fixes[00:36:11] Reza Shabani: itself. Yeah. So, so, so right now there, so there's Ghostrider chat and Ghostrider code completion. So Ghostrider Chat does have, have that advantage in, in that it can it, it knows all the different parts of, of the ide and so for example, like if an error is thrown, it can look at the, the trace back and suggest like a fix for you.[00:36:33] So it has that type of integration. But the what, what we really want to do is is. Is merge the two in a way where we want Ghost Rider to be like, like an autonomous agent that can actually drive the ide. So in these action models, you know, where you have like a sequence of of events and then you can use you know, transformers to kind of keep track of that sequence and predict the next next event.[00:36:56] It's how, you know, companies like, like adapt work these like browser models that can, you know, go and scroll through different websites or, or take some, some series of actions in a, in a sequence. Well, it turns out the IDE is actually a perfect place to do that, right? So like when we talk about creating software, not just completing code in a file what do you do when you, when you build software?[00:37:17] You, you might clone a repo and then you, you know, will go and change some things. You might add a new file go down, highlight some text, delete that value, and point it to some new database, depending on the value in a different config file or in your environment. And then you would go in and add additional block code to, to extend its functionality and then you might deploy that.[00:37:40] Well, we, we have all of that data right there in the replica ide. And and we have like terabytes and terabytes of, of OT data you know, operational transform data. And so, you know, we can we can see that like this person has created a, a file what they call it, and, you know, they start typing in the file.[00:37:58] They go back and edit a different file to match the you know, the class name that they just put in, in the original file. All of that, that kind of sequence data is what we're looking to to train our next model on. And so that, that entire kind of process of actually building software within the I D E, not just like, here's some text what comes next, but rather the, the actions that go into, you know, creating a fully developed program.[00:38:25] And a lot of that includes, for example, like running the code and seeing does this work, does this do what I expected? Does it error out? And then what does it do in response to that error? So all, all of that is like, Insanely valuable information that we want to put into our, our next model. And and that's like, we think that one can be way more advanced than the, than this, you know, go straighter code completion model.[00:38:47] Releasing Replit-code-v1-3b[00:38:47] swyx: Cool. Well we wanted to dive in a little bit more on, on the model that you're releasing. Maybe we can just give people a high level what is being released what have you decided to open source and maybe why open source the story of the YOLO project and Yeah. I mean, it's a cool story and just tell it from the start.[00:39:06] Yeah.[00:39:06] Reza Shabani: So, so what's being released is the, the first version that we're going to release. It's a, it's a code model called replica Code V1 three B. So this is a relatively small model. It's 2.7 billion parameters. And it's a, it's the first llama style model for code. So, meaning it's just seen tons and tons of tokens.[00:39:26] It's been trained on 525 billion tokens of, of code all permissively licensed code. And it's it's three epox over the training set. And And, you know, all of that in a, in a 2.7 billion parameter model. And in addition to that, we, for, for this project or, and for this model, we trained our very own vocabulary as well.[00:39:48] So this, this doesn't use the cogen vocab. For, for the tokenize we, we trained a totally new tokenize on the underlying data from, from scratch, and we'll be open sourcing that as well. It has something like 32,000. The vocabulary size is, is in the 32 thousands as opposed to the 50 thousands.[00:40:08] Much more specific for, for code. And, and so it's smaller faster, that helps with inference, it helps with training and it can produce more relevant content just because of the you know, the, the vocab is very much trained on, on code as opposed to, to natural language. So, yeah, we'll be releasing that.[00:40:29] This week it'll be up on, on hugging pace so people can take it play with it, you know, fine tune it, do all type of things with it. We want to, we're eager and excited to see what people do with the, the code completion model. It's, it's small, it's very fast. We think it has great vibes, but we, we hope like other people feel the same way.[00:40:49] And yeah. And then after, after that, we might consider releasing the replica tuned model at, at some point as well, but still doing some, some more work around that.[00:40:58] swyx: Right? So there are actually two models, A replica code V1 three B and replica fine tune V1 three B. And the fine tune one is the one that has the 50% improvement in in common sense benchmarks, which is going from 20% to 30%.[00:41:13] For,[00:41:13] Reza Shabani: for yes. Yeah, yeah, yeah, exactly. And so, so that one, the, the additional tuning that was done on that was on the publicly available data on, on rep. And so, so that's, that's you know, data that's in public res is Permissively licensed. So fine tuning on on that. Then, Leads to a surprisingly better, like significantly better model, which is this retuned V1 three B, same size, you know, same, very fast inference, same vocabulary and everything.[00:41:46] The only difference is that it's been trained on additional replica data. Yeah.[00:41:50] swyx: And I think I'll call out that I think in one of the follow up q and as that Amjad mentioned, people had some concerns with using replica data. Not, I mean, the licensing is fine, it's more about the data quality because there's a lot of beginner code Yeah.[00:42:03] And a lot of maybe wrong code. Mm-hmm. But it apparently just wasn't an issue at all. You did[00:42:08] Reza Shabani: some filtering. Yeah. I mean, well, so, so we did some filtering, but, but as you know, it's when you're, when you're talking about data at that scale, it's impossible to keep out, you know, all of the, it's, it's impossible to find only select pieces of data that you want the, the model to see.[00:42:24] And, and so a lot of the, a lot of that kind of, you know, people who are learning to code material was in there anyway. And, and you know, we obviously did some quality filtering, but a lot of it went into the fine tuning process and it really helped for some reason. You know, there's a lot of high quality code on, on replica, but there's like you, like you said, a lot of beginner code as well.[00:42:46] And that was, that was the really surprising thing is that That somehow really improved the model and its reasoning capabilities. It felt much more kind of instruction tuned afterward. And, and you know, we have our kind of suspicions as as to why there's, there's a lot of like assignments on rep that kind of explain this is how you do something and then you might have like answers and, and whatnot.[00:43:06] There's a lot of people who learn to code on, on rep, right? And, and like, think of a beginner coder, like think of a code model that's learning to, to code learning this reasoning and logic. It's probably a lot more valuable to see that type of, you know, the, the type of stuff that you find on rep as opposed to like a large legacy code base that that is, you know, difficult to, to parse and, and figure out.[00:43:29] So, so that was very surprising to see, you know, just such a huge jump in in reasoning ability once trained on, on replica data.[00:43:38] The YOLO training run[00:43:38] swyx: Yeah. Perfect. So we're gonna do a little bit of storytelling just leading up to the, the an the developer day that you had last week. Yeah. My understanding is you decide, you raised some money, you decided to have a developer day, you had a bunch of announcements queued up.[00:43:52] And then you were like, let's train the language model. Yeah. You published a blog post and then you announced it on Devrel Day. What, what, and, and you called it the yolo, right? So like, let's just take us through like the[00:44:01] Reza Shabani: sequence of events. So so we had been building the infrastructure to kind of to, to be able to train our own models for, for months now.[00:44:08] And so that involves like laying out the infrastructure, being able to pull in the, the data processes at scale. Being able to do things like train your own tokenizes. And and even before this you know, we had to build out a lot of this data infrastructure for, for powering things like search.[00:44:24] There's over, I think the public number is like 200 and and 30 million res on, on re. And each of these res have like many different files and, and lots of code, lots of content. And so you can imagine like what it must be like to, to be able to query that, that amount of, of data in a, in a reasonable amount of time.[00:44:45] So we've You know, we spent a lot of time just building the infrastructure that allows for for us to do something like that and, and really optimize that. And, and this was by the end of last year. That was the case. Like I think I did a demo where I showed you can, you can go through all of replica data and parse the function signature of every Python function in like under two minutes.[00:45:07] And, and there's, you know, many, many of them. And so a and, and then leading up to developer day, you know, we had, we'd kind of set up these pipelines. We'd started training these, these models, deploying them into production, kind of iterating and, and getting that model training to production loop.[00:45:24] But we'd only really done like 1.3 billion parameter models. It was like all JavaScript or all Python. So there were still some things like we couldn't figure out like the most optimal way to to, to do it. So things like how do you pad or yeah, how do you how do you prefix chunks when you have like multi-language models, what's like the optimal way to do it and, and so on.[00:45:46] So you know, there's two PhDs on, on the team. Myself and Mike and PhDs tend to be like careful about, you know, a systematic approach and, and whatnot. And so we had this whole like list of things we were gonna do, like, oh, we'll test it on this thing and, and so on. And even these, like 1.3 billion parameter models, they were only trained on maybe like 20 billion tokens or 30 billion tokens.[00:46:10] And and then Amjad joins the call and he's like, no, let's just, let's just yolo this. Like, let's just, you know, we're raising money. Like we should have a better code model. Like, let's yolo it. Let's like run it on all the data. How many tokens do we have? And, and, and we're like, you know, both Michael and I are like, I, I looked at 'em during the call and we were both like, oh God is like, are we really just gonna do this?[00:46:33] And[00:46:34] swyx: well, what is the what's the hangup? I mean, you know that large models work,[00:46:37] Reza Shabani: you know that they work, but you, you also don't know whether or not you can improve the process in, in In important ways by doing more data work, scrubbing additional content, and, and also it's expensive. It's like, it, it can, you know it can cost quite a bit and if you, and if you do it incorrectly, you can actually get it.[00:47:00] Or you, you know, it's[00:47:02] swyx: like you hit button, the button, the go button once and you sit, sit back for three days.[00:47:05] Reza Shabani: Exactly. Yeah. Right. Well, like more like two days. Yeah. Well, in, in our case, yeah, two days if you're running 256 GP 100. Yeah. Yeah. And and, and then when that comes back, you know, you have to take some time to kind of to test it.[00:47:19] And then if it fails and you can't really figure out why, and like, yeah, it's, it's just a, it's kind of like a, a. A time consuming process and you just don't know what's going to, to come out of it. But no, I mean, I'm Judd was like, no, let's just train it on all the data. How many tokens do we have? We tell him and he is like, that's not enough.[00:47:38] Where can we get more tokens? Okay. And so Michele had this you know, great idea to to train it on multiple epox and so[00:47:45] swyx: resampling the same data again.[00:47:47] Reza Shabani: Yeah. Which, which can be, which is known risky or like, or tends to overfit. Yeah, you can, you can over overfit. But you know, he, he pointed us to some evidence that actually maybe this isn't really a going to be a problem.[00:48:00] And, and he was very persuasive in, in doing that. And so it, it was risky and, and you know, we did that training. It turned out. Like to actually be great for that, for that base model. And so then we decided like, let's keep pushing. We have 256 TVs running. Let's see what else we can do with it.[00:48:20] So we ran a couple other implementations. We ran you know, a the fine tune version as I, as I said, and that's where it becomes really valuable to have had that entire pipeline built out because then we can pull all the right data, de-dupe it, like go through the, the entire like processing stack that we had done for like months.[00:48:41] We did that in, in a matter of like two days for, for the replica data as well removed, you know, any of, any personal any pii like personal information removed, harmful content, removed, any of, of that stuff. And we just put it back through the that same pipeline and then trained on top of that.[00:48:59] And so I believe that replica tune data has seen something like 680. Billion tokens. And, and that's in terms of code, I mean, that's like a, a universe of code. There really isn't that much more out there. And, and it, you know, gave us really, really promising results. And then we also did like a UL two run, which allows like fill the middle capabilities and and, and will be, you know working to deploy that on, on rep and test that out as well soon.[00:49:29] But it was really just one of those Those cases where, like, leading up to developer day, had we, had we done this in this more like careful, systematic way what, what would've occurred in probably like two, three months. I got us to do it in, in a week. That's fun. It was a lot of fun. Yeah.[00:49:49] Scaling Laws: from Kaplan to Chinchilla to LLaMA[00:49:49] Alessio Fanelli: And so every time I, I've seen the stable releases to every time none of these models fit, like the chinchilla loss in, in quotes, which is supposed to be, you know, 20 tokens per, per, what's this part of the yo run?[00:50:04] Or like, you're just like, let's just throw out the tokens at it doesn't matter. What's most efficient or like, do you think there's something about some of these scaling laws where like, yeah, maybe it's good in theory, but I'd rather not risk it and just throw out the tokens that I have at it? Yeah,[00:50:18] Reza Shabani: I think it's, it's hard to, it's hard to tell just because there's.[00:50:23] You know, like, like I said, like these runs are expensive and they haven't, if, if you think about how many, how often these runs have been done, like the number of models out there and then, and then thoroughly tested in some forum. And, and so I don't mean just like human eval, but actually in front of actual users for actual inference as part of a, a real product that, that people are using.[00:50:45] I mean, it's not that many. And, and so it's not like there's there's like really well established kind of rules as to whether or not something like that could lead to, to crazy amounts of overfitting or not. You just kind of have to use some, some intuition around it. And, and what we kind of found is that our, our results seem to imply that we've really been under training these, these models.[00:51:06] Oh my god. And so like that, you know, all, all of the compute that we kind of. Through, with this and, and the number of tokens, it, it really seems to help and really seems to to improve. And I, and I think, you know, these things kind of happen where in, in the literature where everyone kind of converges to something seems to take it for for a fact.[00:51:27] And like, like Chinchilla is a great example of like, okay, you know, 20 tokens. Yeah. And but, but then, you know, until someone else comes along and kind of tries tries it out and sees actually this seems to work better. And then from our results, it seems imply actually maybe even even lla. Maybe Undertrained.[00:51:45] And, and it may be better to go even You know, like train on on even more tokens then and for, for the[00:51:52] swyx: listener, like the original scaling law was Kaplan, which is 1.7. Mm-hmm. And then Chin established 20. Yeah. And now Lama style seems to mean 200 x tokens to parameters, ratio. Yeah. So obviously you should go to 2000 X, right?[00:52:06] Like, I mean, it's,[00:52:08] Reza Shabani: I mean, we're, we're kind of out of code at that point, you know, it's like there, there is a real shortage of it, but I know that I, I know there are people working on I don't know if it's quite 2000, but it's, it's getting close on you know language models. And so our friends at at Mosaic are are working on some of these really, really big models that are, you know, language because you with just code, you, you end up running out of out of context.[00:52:31] So Jonathan at, at Mosaic has Jonathan and Naveen both have really interesting content on, on Twitter about that. Yeah. And I just highly recommend following Jonathan. Yeah,[00:52:43] MosaicML[00:52:43] swyx: I'm sure you do. Well, CAGR, can we talk about, so I, I was sitting next to Naveen. I'm sure he's very, very happy that you, you guys had such, such success with Mosaic.[00:52:50] Maybe could, could you shout out like what Mosaic did to help you out? What, what they do well, what maybe people don't appreciate about having a trusted infrastructure provider versus a commodity GPU provider?[00:53:01] Reza Shabani: Yeah, so I mean, I, I talked about this a little bit in the in, in the blog post in terms of like what, what advantages like Mosaic offers and, and you know, keep in mind, like we had, we had deployed our own training infrastructure before this, and so we had some experience with it.[00:53:15] It wasn't like we had just, just tried Mosaic And, and some of those things. One is like you can actually get GPUs from different providers and you don't need to be you know, signed up for that cloud provider. So it's, it kind of detaches like your GPU offering from the rest of your cloud because most of our cloud runs in, in gcp.[00:53:34] But you know, this allowed us to leverage GPUs and other providers as well. And then another thing is like train or infrastructure as a service. So you know, these GPUs burn out. You have note failures, you have like all, all kinds of hardware issues that come up. And so the ability to kind of not have to deal with that and, and allow mosaic and team to kind of provide that type of, of fault tolerance was huge for us.[00:53:59] As well as a lot of their preconfigured l m configurations for, for these runs. And so they have a lot of experience in, in training these models. And so they have. You know, the, the right kind of pre-configured setups for, for various models that make sure that, you know, you have the right learning rates, the right training parameters, and that you're making the, the best use of the GPU and, and the underlying hardware.[00:54:26] And so you know, your GPU utilization is always at, at optimal levels. You have like fewer law spikes than if you do, you can recover from them. And you're really getting the most value out of, out of the compute that you're kind of throwing at, at your data. We found that to be incredibly, incredibly helpful.[00:54:44] And so it, of the time that we spent running things on Mosaic, like very little of that time is trying to figure out why the G P U isn't being utilized or why you know, it keeps crashing or, or why we, you have like a cuda out of memory errors or something like that. So like all, all of those things that make training a nightmare Are are, you know, really well handled by, by Mosaic and the composer cloud and and ecosystem.[00:55:12] Yeah. I was gonna[00:55:13] swyx: ask cuz you're on gcp if you're attempted to rewrite things for the TPUs. Cause Google's always saying that it's more efficient and faster, whatever, but no one has experience with them. Yeah.[00:55:23] Reza Shabani: That's kind of the problem is that no one's building on them, right? Yeah. Like, like we want to build on, on systems that everyone else is, is building for.[00:55:31] Yeah. And and so with, with the, with the TPUs that it's not easy to do that.[00:55:36] Replit's Plans for the Future (and Hiring!)[00:55:36] swyx: So plans for the future, like hard problems that you wanna solve? Maybe like what, what do you like what kind of people that you're hiring on your team?[00:55:44] Reza Shabani: Yeah. So We are, we're currently hiring for for two different roles on, on my team.[00:55:49] Although we, you know, welcome applications from anyone that, that thinks they can contribute in, in this area. Replica tends to be like a, a band of misfits. And, and the type of people we work with and, and have on our team are you know, like just the, the perfect mix to, to do amazing projects like this with very, very few people.[00:56:09] Right now we're hiring for the applied a applied to AI ml engineer. And so, you know, this is someone who's. Creating data pipelines, processing the data at scale creating runs and and training models and you
Hello Friends! We're so happy you're with us again! This episode is super fun! Robbie's hero is a Magician named Dave, Jordan has some BIG NEWS and they both share some emails from the past episode! Thanks for stopping by!Email us @ tidbitzwiththeboyz@gmail.com Tik Tok -- https://www.tiktok.com/@tidbitzwiththeboyz?lang=en Instagram -- https://www.instagram.com/tidbitzwiththeboyz/ Facebook -- https://www.facebook.com/tidbitzwtheboyz/
Things we take for granted often have unusual origin stories, which clear make them great additions to our Cabinet of Curiosities.See omnystudio.com/listener for privacy information.
Apologies for today's Rumble related audio issues. Political frustration seems to be the norm for all of us. Returning from an absense results in more questions. The early handlers and what they taught. Why VAX doses matter, and how they got produced. The HAVA act and it's impact on us all. Julian Assange and what he stands for. Palin walks back the tough talk. When the DOJ sued the states over election law. Look how evil human beings can be. Aaron Swartz spoke truth to power. Foster crimes happen when the gov't claims children. It's true, they experimented on the homeless. Vulnerable and helpless but still citizens. Law suit records should be available to all. The little black box and what it tells us. They want a future of online elections. Is voter fraud really high tech terrorism? Above all, these times have shown how the people hunger for the truth. Learn more about your ad choices. Visit megaphone.fm/adchoices
Halvy comes out against snakes, a new movie about a temporary department store is discussed, Cory has Headlines