POPULARITY
Unsupervised Learning is a podcast that interviews the sharpest minds in AI about what's real today, what will be real in the future and what it means for businesses and the world - helping builders, researchers and founders deconstruct and understand the biggest breakthroughs. Top guests: Noam Shazeer, Bob McGrew, Noam Brown, Dylan Patel, Percy Liang, David Luan https://www.latent.space/p/unsupervised-learning Timestamps 00:00 Introduction and Excitement for Collaboration 00:27 Reflecting on Surprises in AI Over the Past Year 01:44 Open Source Models and Their Adoption 06:01 The Rise of GPT Wrappers 06:55 AI Builders and Low-Code Platforms 09:35 Overhyped and Underhyped AI Trends 22:17 Product Market Fit in AI 28:23 Google's Current Momentum 28:33 Customer Support and AI 29:54 AI's Impact on Cost and Growth 31:05 Voice AI and Scheduling 32:59 Emerging AI Applications 34:12 Education and AI 36:34 Defensibility in AI Applications 40:10 Infrastructure and AI 47:08 Challenges and Future of AI 52:15 Quick Fire Round and Closing Remarks Chapters 00:00:00 Introduction and Collab Excitement 00:00:58 Open Source and Model Adoption 00:01:58 Enterprise Use of Open Source Models 00:02:57 The Competitive Edge of Closed Source Models 00:03:56 DeepSea and Open Source Model Releases 00:04:54 Market Narrative and DeepSea Impact 00:05:53 AI Engineering and GPT Wrappers 00:06:53 AI Builders and Low-Code Platforms 00:07:50 Innovating Beyond Existing Paradigms 00:08:50 Apple and AI Product Development 00:09:48 Overhyped and Underhyped AI Trends 00:10:46 Frameworks and Protocols in AI Development 00:11:45 Emerging Opportunities in AI 00:12:44 Stateful AI and Memory Innovation 00:13:44 Challenges with Memory in AI Agents 00:14:44 The Future of Model Training Companies 00:15:44 Specialized Use Cases for AI Models 00:16:44 Vertical Models vs General Purpose Models 00:17:42 General Purpose vs Domain-Specific Models 00:18:42 Reflections on Model Companies 00:19:39 Model Companies Entering Product Space 00:20:38 Competition in AI Model and Product Sectors 00:21:35 Coding Agents and Market Dynamics 00:22:35 Defensibility in AI Applications 00:23:35 Investing in Underappreciated AI Ventures 00:24:32 Analyzing Market Fit in AI 00:25:31 AI Applications with Product Market Fit 00:26:31 OpenAI's Impact on the Market 00:27:31 Google and OpenAI Competition 00:28:31 Exploring Google's Advancements 00:29:29 Customer Support and AI Applications 00:30:27 The Future of AI in Customer Support 00:31:26 Cost-Cutting vs Growth in AI 00:32:23 Voice AI and Real-World Applications 00:33:23 Scaling AI Applications for Demand 00:34:22 Summarization and Conversational AI 00:35:20 Future AI Use Cases and Market Fit 00:36:20 AI Education and Model Capabilities 00:37:17 Reforming Education with AI 00:38:15 Defensibility in AI Apps 00:39:13 Network Effects and AI 00:40:12 AI Brand and Market Positioning 00:41:11 AI Application Defensibility 00:42:09 LLM OS and AI Infrastructure 00:43:06 Security and AI Application 00:44:06 OpenAI's Role in AI Infrastructure 00:45:02 The Balance of AI Applications and Infrastructure 00:46:02 Capital Efficiency in AI Infrastructure 00:47:01 Challenges in AI DevOps and Infrastructure 00:47:59 AI SRE and Monitoring 00:48:59 Scaling AI and Hardware Challenges 00:49:58 Reliability and Compute in AI 00:50:57 Nvidia's Dominance and AI Hardware 00:51:57 Emerging Competition in AI Silicon 00:52:54 Agent Authentication Challenges 00:53:53 Dream Podcast Guests 00:54:51 Favorite News Sources and Startups 00:55:50 The Value of In-Person Conversations 00:56:50 Private vs Public AI Discourse 00:57:48 Latent Space and Podcasting 00:58:46 Conclusion and Final Thoughts
This conversation explores the complexities of classroom censorship, the impact of educational policies on teacher autonomy, and the importance of fostering trust and transparency in education. Experts discuss the challenges teachers face in navigating restrictive guidelines while striving to engage students in meaningful discussions. The dialogue emphasizes the need for professionalism, objectivity, and skills development for constructive conversations in the classroom. Additionally, the panel shares resources and strategies to effectively support educators in addressing these challenges. Follow our PLN on Twitter: @rickwormeli2 @rpondiscio @mellyteaches @bamradionetwork @jonHarper70bd @curriculumblog Dr. Steven Weber is an Assistant Principal at Rogers Heritage High School (AR). He has spent over twenty five years in education, serving as a teacher, administrator, and adjunct professor. His leadership experience includes serving as Associate Superintendent for Teaching and Learning with Fayetteville Public Schools (AR), Executive Director for Curriculum and Instruction with Chapel Hill-Carrboro City Schools (NC), and Director of Secondary Instruction for Orange County Schools (NC). Weber was a social studies curriculum specialist with the Arkansas Department of Education and North Carolina Department of Public Instruction. In 2019, Weber was named the AACIA (Arkansas Association of Curriculum & Instruction Administrators) Administrator of the Year. Weber is the past president of Arkansas Association of Curriculum & Instruction Administrators, vice president of Arkansas ASCD, and has served on multiple state and national boards. Robert Pondiscio is a senior fellow at the American Enterprise Institute where he focuses on K–12 education, curriculum, teaching, school choice, and charter schooling. He is also a former New York City public school teacher and the author of many books, including “How the Other Half Learns: Equality, Excellence, and the Battle over School Choice” (Avery, 2019), about Success Academy Charter Schools. Rick Wormeli is a long-time teacher, education leader, and teacher/principal trainer. He is the author of nine books, including The Collected Writings (So Far) of Rick Wormeli: Crazy, Good Stuff I Learned about Teaching Along the Way (AMLE), Fair Isn't Always Equal: Second Edition (Taylor & Francis), Metaphors & Analogies: Power Tools for Teaching any Subject (Taylor & Francis), and Summarization in any Subject: 60 Innovative, Tech-Infused Strategies for Deeper Student Learning, 2nd edition, co-authored with Dedra Stafford. He is currently working directly with schools and organizations in variety of education elements, including accurate/ethical grading, equity, motivation, cognitive psychology applications, teacher professionalism, literacy, and teacher leadership. Christina Andrade Melly, an English teacher at Ritenour High School in the Ritenour School District in St. Louis, Mo., was recently named the 2023 Missouri Teacher of the Year 2023.
Listen Ad Free https://www.solgoodmedia.com - Listen to hundreds of audiobooks, thousands of short stories, and ambient sounds all ad free!
Edge of the Web - An SEO Podcast for Today's Digital Marketer
What is the future of Large Language Models and Search? Kristine Schachinger, SEO consultant at Sites Without Walls, joins us for another episode to discuss the intricacies of Navboost and its ramifications for SEO. Drawing insights from the recent Google versus DOJ court documents, she unpacks this misunderstood “ranking signal.” Continuing the conversation, Kristine shares the concept of “summarization engines” in replacement of AI Search - as she weighs into what the future of search may be and most likely won't be. Large language models aren't all what they are cracked up to be. What is the real scenario, with worsening quality, exploding costs, and unsustainable investments? [00:05:52] Ensuring Factual Information To Protect Clients. [00:10:24] Google's Monopoly Deemed Illegal; Future Uncertain. [00:14:17] EDGE of the Web Sponsor: Site Strategics [00:18:36] Could AI Become The Default Search Engine? [00:22:09] Language Models: Quality, Costs, Investment. [00:27:40] AI Models Decentralized [00:34:06] EDGE of The Web Sponsor: Wix Studio Thanks to our sponsors! Site Strategics: http://edgeofthewebradio.com/site Wix: http://edgeofthewebradio.com/wix Follow Our Guest Twitter: https://x.com/schachin LinkedIn: https://www.linkedin.com/in/kschachinger-seo
Listen Ad Free https://www.solgoodmedia.com - Listen to hundreds of audiobooks, thousands of short stories, and ambient sounds all ad free!
OpenAI DevDay is almost here! Per tradition, we are hosting a DevDay pregame event for everyone coming to town! Join us with demos and gossip!Also sign up for related events across San Francisco: the AI DevTools Night, the xAI open house, the Replicate art show, the DevDay Watch Party (for non-attendees), Hack Night with OpenAI at Cloudflare. For everyone else, join the Latent Space Discord for our online watch party and find fellow AI Engineers in your city.OpenAI's recent o1 release (and Reflection 70b debacle) has reignited broad interest in agentic general reasoning and tree search methods.While we have covered some of the self-taught reasoning literature on the Latent Space Paper Club, it is notable that the Eric Zelikman ended up at xAI, whereas OpenAI's hiring of Noam Brown and now Shunyu suggests more interest in tool-using chain of thought/tree of thought/generator-verifier architectures for Level 3 Agents.We were more than delighted to learn that Shunyu is a fellow Latent Space enjoyer, and invited him back (after his first appearance on our NeurIPS 2023 pod) for a look through his academic career with Harrison Chase (one year after his first LS show).ReAct: Synergizing Reasoning and Acting in Language Modelspaper linkFollowing seminal Chain of Thought papers from Wei et al and Kojima et al, and reflecting on lessons from building the WebShop human ecommerce trajectory benchmark, Shunyu's first big hit, the ReAct paper showed that using LLMs to “generate both reasoning traces and task-specific actions in an interleaved manner” achieved remarkably greater performance (less hallucination/error propagation, higher ALFWorld/WebShop benchmark success) than CoT alone. In even better news, ReAct scales fabulously with finetuning:As a member of the elite Princeton NLP group, Shunyu was also a coauthor of the Reflexion paper, which we discuss in this pod.Tree of Thoughtspaper link hereShunyu's next major improvement on the CoT literature was Tree of Thoughts:Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role…ToT allows LMs to perform deliberate decision making by considering multiple different reasoning paths and self-evaluating choices to decide the next course of action, as well as looking ahead or backtracking when necessary to make global choices.The beauty of ToT is it doesnt require pretraining with exotic methods like backspace tokens or other MCTS architectures. You can listen to Shunyu explain ToT in his own words on our NeurIPS pod, but also the ineffable Yannic Kilcher:Other WorkWe don't have the space to summarize the rest of Shunyu's work, you can listen to our pod with him now, and recommend the CoALA paper and his initial hit webinar with Harrison, today's guest cohost:as well as Shunyu's PhD Defense Lecture:as well as Shunyu's latest lecture covering a Brief History of LLM Agents:As usual, we are live on YouTube! Show Notes* Harrison Chase* LangChain, LangSmith, LangGraph* Shunyu Yao* Alec Radford* ReAct Paper* Hotpot QA* Tau Bench* WebShop* SWE-Agent* SWE-Bench* Trees of Thought* CoALA Paper* Related Episodes* Our Thomas Scialom (Meta) episode* Shunyu on our NeurIPS 2023 Best Papers episode* Harrison on our LangChain episode* Mentions* Sierra* Voyager* Jason Wei* Tavily* SERP API* ExaTimestamps* [00:00:00] Opening Song by Suno* [00:03:00] Introductions* [00:06:16] The ReAct paper* [00:12:09] Early applications of ReAct in LangChain* [00:17:15] Discussion of the Reflection paper* [00:22:35] Tree of Thoughts paper and search algorithms in language models* [00:27:21] SWE-Agent and SWE-Bench for coding benchmarks* [00:39:21] CoALA: Cognitive Architectures for Language Agents* [00:45:24] Agent-Computer Interfaces (ACI) and tool design for agents* [00:49:24] Designing frameworks for agents vs humans* [00:53:52] UX design for AI applications and agents* [00:59:53] Data and model improvements for agent capabilities* [01:19:10] TauBench* [01:23:09] Promising areas for AITranscriptAlessio [00:00:01]: Hey, everyone, welcome to the Latent Space podcast. This is Alessio, partner and CTO of Residence at Decibel Partners, and I'm joined by my co-host Swyx, founder of Small AI.Swyx [00:00:12]: Hey, and today we have a super special episode. I actually always wanted to take like a selfie and go like, you know, POV, you're about to revolutionize the world of agents because we have two of the most awesome hiring agents in the house. So first, we're going to welcome back Harrison Chase. Welcome. Excited to be here. What's new with you recently in sort of like the 10, 20 second recap?Harrison [00:00:34]: Linkchain, Linksmith, Lingraph, pushing on all of them. Lots of cool stuff related to a lot of the stuff that we're going to talk about today, probably.Swyx [00:00:42]: Yeah.Alessio [00:00:43]: We'll mention it in there. And the Celtics won the title.Swyx [00:00:45]: And the Celtics won the title. You got that going on for you. I don't know. Is that like floorball? Handball? Baseball? Basketball.Alessio [00:00:52]: Basketball, basketball.Harrison [00:00:53]: Patriots aren't looking good though, so that's...Swyx [00:00:56]: And then Xun Yu, you've also been on the pod, but only in like a sort of oral paper presentation capacity. But welcome officially to the LinkedSpace pod.Shunyu [00:01:03]: Yeah, I've been a huge fan. So thanks for the invitation. Thanks.Swyx [00:01:07]: Well, it's an honor to have you on. You're one of like, you're maybe the first PhD thesis defense I've ever watched in like this AI world, because most people just publish single papers, but every paper of yours is a banger. So congrats.Shunyu [00:01:22]: Thanks.Swyx [00:01:24]: Yeah, maybe we'll just kick it off with, you know, what was your journey into using language models for agents? I like that your thesis advisor, I didn't catch his name, but he was like, you know... Karthik. Yeah. It's like, this guy just wanted to use language models and it was such a controversial pick at the time. Right.Shunyu [00:01:39]: The full story is that in undergrad, I did some computer vision research and that's how I got into AI. But at the time, I feel like, you know, you're just composing all the GAN or 3D perception or whatever together and it's not exciting anymore. And one day I just see this transformer paper and that's really cool. But I really got into language model only when I entered my PhD and met my advisor Karthik. So he was actually the second author of GPT-1 when he was like a visiting scientist at OpenAI. With Alec Redford?Swyx [00:02:10]: Yes.Shunyu [00:02:11]: Wow. That's what he told me. It's like back in OpenAI, they did this GPT-1 together and Ilya just said, Karthik, you should stay because we just solved the language. But apparently Karthik is not fully convinced. So he went to Princeton, started his professorship and I'm really grateful. So he accepted me as a student, even though I have no prior knowledge in NLP. And you know, we just met for the first time and he's like, you know, what do you want to do? And I'm like, you know, you have done those test game scenes. That's really cool. I wonder if we can just redo them with language models. And that's how the whole journey began. Awesome.Alessio [00:02:46]: So GPT-2 was out at the time? Yes, that was 2019.Shunyu [00:02:48]: Yeah.Alessio [00:02:49]: Way too dangerous to release. And then I guess the first work of yours that I came across was React, which was a big part of your defense. But also Harrison, when you came on The Pockets last year, you said that was one of the first papers that you saw when you were getting inspired for BlankChain. So maybe give a recap of why you thought it was cool, because you were already working in AI and machine learning. And then, yeah, you can kind of like intro the paper formally. What was that interesting to you specifically?Harrison [00:03:16]: Yeah, I mean, I think the interesting part was using these language models to interact with the outside world in some form. And I think in the paper, you mostly deal with Wikipedia. And I think there's some other data sets as well. But the outside world is the outside world. And so interacting with things that weren't present in the LLM and APIs and calling into them and thinking about the React reasoning and acting and kind of like combining those together and getting better results. I'd been playing around with LLMs, been talking with people who were playing around with LLMs. People were trying to get LLMs to call into APIs, do things, and it was always, how can they do it more reliably and better? And so this paper was basically a step in that direction. And I think really interesting and also really general as well. Like I think that's part of the appeal is just how general and simple in a good way, I think the idea was. So that it was really appealing for all those reasons.Shunyu [00:04:07]: Simple is always good. Yeah.Alessio [00:04:09]: Do you have a favorite part? Because I have one favorite part from your PhD defense, which I didn't understand when I read the paper, but you said something along the lines, React doesn't change the outside or the environment, but it does change the insight through the context, putting more things in the context. You're not actually changing any of the tools around you to work for you, but you're changing how the model thinks. And I think that was like a very profound thing when I, not that I've been using these tools for like 18 months. I'm like, I understand what you meant, but like to say that at the time you did the PhD defense was not trivial. Yeah.Shunyu [00:04:41]: Another way to put it is like thinking can be an extra tool that's useful.Alessio [00:04:47]: Makes sense. Checks out.Swyx [00:04:49]: Who would have thought? I think it's also more controversial within his world because everyone was trying to use RL for agents. And this is like the first kind of zero gradient type approach. Yeah.Shunyu [00:05:01]: I think the bigger kind of historical context is that we have this two big branches of AI. So if you think about RL, right, that's pretty much the equivalent of agent at a time. And it's like agent is equivalent to reinforcement learning and reinforcement learning is equivalent to whatever game environment they're using, right? Atari game or go or whatever. So you have like a pretty much, you know, you have a biased kind of like set of methodologies in terms of reinforcement learning and represents agents. On the other hand, I think NLP is like a historical kind of subject. It's not really into agents, right? It's more about reasoning. It's more about solving those concrete tasks. And if you look at SEL, right, like each task has its own track, right? Summarization has a track, question answering has a track. So I think really it's about rethinking agents in terms of what could be the new environments that we came to have is not just Atari games or whatever video games, but also those text games or language games. And also thinking about, could there be like a more general kind of methodology beyond just designing specific pipelines for each NLP task? That's like the bigger kind of context, I would say.Alessio [00:06:14]: Is there an inspiration spark moment that you remember or how did you come to this? We had Trida on the podcast and he mentioned he was really inspired working with like systems people to think about Flash Attention. What was your inspiration journey?Shunyu [00:06:27]: So actually before React, I spent the first two years of my PhD focusing on text-based games, or in other words, text adventure games. It's a very kind of small kind of research area and quite ad hoc, I would say. And there are like, I don't know, like 10 people working on that at the time. And have you guys heard of Zork 1, for example? So basically the idea is you have this game and you have text observations, like you see a monster, you see a dragon.Swyx [00:06:57]: You're eaten by a grue.Shunyu [00:06:58]: Yeah, you're eaten by a grue. And you have actions like kill the grue with a sword or whatever. And that's like a very typical setup of a text game. So I think one day after I've seen all the GPT-3 stuff, I just think about, you know, how can I solve the game? Like why those AI, you know, machine learning methods are pretty stupid, but we are pretty good at solving the game relatively, right? So for the context, the predominant method to solve this text game is obviously reinforcement learning. And the idea is you just try out an arrow in those games for like millions of steps and you kind of just overfit to the game. But there's no language understanding at all. And I'm like, why can't I solve the game better? And it's kind of like, because we think about the game, right? Like when we see this very complex text observation, like you see a grue and you might see a sword, you know, in the right of the room and you have to go through the wooden door to go to that room. You will think, you know, oh, I have to kill the monster and to kill that monster, I have to get the sword, I have to get the sword, I have to go, right? And this kind of thinking actually helps us kind of throw shots off the game. And it's like, why don't we also enable the text agents to think? And that's kind of the prototype of React. And I think that's actually very interesting because the prototype, I think, was around November of 2021. So that's even before like chain of thought or whatever came up. So we did a bunch of experiments in the text game, but it was not really working that well. Like those text games are just too hard. I think today it's still very hard. Like if you use GPD 4 to solve it, it's still very hard. So the change came when I started the internship in Google. And apparently Google care less about text game, they care more about what's more practical. So pretty much I just reapplied the idea, but to more practical kind of environments like Wikipedia or simpler text games like Alphard, and it just worked. It's kind of like you first have the idea and then you try to find the domains and the problems to demonstrate the idea, which is, I would say, different from most of the AI research, but it kind of worked out for me in that case.Swyx [00:09:09]: For Harrison, when you were implementing React, what were people applying React to in the early days?Harrison [00:09:14]: I think the first demo we did probably had like a calculator tool and a search tool. So like general things, we tried to make it pretty easy to write your own tools and plug in your own things. And so this is one of the things that we've seen in LangChain is people who build their own applications generally write their own tools. Like there are a few common ones. I'd say like the three common ones might be like a browser, a search tool, and a code interpreter. But then other than that-Swyx [00:09:37]: The LMS. Yep.Harrison [00:09:39]: Yeah, exactly. It matches up very nice with that. And we actually just redid like our integrations docs page, and if you go to the tool section, they like highlight those three, and then there's a bunch of like other ones. And there's such a long tail of other ones. But in practice, like when people go to production, they generally have their own tools or maybe one of those three, maybe some other ones, but like very, very few other ones. So yeah, I think the first demos was a search and a calculator one. And there's- What's the data set?Shunyu [00:10:04]: Hotpot QA.Harrison [00:10:05]: Yeah. Oh, so there's that one. And then there's like the celebrity one by the same author, I think.Swyx [00:10:09]: Olivier Wilde's boyfriend squared. Yeah. 0.23. Yeah. Right, right, right.Harrison [00:10:16]: I'm forgetting the name of the author, but there's-Swyx [00:10:17]: I was like, we're going to over-optimize for Olivier Wilde's boyfriend, and it's going to change next year or something.Harrison [00:10:21]: There's a few data sets kind of like in that vein that require multi-step kind of like reasoning and thinking. So one of the questions I actually had for you in this vein, like the React paper, there's a few things in there, or at least when I think of that, there's a few things that I think of. There's kind of like the specific prompting strategy. Then there's like this general idea of kind of like thinking and then taking an action. And then there's just even more general idea of just like taking actions in a loop. Today, like obviously language models have changed a lot. We have tool calling. The specific prompting strategy probably isn't used super heavily anymore. Would you say that like the concept of React is still used though? Or like do you think that tool calling and running tool calling in a loop, is that ReactSwyx [00:11:02]: in your mind?Shunyu [00:11:03]: I would say like it's like more implicitly used than explicitly used. To be fair, I think the contribution of React is actually twofold. So first is this idea of, you know, we should be able to use calls in a very general way. Like there should be a single kind of general method to handle interaction with various environments. I think React is the first paper to demonstrate the idea. But then I think later there are two form or whatever, and this becomes like a trivial idea. But I think at the time, that's like a pretty non-trivial thing. And I think the second contribution is this idea of what people call like inner monologue or thinking or reasoning or whatever, to be paired with tool use. I think that's still non-trivial because if you look at the default function calling or whatever, like there's no inner monologue. And in practice, that actually is important, especially if the tool that you use is pretty different from the training distribution of the language model. I think those are the two main things that are kind of inherited.Harrison [00:12:10]: On that note, I think OpenAI even recommended when you're doing tool calling, it's sometimes helpful to put a thought field in the tool, along with all the actual acquired arguments,Swyx [00:12:19]: and then have that one first.Harrison [00:12:20]: So it fills out that first, and they've shown that that's yielded better results. The reason I ask is just like this same concept is still alive, and I don't know whether to call it a React agent or not. I don't know what to call it. I think of it as React, like it's the same ideas that were in the paper, but it's obviously a very different implementation at this point in time. And so I just don't know what to call it.Shunyu [00:12:40]: I feel like people will sometimes think more in terms of different tools, right? Because if you think about a web agent versus, you know, like a function calling agent, calling a Python API, you would think of them as very different. But in some sense, the methodology is the same. It depends on how you view them, right? I think people will tend to think more in terms of the environment and the tools rather than the methodology. Or, in other words, I think the methodology is kind of trivial and simple, so people will try to focus more on the different tools. But I think it's good to have a single underlying principle of those things.Alessio [00:13:17]: How do you see the surface of React getting molded into the model? So a function calling is a good example of like, now the model does it. What about the thinking? Now most models that you use kind of do chain of thought on their own, they kind of produce steps. Do you think that more and more of this logic will be in the model? Or do you think the context window will still be the main driver of reasoning and thinking?Shunyu [00:13:39]: I think it's already default, right? You do some chain of thought and you do some tool call, the cost of adding the chain of thought is kind of relatively low compared to other things. So it's not hurting to do that. And I think it's already kind of common practice, I would say.Swyx [00:13:56]: This is a good place to bring in either Tree of Thought or Reflection, your pick.Shunyu [00:14:01]: Maybe Reflection, to respect the time order, I would say.Swyx [00:14:05]: Any backstory as well, like the people involved with NOAA and the Princeton group. We talked about this offline, but people don't understand how these research pieces come together and this ideation.Shunyu [00:14:15]: I think Reflection is mostly NOAA's work, I'm more like advising kind of role. The story is, I don't remember the time, but one day we just see this pre-print that's like Reflection and Autonomous Agent with memory or whatever. And it's kind of like an extension to React, which uses this self-reflection. I'm like, oh, somehow you've become very popular. And NOAA reached out to me, it's like, do you want to collaborate on this and make this from an archive pre-print to something more solid, like a conference submission? I'm like, sure. We started collaborating and we remain good friends today. And I think another interesting backstory is NOAA was contacted by OpenAI at the time. It's like, this is pretty cool, do you want to just work at OpenAI? And I think Sierra also reached out at the same time. It's like, this is pretty cool, do you want to work at Sierra? And I think NOAA chose Sierra, but it's pretty cool because he was still like a second year undergrad and he's a very smart kid.Swyx [00:15:16]: Based on one paper. Oh my god.Shunyu [00:15:19]: He's done some other research based on programming language or chemistry or whatever, but I think that's the paper that got the attention of OpenAI and Sierra.Swyx [00:15:28]: For those who haven't gone too deep on it, the way that you present the inside of React, can you do that also for reflection? Yeah.Shunyu [00:15:35]: I think one way to think of reflection is that the traditional idea of reinforcement learning is you have a scalar reward and then you somehow back-propagate the signal of the scalar reward to the rest of your neural network through whatever algorithm, like policy grading or A2C or whatever. And if you think about the real life, most of the reward signal is not scalar. It's like your boss told you, you should have done a better job in this, but you could jump on that or whatever. It's not like a scalar reward, like 29 or something. I think in general, humans deal more with long scalar reward, or you can say language feedback. And the way that they deal with language feedback also has this back-propagation process, right? Because you start from this, you did a good job on job B, and then you reflect what could have been done differently to change to make it better. And you kind of change your prompt, right? Basically, you change your prompt on how to do job A and how to do job B, and then you do the whole thing again. So it's really like a pipeline of language where in self-graded descent, you have something like text reasoning to replace those gradient descent algorithms. I think that's one way to think of reflection.Harrison [00:16:47]: One question I have about reflection is how general do you think the algorithm there is? And so for context, I think at LangChain and at other places as well, we found it pretty easy to implement React in a standard way. You plug in any tools and it kind of works off the shelf, can get it up and running. I don't think we have an off-the-shelf kind of implementation of reflection and kind of the general sense. I think the concepts, absolutely, we see used in different kind of specific cognitive architectures, but I don't think we have one that comes off the shelf. I don't think any of the other frameworks have one that comes off the shelf. And I'm curious whether that's because it's not general enough or it's complex as well, because it also requires running it more times.Swyx [00:17:28]: Maybe that's not feasible.Harrison [00:17:30]: I'm curious how you think about the generality, complexity. Should we have one that comes off the shelf?Shunyu [00:17:36]: I think the algorithm is general in the sense that it's just as general as other algorithms, if you think about policy grading or whatever, but it's not applicable to all tasks, just like other algorithms. So you can argue PPO is also general, but it works better for those set of tasks, but not on those set of tasks. I think it's the same situation for reflection. And I think a key bottleneck is the evaluator, right? Basically, you need to have a good sense of the signal. So for example, if you are trying to do a very hard reasoning task, say mathematics, for example, and you don't have any tools, you're operating in this chain of thought setup, then reflection will be pretty hard because in order to reflect upon your thoughts, you have to have a very good evaluator to judge whether your thought is good or not. But that might be as hard as solving the problem itself or even harder. The principle of self-reflection is probably more applicable if you have a good evaluator, for example, in the case of coding. If you have those arrows, then you can just reflect on that and how to solve the bug andSwyx [00:18:37]: stuff.Shunyu [00:18:38]: So I think another criteria is that it depends on the application, right? If you have this latency or whatever need for an actual application with an end-user, the end-user wouldn't let you do two hours of tree-of-thought or reflection, right? You need something as soon as possible. So in that case, maybe this is better to be used as a training time technique, right? You do those reflection or tree-of-thought or whatever, you get a lot of data, and then you try to use the data to train your model better. And then in test time, you still use something as simple as React, but that's already improved.Alessio [00:19:11]: And if you think of the Voyager paper as a way to store skills and then reuse them, how would you compare this reflective memory and at what point it's just ragging on the memory versus you want to start to fine-tune some of them or what's the next step once you get a very long reflective corpus? Yeah.Shunyu [00:19:30]: So I think there are two questions here. The first question is, what type of information or memory are you considering, right? Is it like semantic memory that stores knowledge about the word, or is it the episodic memory that stores trajectories or behaviors, or is it more of a procedural memory like in Voyager's case, like skills or code snippets that you can use to do actions, right?Swyx [00:19:54]: That's one dimension.Shunyu [00:19:55]: And the second dimension is obviously how you use the memory, either retrieving from it, using it in the context, or fine-tuning it. I think the Cognitive Architecture for Language Agents paper has a good categorization of all the different combinations. And of course, which way you use depends on the concrete application and the concrete need and the concrete task. But I think in general, it's good to think of those systematic dimensions and all the possible options there.Swyx [00:20:25]: Harrison also has in LangMEM, I think you did a presentation in my meetup, and I think you've done it at a couple other venues as well. User state, semantic memory, and append-only state, I think kind of maps to what you just said.Shunyu [00:20:38]: What is LangMEM? Can I give it like a quick...Harrison [00:20:40]: One of the modules of LangChain for a long time has been something around memory. And I think we're still obviously figuring out what that means, as is everyone kind of in the space. But one of the experiments that we did, and one of the proof of concepts that we did was, technically what it was is you would basically create threads, you'd push messages to those threads in the background, we process the data in a few ways. One, we put it into some semantic store, that's the semantic memory. And then two, we do some extraction and reasoning over the memories to extract. And we let the user define this, but extract key facts or anything that's of interest to the user. Those aren't exactly trajectories, they're maybe more closer to the procedural memory. Is that how you'd think about it or classify it?Shunyu [00:21:22]: Is it like about knowledge about the word, or is it more like how to do something?Swyx [00:21:27]: It's reflections, basically.Harrison [00:21:28]: So in generative worlds.Shunyu [00:21:30]: Generative agents.Swyx [00:21:31]: The Smallville. Yeah, the Smallville one.Harrison [00:21:33]: So the way that they had their memory there was they had the sequence of events, and that's kind of like the raw events that happened. But then every N events, they'd run some synthesis over those events for the LLM to insert its own memory, basically. It's that type of memory.Swyx [00:21:49]: I don't know how that would be classified.Shunyu [00:21:50]: I think of that as more of the semantic memory, but to be fair, I think it's just one way to think of that. But whether it's semantic memory or procedural memory or whatever memory, that's like an abstraction layer. But in terms of implementation, you can choose whatever implementation for whatever memory. So they're totally kind of orthogonal. I think it's more of a good way to think of the things, because from the history of cognitive science and cognitive architecture and how people study even neuroscience, that's the way people think of how the human brain organizes memory. And I think it's more useful as a way to think of things. But it's not like for semantic memory, you have to do this kind of way to retrieve or fine-tune, and for procedural memory, you have to do that. I think those are totally orthogonal kind of dimensions.Harrison [00:22:34]: How much background do you have in cognitive sciences, and how much do you model some of your thoughts on?Shunyu [00:22:40]: That's a great question, actually. I think one of the undergrad influences for my follow-up research is I was doing an internship at MIT's Computational Cognitive Science Lab with Josh Tannenbaum, and he's a very famous cognitive scientist. And I think a lot of his ideas still influence me today, like thinking of things in computational terms and getting interested in language and a lot of stuff, or even developing psychology kind of stuff. So I think it still influences me today.Swyx [00:23:14]: As a developer that tried out LangMEM, the way I view it is just it's a materialized view of a stream of logs. And if anything, that's just useful for context compression. I don't have to use the full context to run it over everything. But also it's kind of debuggable. If it's wrong, I can show it to the user, the user can manually fix it, and I can carry on. That's a really good analogy. I like that. I'm going to steal that. Sure. Please, please. You know I'm bullish on memory databases. I guess, Tree of Thoughts? Yeah, Tree of Thoughts.Shunyu [00:23:39]: I feel like I'm relieving the defense in like a podcast format. Yeah, no.Alessio [00:23:45]: I mean, you had a banger. Well, this is the one where you're already successful and we just highlight the glory. It was really good. You mentioned that since thinking is kind of like taking an action, you can use action searching algorithms to think of thinking. So just like you will use Tree Search to find the next thing. And the idea behind Tree of Thought is that you generate all these possible outcomes and then find the best tree to get to the end. Maybe back to the latency question, you can't really do that if you have to respond in real time. So what are maybe some of the most helpful use cases for things like this? Where have you seen people adopt it where the high latency is actually worth the wait?Shunyu [00:24:21]: For things that you don't care about latency, obviously. For example, if you're trying to do math, if you're just trying to come up with a proof. But I feel like one type of task is more about searching for a solution. You can try a hundred times, but if you find one solution, that's good. For example, if you're finding a math proof or if you're finding a good code to solve a problem or whatever, I think another type of task is more like reacting. For example, if you're doing customer service, you're like a web agent booking a ticket for an end user. Those are more reactive kind of tasks, or more real-time tasks. You have to do things fast. They might be easy, but you have to do it reliably. And you care more about can you solve 99% of the time out of a hundred. But for the type of search type of tasks, then you care more about can I find one solution out of a hundred. So it's kind of symmetric and different.Alessio [00:25:11]: Do you have any data or intuition from your user base? What's the split of these type of use cases? How many people are doing more reactive things and how many people are experimenting with deep, long search?Harrison [00:25:23]: I would say React's probably the most popular. I think there's aspects of reflection that get used. Tree of thought, probably the least so. There's a great tweet from Jason Wei, I think you're now a colleague, and he was talking about prompting strategies and how he thinks about them. And I think the four things that he had was, one, how easy is it to implement? How much compute does it take? How many tasks does it solve? And how much does it improve on those tasks? And I'd add a fifth, which is how likely is it to be relevant when the next generation of models come out? And I think if you look at those axes and then you look at React, reflection, tree of thought, it tracks that the ones that score better are used more. React is pretty easy to implement. Tree of thought's pretty hard to implement. The amount of compute, yeah, a lot more for tree of thought. The tasks and how much it improves, I don't have amazing visibility there. But I think if we're comparing React versus tree of thought, React just dominates the first two axes so much that my question around that was going to be like, how do you think about these prompting strategies, cognitive architectures, whatever you want to call them? When you're thinking of them, what are the axes that you're judging them on in your head when you're thinking whether it's a good one or a less good one?Swyx [00:26:38]: Right.Shunyu [00:26:39]: Right. I think there is a difference between a prompting method versus research, in the sense that for research, you don't really even care about does it actually work on practical tasks or does it help? Whatever. I think it's more about the idea or the principle, right? What is the direction that you're unblocking and whatever. And I think for an actual prompting method to solve a concrete problem, I would say simplicity is very important because the simpler it is, the less decision you have to make about it. And it's easier to design. It's easier to propagate. And it's easier to do stuff. So always try to be as simple as possible. And I think latency obviously is important. If you can do things fast and you don't want to do things slow. And I think in terms of the actual prompting method to use for a particular problem, I think we should all be in the minimalist kind of camp, right? You should try the minimum thing and see if it works. And if it doesn't work and there's absolute reason to add something, then you add something, right? If there's absolute reason that you need some tool, then you should add the tool thing. If there's absolute reason to add reflection or whatever, you should add that. Otherwise, if a chain of thought can already solve something, then you don't even need to use any of that.Harrison [00:27:57]: Yeah. Or if it's just better prompting can solve it. Like, you know, you could add a reflection step or you could make your instructions a little bit clearer.Swyx [00:28:03]: And it's a lot easier to do that.Shunyu [00:28:04]: I think another interesting thing is like, I personally have never done those kind of like weird tricks. I think all the prompts that I write are kind of like just talking to a human, right? It's like, I don't know. I never say something like, your grandma is dying and you have to solve it. I mean, those are cool, but I feel like we should all try to solve things in a very intuitive way. Just like talking to your co-worker. That should work 99% of the time. That's my personal take.Swyx [00:28:29]: The problem with how language models, at least in the GPC 3 era, was that they over-optimized to some sets of tokens in sequence. So like reading the Kojima et al. paper that was listing step-by-step, like he tried a bunch of them and they had wildly different results. It should not be the case, but it is the case. And hopefully we're getting better there.Shunyu [00:28:51]: Yeah. I think it's also like a timing thing in the sense that if you think about this whole line of language model, right? Like at the time it was just like a text generator. We don't have any idea how it's going to be used, right? And obviously at the time you will find all kinds of weird issues because it's not trained to do any of that, right? But then I think we have this loop where once we realize chain of thought is important or agent is important or tool using is important, what we see is today's language models are heavily optimized towards those things. So I think in some sense they become more reliable and robust over those use cases. And you don't need to do as much prompt engineering tricks anymore to solve those things. I feel like in some sense, I feel like prompt engineering even is like a slightly negative word at the time because it refers to all those kind of weird tricks that you have to apply. But I think we don't have to do that anymore. Like given today's progress, you should just be able to talk to like a coworker. And if you're clear and concrete and being reasonable, then it should do reasonable things for you.Swyx [00:29:51]: Yeah. The way I put this is you should not be a prompt engineer because it is the goal of the big labs to put you out of a job.Shunyu [00:29:58]: You should just be a good communicator. Like if you're a good communicator to humans, you should be a good communicator to languageSwyx [00:30:02]: models.Harrison [00:30:03]: That's the key though, because oftentimes people aren't good communicators to these language models and that is a very important skill and that's still messing around with the prompt. And so it depends what you're talking about when you're saying prompt engineer.Shunyu [00:30:14]: But do you think it's like very correlated with like, are they like a good communicator to humans? You know, it's like.Harrison [00:30:20]: It may be, but I also think I would say on average, people are probably worse at communicating with language models than to humans right now, at least, because I think we're still figuring out how to do it. You kind of expect it to be magical and there's probably some correlation, but I'd say there's also just like, people are worse at it right now than talking to humans.Shunyu [00:30:36]: We should make it like a, you know, like an elementary school class or whatever, how toSwyx [00:30:41]: talk to language models. Yeah. I don't know. Very pro that. Yeah. Before we leave the topic of trees and searching, not specific about QSTAR, but there's a lot of questions about MCTS and this combination of tree search and language models. And I just had to get in a question there about how seriously should people take this?Shunyu [00:30:59]: Again, I think it depends on the tasks, right? So MCTS was magical for Go, but it's probably not as magical for robotics, right? So I think right now the problem is not even that we don't have good methodologies, it's more about we don't have good tasks. It's also very interesting, right? Because if you look at my citation, it's like, obviously the most cited are React, Refraction and Tree of Thought. Those are methodologies. But I think like equally important, if not more important line of my work is like benchmarks and environments, right? Like WebShop or SuiteVenture or whatever. And I think in general, what people do in academia that I think is not good is they choose a very simple task, like Alford, and then they apply overly complex methods to show they improve 2%. I think you should probably match the level of complexity of your task and your method. I feel like where tasks are kind of far behind the method in some sense, right? Because we have some good test-time approaches, like whatever, React or Refraction or Tree of Thought, or like there are many, many more complicated test-time methods afterwards. But on the benchmark side, we have made a lot of good progress this year, last year. But I think we still need more progress towards that, like better coding benchmark, better web agent benchmark, better agent benchmark, not even for web or code. I think in general, we need to catch up with tasks.Harrison [00:32:27]: What are the biggest reasons in your mind why it lags behind?Shunyu [00:32:31]: I think incentive is one big reason. Like if you see, you know, all the master paper are cited like a hundred times more than the task paper. And also making a good benchmark is actually quite hard. It's almost like a different set of skills in some sense, right? I feel like if you want to build a good benchmark, you need to be like a good kind of product manager kind of mindset, right? You need to think about why people should use your benchmark, why it's challenging, why it's useful. If you think about like a PhD going into like a school, right? The prior skill that expected to have is more about, you know, can they code this method and can they just run experiments and can solve that? I think building a benchmark is not the typical prior skill that we have, but I think things are getting better. I think more and more people are starting to build benchmarks and people are saying that it's like a way to get more impact in some sense, right? Because like if you have a really good benchmark, a lot of people are going to use it. But if you have a super complicated test time method, like it's very hard for people to use it.Harrison [00:33:35]: Are evaluation metrics also part of the reason? Like for some of these tasks that we might want to ask these agents or language models to do, is it hard to evaluate them? And so it's hard to get an automated benchmark. Obviously with SweetBench you can, and with coding, it's easier, but.Shunyu [00:33:50]: I think that's part of the skillset thing that I mentioned, because I feel like it's like a product manager because there are many dimensions and you need to strike a balance and it's really hard, right? If you want to make sense, very easy to autogradable, like automatically gradable, like either to grade or either to evaluate, then you might lose some of the realness or practicality. Or like it might be practical, but it might not be as scalable, right? For example, if you think about text game, human have pre-annotated all the rewards and all the language are real. So it's pretty good on autogradable dimension and the practical dimension. If you think about, you know, practical, like actual English being practical, but it's not scalable, right? It takes like a year for experts to build that game. So it's not really that scalable. And I think part of the reason that SweetBench is so popular now is it kind of hits the balance between these three dimensions, right? Easy to evaluate and being actually practical and being scalable. Like if I were to criticize upon some of my prior work, I think webshop, like it's my initial attempt to get into benchmark world and I'm trying to do a good job striking the balance. But obviously we make it all gradable and it's really scalable, but then I think the practicality is not as high as actually just using GitHub issues, right? Because you're just creating those like synthetic tasks.Harrison [00:35:13]: Are there other areas besides coding that jump to mind as being really good for being autogradable?Shunyu [00:35:20]: Maybe mathematics.Swyx [00:35:21]: Classic. Yeah. Do you have thoughts on alpha proof, the new DeepMind paper? I think it's pretty cool.Shunyu [00:35:29]: I think it's more of a, you know, it's more of like a confidence boost or like sometimes, you know, the work is not even about, you know, the technical details or the methodology that it chooses or the concrete results. I think it's more about a signal, right?Swyx [00:35:47]: Yeah. Existence proof. Yeah.Shunyu [00:35:50]: Yeah. It can be done. This direction is exciting. It kind of encourages people to work more towards that direction. I think it's more like a boost of confidence, I would say.Swyx [00:35:59]: Yeah. So we're going to focus more on agents now and, you know, all of us have a special interest in coding agents. I would consider Devin to be the sort of biggest launch of the year as far as AI startups go. And you guys in the Princeton group worked on Suiagents alongside of Suibench. Tell us the story about Suiagent. Sure.Shunyu [00:36:21]: I think it's kind of like a triology, it's actually a series of three works now. So actually the first work is called Intercode, but it's not as famous, I know. And the second work is called Suibench and the third work is called Suiagent. And I'm just really confused why nobody is working on coding. You know, it's like a year ago, but I mean, not everybody's working on coding, obviously, but a year ago, like literally nobody was working on coding. I was really confused. And the people that were working on coding are, you know, trying to solve human evil in like a sick-to-sick way. There's no agent, there's no chain of thought, there's no anything, they're just, you know, fine tuning the model and improve some points and whatever, like, I was really confused because obviously coding is the best application for agents because it's autogradable, it's super important, you can make everything like API or code action, right? So I was confused and I collaborated with some of the students in Princeton and we have this work called Intercode and the idea is, first, if you care about coding, then you should solve coding in an interactive way, meaning more like a Jupyter Notebook kind of way than just writing a program and seeing if it fails or succeeds and stop, right? You should solve it in an interactive way because that's exactly how humans solve it, right? You don't have to, you know, write a program like next token, next token, next token and stop and never do any edits and you cannot really use any terminal or whatever tool. It doesn't make sense, right? And that's the way people are solving coding at the time, basically like sampling a program from a language model without chain of thought, without tool call, without refactoring, without anything. So the first point is we should solve coding in a very interactive way and that's a very general principle that applies for various coding benchmarks. And also, I think you can make a lot of the agent task kind of like interactive coding. If you have Python and you can call any package, then you can literally also browse internet or do whatever you want, like control a robot or whatever. So that seems to be a very general paradigm. But obviously I think a bottleneck is at the time we're still doing, you know, very simple tasks like human eval or whatever coding benchmark people proposed. They were super hard in 2021, like 20%, but they're like 95% already in 2023. So obviously the next step is we need a better benchmark. And Carlos and John, which are the first authors of Swaybench, I think they come up with this great idea that we should just script GitHub and solve whatever human engineers are solving. And I think it's actually pretty easy to come up with the idea. And I think in the first week, they already made a lot of progress. They script the GitHub and they make all the same, but then there's a lot of painful info work and whatever, you know. I think the idea is super easy, but the engineering is super hard. And I feel like that's a very typical signal of a good work in the AI era now.Swyx [00:39:17]: I think also, I think the filtering was challenging, because if you look at open source PRs, a lot of them are just like, you know, fixing typos. I think it's challenging.Shunyu [00:39:27]: And to be honest, we didn't do a perfect job at the time. So if you look at the recent blog post with OpenAI, we improved the filtering so that it's more solvable.Swyx [00:39:36]: I think OpenAI was just like, look, this is a thing now. We have to fix this. These students just rushed it.Shunyu [00:39:45]: It's a good convergence of interests for me.Alessio [00:39:48]: Was that tied to you joining OpenAI? Or was that just unrelated?Shunyu [00:39:52]: It's a coincidence for me, but it's a good coincidence.Swyx [00:39:55]: There is a history of anytime a big lab adopts a benchmark, they fix it. Otherwise, it's a broken benchmark.Shunyu [00:40:03]: So naturally, once we propose swimmage, the next step is to solve it. But I think the typical way you solve something now is you collect some training samples, or you design some complicated agent method, and then you try to solve it. Either super complicated prompt, or you build a better model with more training data. But I think at the time, we realized that even before those things, there's a fundamental problem with the interface or the tool that you're supposed to use. Because that's like an ignored problem in some sense. What your tool is, or how that matters for your task. So what we found concretely is that if you just use the text terminal off the shelf as a tool for those agents, there's a lot of problems. For example, if you edit something, there's no feedback. So you don't know whether your edit is good or not. That makes the agent very confused and makes a lot of mistakes. There are a lot of small problems, you would say. Well, you can try to do prompt engineering and improve that, but it turns out to be actually very hard. We realized that the interface design is actually a very omitted part of agent design. So we did this switch agent work. And the key idea is just, even before you talk about what the agent is, you should talk about what the environment is. You should make sure that the environment is actually friendly to whatever agent you're trying to apply. That's the same idea for humans. Text terminal is good for some tasks, like git, pool, or whatever. But it's not good if you want to look at browser and whatever. Also, browser is a good tool for some tasks, but it's not a good tool for other tasks. We need to talk about how design interface, in some sense, where we should treat agents as our customers. It's like when we treat humans as a customer, we design human computer interfaces. We design those beautiful desktops or browsers or whatever, so that it's very intuitive and easy for humans to use. And this whole great subject of HCI is all about that. I think now the research idea of switch agent is just, we should treat agents as our customers. And we should do like, you know… AICI.Swyx [00:42:16]: AICI, exactly.Harrison [00:42:18]: So what are the tools that a suite agent should have, or a coding agent in general should have?Shunyu [00:42:24]: For suite agent, it's like a modified text terminal, which kind of adapts to a lot of the patterns of language models to make it easier for language models to use. For example, now for edit, instead of having no feedback, it will actually have a feedback of, you know, actually here you introduced like a syntax error, and you should probably want to fix that, and there's an ended error there. And that makes it super easy for the model to actually do that. And there's other small things, like how exactly you write arguments, right? Like, do you want to write like a multi-line edit, or do you want to write a single line edit? I think it's more interesting to think about the way of the development process of an ACI rather than the actual ACI for like a concrete application. Because I think the general paradigm is very similar to HCI and psychology, right? Basically, for how people develop HCIs, they do behavior experiments on humans, right? I do every test, right? Like, which interface is actually better? And I do those behavior experiments, kind of like psychology experiments to humans, and I change things. And I think what's really interesting for me, for this three-agent paper, is we can probably do the same thing for agents, right? We can do every test for those agents and do behavior tests. And through the process, we not only invent better interfaces for those agents, that's the practical value, but we also better understand agents. Just like when we do those A-B tests, we do those HCI, we better understand humans. Doing those ACI experiments, we actually better understand agents. And that's pretty cool.Harrison [00:43:51]: Besides that A-B testing, what are other processes that people can use to think about this in a good way?Swyx [00:43:57]: That's a great question.Shunyu [00:43:58]: And I think three-agent is an initial work. And what we do is the kind of the naive approach, right? You just try some interface, and you see what's going wrong, and then you try to fix that. We do this kind of iterative fixing. But I think what's really interesting is there'll be a lot of future directions that's very promising if we can apply some of the HCI principles more systematically into the interface design. I think that would be a very cool interdisciplinary research opportunity.Harrison [00:44:26]: You talked a lot about agent-computer interfaces and interactions. What about human-to-agent UX patterns? Curious for any thoughts there that you might have.Swyx [00:44:38]: That's a great question.Shunyu [00:44:39]: And in some sense, I feel like prompt engineering is about human-to-agent interface. But I think there can be a lot of interesting research done about... So prompting is about how humans can better communicate with the agent. But I think there could be interesting research on how agents can better communicate with humans, right? When to ask questions, how to ask questions, what's the frequency of asking questions. And I think those kinds of stuff could be very cool research.Harrison [00:45:07]: Yeah, I think some of the most interesting stuff that I saw here was also related to coding with Devin from Cognition. And they had the three or four different panels where you had the chat, the browser, the terminal, and I guess the code editor as well.Swyx [00:45:19]: There's more now.Harrison [00:45:19]: There's more. Okay, I'm not up to date. Yeah, I think they also did a good job on ACI.Swyx [00:45:25]: I think that's the main learning I have from Devin. They cracked that. Actually, there was no foundational planning breakthrough. The planner is actually pretty simple, but ACI that they broke through on.Shunyu [00:45:35]: I think making the tool good and reliable is probably like 90% of the whole agent. Once the tool is actually good, then the agent design can be much, much simpler. On the other hand, if the tool is bad, then no matter how much you put into the agent design, planning or search or whatever, it's still going to be trash.Harrison [00:45:53]: Yeah, I'd argue the same. Same with like context and instructions. Like, yeah, go hand in hand.Alessio [00:46:00]: On the tool, how do you think about the tension of like, for both of you, I mean, you're building a library, so even more for you. The tension between making now a language or a library that is like easy for the agent to grasp and write versus one that is easy for like the human to grasp and write. Because, you know, the trend is like more and more code gets written by the agent. So why wouldn't you optimize the framework to be as easy as possible for the model versus for the person?Swyx [00:46:24]: I think it's possible to design an interfaceShunyu [00:46:25]: that's both friendly to humans and agents. But what do you think?Harrison [00:46:29]: We haven't thought about that from the perspective, like we're not trying to design LangChain or LangGraph to be friendly. But I mean, I think to be friendly for agents to write.Swyx [00:46:42]: But I mean, I think we see this with like,Harrison [00:46:43]: I saw some paper that used TypeScript notation instead of JSON notation for tool calling and it got a lot better performance. So it's definitely a thing. I haven't really heard of anyone designing like a syntax or a language explicitly for agents, but there's clearly syntaxes that are better.Shunyu [00:46:59]: I think function calling is a good example where it's like a good interface for both human programmers and for agents, right? Like for developers, it's actually a very friendly interface because it's very concrete and you don't have to do prompt engineering anymore. You can be very systematic. And for models, it's also pretty good, right? Like it can use all the existing coding content. So I think we need more of those kinds of designs.Swyx [00:47:21]: I will mostly agree and I'll slightly disagree in terms of this, which is like, whether designing for humans also overlaps with designing for AI. So Malte Ubo, who's the CTO of Vercel, who is creating basically JavaScript's competitor to LangChain, they're observing that basically, like if the API is easy to understand for humans, it's actually much easier to understand for LLMs, for example, because they're not overloaded functions. They don't behave differently under different contexts. They do one thing and they always work the same way. It's easy for humans, it's easy for LLMs. And like that makes a lot of sense. And obviously adding types is another one. Like type annotations only help give extra context, which is really great. So that's the agreement. And then a disagreement is that when I use structured output to do my chain of thought, I have found that I change my field names to hint to the LLM of what the field is supposed to do. So instead of saying topics, I'll say candidate topics. And that gives me a better result because the LLM was like, ah, this is just a draft thing I can use for chain of thought. And instead of like summaries, I'll say topic summaries to link the previous field to the current field. So like little stuff like that, I find myself optimizing for the LLM where I, as a human, would never do that. Interesting.Shunyu [00:48:32]: It's kind of like the way you optimize the prompt, it might be different for humans and for machines. You can have a common ground that's both clear for humans and agents, but to improve the human performance versus improving the agent performance, they might move to different directions.Swyx [00:48:48]: Might move different directions. There's a lot more use of metadata as well, like descriptions, comments, code comments, annotations and stuff like that. Yeah.Harrison [00:48:56]: I would argue that's just you communicatingSwyx [00:48:58]: to the agent what it should do.Harrison [00:49:00]: And maybe you need to communicate a little bit more than to humans because models aren't quite good enough yet.Swyx [00:49:06]: But like, I don't think that's crazy.Harrison [00:49:07]: I don't think that's like- It's not crazy.Swyx [00:49:09]: I will bring this in because it just happened to me yesterday. I was at the cursor office. They held their first user meetup and I was telling them about the LLM OS concept and why basically every interface, every tool was being redesigned for AIs to use rather than humans. And they're like, why? Like, can we just use Bing and Google for LLM search? Why must I use Exa? Or what's the other one that you guys work with?Harrison [00:49:32]: Tavilli.Swyx [00:49:33]: Tavilli. Web Search API dedicated for LLMs. What's the difference?Shunyu [00:49:36]: Exactly. To Bing API.Swyx [00:49:38]: Exactly.Harrison [00:49:38]: There weren't great APIs for search. Like the best one, like the one that we used initially in LangChain was SERP API, which is like maybe illegal. I'm not sure.Swyx [00:49:49]: And like, you know,Harrison [00:49:52]: and now there are like venture-backed companies.Swyx [00:49:53]: Shout out to DuckDuckGo, which is free.Harrison [00:49:55]: Yes, yes.Swyx [00:49:56]: Yeah.Harrison [00:49:56]: I do think there are some differences though. I think you want, like, I think generally these APIs try to return small amounts of text information, clear legible field. It's not a massive JSON blob. And I think that matters. I think like when you talk about designing tools, it's not only the, it's the interface in the entirety, not only the inputs, but also the outputs that really matter. And so I think they try to make the outputs.Shunyu [00:50:18]: They're doing ACI.Swyx [00:50:19]: Yeah, yeah, absolutely.Harrison [00:50:20]: Really?Swyx [00:50:21]: Like there's a whole set of industries that are just being redone for ACI. It's weird. And so my simple answer to them was like the error messages. When you give error messages, they should be basically prompts for the LLM to take and then self-correct. Then your error messages get more verbose, actually, than you normally would with a human. Stuff like that. Like a little, honestly, it's not that big. Again, like, is this worth a venture-backed industry? Unless you can tell us. But like, I think Code Interpreter, I think is a new thing. I hope so.Alessio [00:50:52]: We invested in it to be so.Shunyu [00:50:53]: I think that's a very interesting point. You're trying to optimize to the extreme, then obviously they're going to be different. For example, the error—Swyx [00:51:00]: Because we take it very seriously. Right.Shunyu [00:51:01]: The error for like language model, the longer the better. But for humans, that will make them very nervous and very tired, right? But I guess the point is more like, maybe we should try to find a co-optimized common ground as much as possible. And then if we have divergence, then we should try to diverge. But it's more philosophical now.Alessio [00:51:19]: But I think like part of it is like how you use it. So Google invented the PageRank because ideally you only click on one link, you know, like the top three should have the answer. But with models, it's like, well, you can get 20. So those searches are more like semantic grouping in a way. It's like for this query, I'll return you like 20, 30 things that are kind of good, you know? So it's less about ranking and it's more about grouping.Shunyu [00:51:42]: Another fundamental thing about HCI is the difference between human and machine's kind of memory limit, right? So I think what's really interesting about this concept HCI versus HCI is interfaces that's optimized for them. You can kind of understand some of the fundamental characteristics, differences of humans and machines, right? Why, you know, if you look at find or whatever terminal command, you know, you can only look at one thing at a time or that's because we have a very small working memory. You can only deal with one thing at a time. You can only look at one paragraph of text at the same time. So the interface for us is by design, you know, a small piece of information, but more temporal steps. But for machines, that should be the opposite, right? You should just give them a hundred different results and they should just decide in context what's the most relevant stuff and trade off the context for temporal steps. That's actually also better for language models because like the cost is smaller or whatever. So it's interesting to connect those interfaces to the fundamental kind of differences of those.Harrison [00:52:43]: When you said earlier, you know, we should try to design these to maybe be similar as possible and diverge if we need to.Swyx [00:52:49]: I actually don't have a problem with them diverging nowHarrison [00:52:51]: and seeing venture-backed startups emerging now because we are different from machines code AI. And it's just so early on, like they may still look kind of similar and they may still be small differences, but it's still just so early. And I think we'll only discover more ways that they differ. And so I'm totally fine with them kind of like diverging earlySwyx [00:53:10]: and optimizing for the...Harrison [00:53:11]: I agree. I think it's more like, you know,Shunyu [00:53:14]: we should obviously try to optimize human interface just for humans. We're already doing that for 50 years. We should optimize agent interface just for agents, but we might also try to co-optimize both and see how far we can get. There's enough people to try all three directions. Yeah.Swyx [00:53:31]: There's a thesis I sometimes push, which is the sour lesson as opposed to the bitter lesson, which we're always inspired by human development, but actually AI develops its own path.Shunyu [00:53:40]: Right. We need to understand better, you know, what are the fundamental differences between those creatures.Swyx [00:53:45]: It's funny when really early on this pod, you were like, how much grounding do you have in cognitive development and human brain stuff? And I'm like
Get in Touch! Send us a message.In our last episode, we explored how to use AI to extract the right stuff from meeting summaries. Today's topic is another powerful application of AI: using it as a summarization tool to tackle complex information and make better business decisions.GET IN TOUCH
Today on the show Steven and Shaun review the Apple “It's Glowtime” Event featuring new iPhones, Apple Watch and AirPods. The guys dive into the announcements and share their views on the new iPhone 16 lineup, as well as the embedded Apple Intelligence features that have been announced to arrive this year, starting in the US in October. There's also a look at some exciting developments inside the new Apple Watch Series 10, such as the ability to track sleep apnea. Also later this year, AirPods Pro 2 will get a major new assistive feature to protect and test your hearing, and even turn your AirPods Pro 2 into clinical-grade hearing aids. Get in touch with Double Tap by emailing us feedback@doubletaponair.com or by call 1-877-803-4567 and leave us a voicemail. You can also find us across social media. Double Tap is available daily on AMI-audio across Canada, on podcast worldwide and now on YouTube. Chapter Markers: 0:00 - Intro 0:35 - Intro to the Apple Event 3:17 - Apple Intelligence 16:24 - iPhone 16 Action Button 18:06 - iPhone 16 Camera Control Button 20:48 - iPhone 16 Visual Intelligence 28:31 - iPhone 16 Pro Range 41:27 - Air Pods 45:21 - Air Pods & Hearing Protection 46:13 - Air Pods & Hearing Test 47:23 - Air Pods as Hearing Aids 51:06 - Apple Watch 10 53:40 - Apple Watch 10 & Sleep Apnea Detection
Blueprints set a STANDARD How it should be When blueprints aren't followed, disaster happens That's what this series is about… Blueprints God's design for church and family God is a God of design Psalm 8:3-4 3 When I observe your heavens, the work of your fingers, the moon and the stars, which you set in place, 4 what is a human being that you remember him, a son of man that you look after him? A MAJOR THEME in the story the Bible is telling is: Let's first define Family: A family consists of people, usually related, with shared values that provide safety, guidance, accountability, respect, and forgiveness. Let's build a BIBLICAL THEME of Family… 1: God planned and placed the family at the beginning of creation Genesis 2:24 This is why a man leaves his father and mother and bonds with his wife, and they become one flesh. 2: God designed the family for human flourishing Genesis 1:28 God blessed them, and God said to them, “Be fruitful, multiply, fill the earth, and subdue it. Rule the fish of the sea, the birds of the sky, and every creature that crawls on the earth.” 3: The enemy of God hates family Genesis 4 8 Cain said to his brother Abel, “Let's go out to the field.” And while they were in the field, Cain attacked his brother Abel and killed him. 9 Then the Lord said to Cain, “Where is your brother Abel?” “I don't know,” he replied. “Am I my brother's guardian?” The enemy always tries to mimic and distort to eventually destroy anything g that God has created for our good 4: God has chosen to redeem the world through a family Genesis 12 12 The Lord said to Abram: Go from your land, your relatives, and your father's house to the land that I will show you. 2 I will make you into a great nation, I will bless you, I will make your name great, and you will be a blessing. 3 I will bless those who bless you, I will curse anyone who treats you with contempt, and all the peoples on earth will be blessed through you. What does all this mean? To God, Family is a BIG DEAL His blueprint for human flourishing and happiness is through Family Some Examples: Father vs. Absent Fathers According to the U.S. Census Bureau, 17.8 million children, nearly 1 in 4, live without a biological, step, or adoptive father in the home. No father: Research shows that when a child is raised in a father-absent home, they are affected in the following ways… Greater Risk of Poverty More Likely to Have Behavioral Problems Greater Risk of Infant Mortality More Likely to Go to Prison More Likely to Commit Crime More Likely to Become Pregnant as a Teen More Likely to Face Abuse and Neglect More Likely to Abuse Drugs and Alcohol More Likely to Suffer Obesity More Likely to Drop Out of School Kids: Children with involved fathers have a strong foundation for child well-being. They are at lower risk for… Infant Mortality Low Birth Weight Emotional and Behavioral Problems Neglect and Abuse Injury Obesity Poor School Performance Teen Pregnancy Incarceration as Juveniles Alcohol and Substance Abuse Criminal Activity Suicide Mom: Mothers with active fathers in the home… More likely to receive prenatal care Less likely to smoke during pregnancy Healthier births Lower risk of post-partum stress & depression Lower parenting stress More leisure time Higher marital satisfaction (All info taken from https://www.fatherhood.org) Healthy Families lead to HUMAN FLOURISHING Why? Because it's God's blueprint I don't think anyone has a problem with this, but it is INCOMPLETE in scripture's view of FAMILY… 5: Jesus has come, and not only is our savior but also our BROTHER Hebrews 2 11 For the one who sanctifies and those who are sanctified all have one Father. That is why Jesus is not ashamed to call them brothers and sisters, 12 saying: I will proclaim your name to my brothers and sisters; I will sing hymns to you in the congregation. Because we belong to Christ, we belong to his family 6: The church is a family and the Bride of Christ Ephesians 5 22 Wives, submit to your husbands as to the Lord, 23 because the husband is the head of the wife as Christ is the head of the church. He is the Savior of the body. 24 Now as the church submits to Christ, so also wives are to submit to their husbands in everything. 25 Husbands, love your wives, just as Christ loved the church and gave himself for her 26 to make her holy, cleansing her with the washing of water by the word. 31 For this reason a man will leave his father and mother and be joined to his wife, and the two will become one flesh. 32 This mystery is profound, but I am talking about Christ and the church. God has EXPANDED the understanding of FAMILY Not just “DAD, MOM, KIDS The Bible doesn't have a category for that Sermon Title: More than Blood Here's where there is trouble for us… Family as an INDIVIDUAL INSTITUTION Me and mine vs you and yours Instead, it is US/WE Personal Family is important, and so is the FAMILY OF FAITH Christian Family Church Family The Reality We will spend eternity with our FAITH FAMILY, not necessarily our BLOOD relatives God's family is MORE THAN BLOOD How did this work out in the New Testament? Summarization of the Reason for the letter: Written to Philemon by Paul A resident of Colosse (Colossians) He held church as his house He had a Slave named Onesimus (oh NESS in muss) Onesimus stole money and ran away Met Paul and became a Christian Listen for the “family language” Philemon 1 1 Paul, a prisoner of Christ Jesus, and Timothy our brother: To Philemon our dear friend and coworker, 2 to Apphia our sister, to Archippus our fellow soldier, and to the church that meets in your home. 3 Grace to you and peace from God our Father and the Lord Jesus Christ. 4 I always thank my God when I mention you in my prayers, 5 because I hear of your love for all the saints and the faith that you have in the Lord Jesus. 6 I pray that your participation in the faith may become effective through knowing every good thing that is in us for the glory of Christ. 7 For I have great joy and encouragement from your love, because the hearts of the saints have been refreshed through you, brother. 8 For this reason, although I have great boldness in Christ to command you to do what is right, 9 I appeal to you, instead, on the basis of love. I, Paul, as an elderly man and now also as a prisoner of Christ Jesus, 10 appeal to you for my son, Onesimus. I became his father while I was in chains. 11 Once he was useless to you, but now he is useful both to you and to me. 12 I am sending him back to you—I am sending my very own heart. 13 I wanted to keep him with me, so that in my imprisonment for the gospel he might serve me in your place. 14 But I didn't want to do anything without your consent, so that your good deed might not be out of obligation, but of your own free will. 15 For perhaps this is why he was separated from you for a brief time, so that you might get him back permanently, 16 no longer as a slave, but more than a slave—as a dearly loved brother. He is especially so to me, but how much more to you, both in the flesh and in the Lord. 17 So if you consider me a partner, welcome him as you would me. 18 And if he has wronged you in any way, or owes you anything, charge that to my account. 19 I, Paul, write this with my own hand: I will repay it—not to mention to you that you owe me even your very self. 20 Yes, brother, may I benefit from you in the Lord; refresh my heart in Christ. 21 Since I am confident of your obedience, I am writing to you, knowing that you will do even more than I say. God's plan is still the same…. To redeem the world through family Through those who are a part of His REDEEMED family What should we take away from this? 1: Family is a BIG DEAL to God We should make it a big deal in our lives, too We treat it with respect 2: God's vision for the world is a RENEWED FAMILY With Christ as our king 3: You and your family flourish MOST when a part of God's REDEEMED FAMILY Your family flourishes through its activity in the church family Single Older – no kids You no longer need to feel lonely because you have a LARGE family You no longer need to feel threatened because you are a family that protects You have a part to play because everyone takes part in a healthy family
On this episode of The Digital Patient, Dr. Joshua Liu, Co-founder & CEO of SeamlessMD, and marketing colleague, Alan Sardana, chat with Dr. Michael Ross, System CMIO at Northern Light Health, about the "How AI will improve eConsults with contextual summarization, Talking with Medical Assistants to determine physician fit for AI Scribes, how asynchronous patient care will look in the future and how current reimbursement holds it back, and more..."
Summarization of Remote Viewing Black Operations Group, Michael Herrera, Outcomes - Eleana, The star traveler - Awakening cosmic reality show
Join us in this special 300th episode of Aspire to Lead as award-winning author, Rick Wormeli, shares about the evolving educational landscape as the post-pandemic practices have shifted. Rick shares his insights on the major challenges schools are currently facing and how he is actively supporting educators and administrators in overcoming these hurdles. We delve into the exciting potential of AI integration in schools, discussing practical strategies for incorporating AI to enhance learning experiences. Additionally, Rick provides valuable guidance on navigating tough discussions and fostering civil discourse within educational settings. Don't miss this opportunity to gain fresh perspectives from one of the most influential voices in education today! About Rick Wormeli: One of the first Nationally Board Certified teachers in America, Rick brings innovation, energy, validity and high standards to both his presentations and his instructional practice, which include 39 years teaching math, science, English, physical education, health, and history, as well as coaching teachers and principals. Rick's work has been reported in numerous media, including ABC's Good Morning America, Hardball with Chris Matthews, National Geographic and Good Housekeeping magazines, What Matters Most: Teaching for the 21st Century, and the Washington Post. He is a columnist for AMLE Magazine and a frequent contributor to ASCD's Education Leadership magazine. He is the author of the award-winning book Meet Me in the Middle as well as the best-selling books Day One and Beyond, Fair Isn't Always Equal: Assessment and Grading in the Differentiated Classroom (Second Edition), Differentiation: From Planning to Practice and Metaphors & Analogies: Power Tools for Teaching any Subject, all five from Stenhouse Publishers, as well as Summarization in any Subject: 60 Innovative and Tech-Infused Strategies for Deeper Student Learning (releasing in fall 2018) published by ASCD. His book, The Collected Writings (So Far) of Rick Wormeli: Crazy Good Stuff I Learned about Teaching Along the Way, is a collection of his published articles, guest blogs and more through 2013. His classroom practice is a showcase for ASCD's best-selling series, At Work in the Differentiated Classroom. Follow Rick Wormeli: Twitter: https://twitter.com/rickwormeli2 Website:
Summarization of Remote Viewing Black Operations Group, Michael Herrera, Outcomes - Eleana, The star traveller - Awakening cosmic reality show
In this episode of the Eye on AI podcast, we dive into the world of AI forecasting with Danny Halawi, a PhD student at UC Berkeley. Danny shares his groundbreaking research on using large language models (LLMs) to predict future events with accuracy, rivaling human forecasters and prediction markets. Danny recounts his journey from studying computer security and fraud detection to exploring the potential of AI in forecasting geopolitical events and beyond. He introduces us to the sophisticated architecture of his AI system, which leverages real-time data from prediction markets and advanced machine learning techniques to generate reliable forecasts. We explore the complexities of judgmental forecasting versus time series forecasting and how AI can enhance decision-making in various fields. Danny discusses the challenges of training AI models for high-stakes predictions, the role of super forecasters, and the fascinating dynamics of prediction markets. He also sheds light on the ethical considerations and future possibilities of integrating AI into our decision-making processes. Join us as we delve into the future of AI forecasting, the potential of superhuman predictions, and the exciting developments that could reshape our understanding of the future. Don't forget to like, subscribe, and hit the notification bell for more expert insights into the latest AI innovations. This episode is sponsored by Oracle. AI is revolutionizing industries, but needs power without breaking the bank. Enter Oracle Cloud Infrastructure (OCI): the one-stop platform for all your AI needs, with 4-8x the bandwidth of other clouds. Train AI models faster and at half the cost. Be ahead like Uber and Cohere. If you want to do more and spend less like Uber, 8x8, and Databricks Mosaic - take a free test drive of OCI at https://oracle.com/eyeonai Stay Updated: Craig Smith Twitter: https://twitter.com/craigss Eye on A.I. Twitter: https://twitter.com/EyeOn_AI (00:00) Preview and Introduction (01:28) The Importance of AI (02:50) Danny's Background and Interest in AI (04:01) Automated AI Forecasting and Safety Implications (07:34) Judgmental Forecasting Explained (11:01) Accuracy and Challenges in Prediction Markets (16:01) Aggregating Predictions for Better Accuracy (19:25) Data Collection and Model Accuracy (23:18) Improving Model Accuracy Over Time (25:31) Data Sources and Model Training (29:20) Summarizing Information for Predictions (34:08) Potential of Reinforcement Learning in Forecasting (37:50) Automating Information Collection and Summarization (39:01) Training the Model for Accurate Predictions (45:04) Challenges with Uncertain Predictions (50:14) Potential Applications and Future Directions (52:26) The Future of AI Forecasting and Its Impact
Listen Ad Free https://www.solgoodmedia.com - Listen to hundreds of audiobooks, thousands of short stories, and ambient sounds all ad free!
In this week's episode, hosts Mark Thompson and Steve Little explore Meta AI 3.1's huge large language model upgrade, as well as FamilySearch's innovative, AI-based summarization feature. They then address growing concerns about AI hype. In this week's Tip of the Week, they share their approach for mastering the fine art of summarization, a crucial AI skill for genealogical research. The show rounds off with rapid-fire discussions of Google's privacy policy update, Apple's response to accusations made about their training data, and exciting developments in AI-powered education. Whether you're a tech enthusiast or a family history buff, this episode offers invaluable insights into how AI is revolutionizing genealogy and beyond.Please share this episode with a friend!Timestamps:In the News 01:01 Meta AI 3.1: A Huge Upgrade, and it's Free! 13:09 FamilySearch's New AI Summarization Feature 20:16 Addressing AI Hype Concerns Tip of the Week 24:59 AI Building Blocks: Summarization AI RapidFire 31:25 Google's Privacy Policy Update 36:57 Apple's Response to Training Data Accusations 40:02 Apple vs. Google: Platform Competition Heats Up 44:59 AI in Education: New Developments and PartnershipsResource LinksMeta AI: https://meta.aiFamilySearch: https://www.familysearch.org/en/labs/OpenAI (ChatGPT): https://openai.com/chatgptAnthropic (Claude): https://www.anthropic.comGoogle (Gemini): https://gemini.google.com/appMicrosoft: https://www.microsoft.com/en-us/aiFacebook: https://www.facebook.comApple AI: https://www.apple.com/aiYouTube: https://www.youtube.comKhan Academy: https://www.khanacademy.orgGoogle DeepMind: https://www.deepmind.comAndrej Karpathy's Eureka Labs: https://eurekalabs.ai/Tags: Artificial Intelligence, Family History, Genealogy, Large Language Models, Meta AI, Facebook AI, Family Search, AI Summarization, OCR, Land Records, AI Model Comparison, Open Source AI, AI Adoption, AI Investment, AI Winter, AI Ethics, Data Privacy, Training Data, Google Privacy Policy, YouTube Closed Captions, Apple AI, AI Research, Platform Competition, AI Ecosystems, AI in Education, Khan Academy, Microsoft AI, Andrej Karpathy, AI Tutoring, AI Learning
Happy Apple AI week everyone (well, those of us who celebrate, some don't) as this week we finally got told what Apple is planning to do with this whole generative AI wave and presented Apple Intelligence (which is AI, get it? they are trying to rebrand AI!)This weeks pod and newsletter main focus will be Apple Intelligence of course, as it was for most people compared to how the market reacted ($APPL grew over $360B in a few days after this announcement) and how many people watched each live stream (10M at the time of this writing watched the WWDC keynote on youtube, compared to 4.5 for the OpenAI GPT-4o, 1.8 M for Google IO) On the pod we also geeked out on new eval frameworks and benchmarks including a chat with the authors of MixEvals which I wrote about last week and a new benchmark called Live Bench from Abacus and Yan LecunPlus a new video model from Luma and finally SD3, let's go!
The Transcription and Summarization Episode: LLMs, Modems, Magic, Technology, Infinite Toys, Change, Promises, Reality, Tascam, Amiga, Manuals, Summarization, Weird But Tireless, Always a Revolution. Some quick thoughts on the world of LLMs as they start entering my life (and many others) from the point of view of a half century of technology.
It's been two months of running Podscan at full speed.Have I spent 6 figures of money yet? Well, you'll see in this week's update :)This episode is sponsored by Acquire.comThe blog post: https://thebootstrappedfounder.com/podscan-2-months-and-1k-mrr-in/The podcast episode: https://tbf.fm/episodes/317-podscan-2-months-and-1k-mrr-inCheck out Podscan to get alerts when you're mentioned on podcasts: https://podscan.fmSend me a voicemail on Podline: https://podline.fm/arvidYou'll find my weekly article on my blog: https://thebootstrappedfounder.comPodcast: https://thebootstrappedfounder.com/podcastNewsletter: https://thebootstrappedfounder.com/newsletterMy book Zero to Sold: https://zerotosold.com/My book The Embedded Entrepreneur: https://embeddedentrepreneur.com/My course Find Your Following: https://findyourfollowing.comHere are a few tools I use. Using my affiliate links will support my work at no additional cost to you.- Notion (which I use to organize, write, coordinate, and archive my podcast + newsletter): https://affiliate.notion.so/465mv1536drx- Riverside.fm (that's what I recorded this episode with): https://riverside.fm/?via=arvid- TweetHunter (for speedy scheduling and writing Tweets): http://tweethunter.io/?via=arvid- HypeFury (for massive Twitter analytics and scheduling): https://hypefury.com/?via=arvid60- AudioPen (for taking voice notes and getting amazing summaries): https://audiopen.ai/?aff=PXErZ- Descript (for word-based video editing, subtitles, and clips): https://www.descript.com/?lmref=3cf39Q- ConvertKit (for email lists, newsletters, even finding sponsors): https://convertkit.com?lmref=bN9CZw
Akshay Chaudhari is an Assistant Professor in the Integrative Biomedical Imaging Informatics at the Department of Radiology in Stanford University, USA. He leads the Machine Intelligence in Medical Imaging research group and has a primary research interest at the intersection of artificial intelligence and medical imaging. He also serves as the Associate Director of Research and Education at the Stanford AIMI Center. Adapted large language models can outperform medical experts in clinical text summarization
https://www.solgoodmedia.com - Check out our Streaming Service for our full collection; hundreds of audiobooks, thousands of short stories, sounds for sleep/relaxation, and original podcasts - all ad-free!!
Welcome to an eye-opening episode that could change how you face life's big moments. Today, we're exploring the idea that when you hit a tough spot, you actually only have four choices. Sounds simple, right? But it's a game-changer. Imagine feeling stuck, like you're at a crossroads with no clear direction. It happens to all of us. We overthink, get overwhelmed, and just feel more and more stuck. But what if you could see your options clearly and make a choice that really fits? We dive into solving the problem, changing how you see the problem, accepting what's happening, or, yes, even choosing to stay stuck for a bit. These options can lighten the load of decision-making, giving you a clear path forward. It's not just about the tough times; it's about knowing you have the power to choose your next step. So, ready to see what those four choices are and how they can help you? Let's get into it! Download the worksheet: THE FOUR CHOICES CHEAT SHEET: NAVIGATING LIFE'S CHALLENGES Key Topics: - The concept of having only four choices in problematic situations - Strategies for effective decision-making and problem-solving - The importance of changing perception and acceptance - The role of self-compassion in choosing to stay miserable - Practical tools and frameworks for applying these concepts in real life List of Key Moments: - [00:01:25] Introduction to the four choices concept - [00:03:24] Discussion on decision paralysis and overcoming challenges - [00:04:18] Deep dive into solving the problem - [00:07:09] Changing our perception of the problem - [00:09:06] The difficult choice of acceptance - [00:11:09] Exploring the choice to stay miserable - [00:13:57] Summarization and resources for listeners Download the worksheet: THE FOUR CHOICES CHEAT SHEET: NAVIGATING LIFE'S CHALLENGES Additional TAM+ episodes that support this episode. Episode 6 : Unstuck Your Thoughts: 7 Cognitive Distortions Sabotaging Your Recovery Episode 9: Embrace the Now: How Radically Accepting Reality Can Transform Your Life Supporting Resources: If you live in California and are looking for counseling or therapy please check out Novus Mindful Life Counseling and Recovery Center NovusMindfulLife.com We want to hear from you. Leave us a message or ask us a question: https://www.speakpipe.com/addictedmind Disclaimer Learn more about your ad choices. Visit megaphone.fm/adchoices
Listen in as Tom Nettles joins David Schrock and Stephen Wellum to discuss his longford essay "The Good Confession: Why Southern Baptists Would Do Well to Embrace Their Confession." Timestamps Intro – 00:50 Keeping Up with Dr. Nettles – 3:00 Being Crystal Clear in Our Confessions - 05:11 Connecting Individual & Corporate Confessions - 09:07 Teaching Systematic Theology Along With Confessions - 16:22 Confessions and Theological Triage - 19:59 B.H. Carroll - 30:38 A History of Baptists Moving Away from Confessions and Associationalism - 32:53 Dr. Wellum's Summarization of that History - 41:45 Being Open Handed With Our Confession Does Not Bode Well - 46:55 Dr. Nettles' Current Efforts with Malcom Yarnell & Steven McKinion - 55:42 Defining Cooperation - 58:25 Final Thoughts from Dr. Wellum - 1:00:26 Outro - 1:01:56 Resources to Click “The Good Confession: Why Southern Baptists Would Do Well to Embrace Their Confession” – Tom J. Nettles “On Baptist Creedalism” – Malcom B. Yarnell III & Steven A. McKinion “Creeds, Confessions, and Carroll: An Essay In Defense of Baptist “Creedalism” – Jordan Steffaniak Theme: Creeds, Confessions, and Cooperation Christoverall.com/give Books to Read Remember Jesus Christ – Tom J. Nettles An Interpretation of the English Bible Vol. XV: Colossians, Ephesians, Hebrews – B.H. Carroll
https://www.solgoodmedia.com - Check out our Streaming Service for our full collection; hundreds of audiobooks, thousands of short stories, sounds for sleep/relaxation, and original podcasts - all ad-free!!
Yup, that about sums it up. The hour begins with ABC's Steven Portnoy to talk about Nikki Haley dropping out of the Presidential race, of course we talk about the eclipse that we're trying to go- and we're getting a Dog! Vince is not totally on board...yet.
How can you provide white-glove customer service if you don't even know what it looks like? That —and a few very exciting development with my recent SaaS project(s?!)— will be what I want to share with you today.This episode is sponsored by Acquire.comThe blog post: https://thebootstrappedfounder.com/white-glove-onboarding/The podcast episode: https://tbf.fm/episodes/287-white-glove-onboardingYou'll find my weekly article on my blog: https://thebootstrappedfounder.comPodcast: https://thebootstrappedfounder.com/podcastNewsletter: https://thebootstrappedfounder.com/newsletterMy book Zero to Sold: https://zerotosold.com/My book The Embedded Entrepreneur: https://embeddedentrepreneur.com/My course Find Your Following: https://findyourfollowing.comHere are a few tools I use. Using my affiliate links will support my work at no additional cost to you.- Notion (which I use to organize, write, coordinate, and archive my podcast + newsletter): https://affiliate.notion.so/465mv1536drx- Riverside.fm (that's what I recorded this episode with): https://riverside.fm/?via=arvid- TweetHunter (for speedy scheduling and writing Tweets): http://tweethunter.io/?via=arvid- HypeFury (for massive Twitter analytics and scheduling): https://hypefury.com/?via=arvid60- AudioPen (for taking voice notes and getting amazing summaries): https://audiopen.ai/?aff=PXErZ- Descript (for word-based video editing, subtitles, and clips): https://www.descript.com/?lmref=3cf39Q- ConvertKit (for email lists, newsletters, even finding sponsors): https://convertkit.com?lmref=bN9CZw
“Biblical criticism is the use of critical analysis to understand and explain the Bible. During the eighteenth century, when it began as historical-biblical criticism, it was based on two distinguishing characteristics: (1) the scientific concern to avoid dogma and bias by applying a neutral, non-sectarian, reason-based judgment to the study of the Bible, and (2) the belief that the reconstruction of the historical events behind the texts, as well as the history of how the texts themselves developed, would lead to a correct understanding of the Bible. This sets it apart from earlier, pre-critical methods; from the anti-critical methods of those who oppose criticism-based study; from the post-critical orientation of later scholarship; and from the multiple distinct schools of criticism into which it evolved in the late twentieth and early twenty-first centuries. The emergence of biblical criticism is most often attributed by scholars to the German Enlightenment (c. 1650 – c. 1800), but some trace its roots back further, to the Reformation. Its principle scholarly influences were rationalist and Protestant in orientation; German pietism played a role in its development, as did British deism. Against the backdrop of Enlightenment-era skepticism of biblical and church authority, scholars began to study the life of Jesus through a historical lens, breaking with the traditional theological focus on the nature and interpretation of his divinity. This historical turn marked the beginning of the quest for the historical Jesus, which would remain an area of scholarly interest for over 200 years. Historical-biblical criticism includes a wide range of approaches and questions within four major methodologies: textual, source, form, and literary criticism. Textual criticism examines biblical manuscripts and their content to identify what the original text probably said. Source criticism searches the text for evidence of their original sources. Form criticism identifies short units of text seeking the setting of their origination. Redaction criticism later developed as a derivative of both source and form criticism. Each of these methods was primarily historical and focused on what went on before the texts were in their present form. Literary criticism, which emerged in the twentieth century, differed from these earlier methods. It focused on the literary structure of the texts as they currently exist, determining, where possible, the author's purpose, and discerning the reader's response to the text through methods such as rhetorical criticism, canonical criticism, and narrative criticism. All together, these various methods of biblical criticism permanently changed how people understood and saw the Bible. In the late twentieth and early twenty-first century, biblical criticism was influenced by a wide range of additional academic disciplines and theoretical perspectives which led to its transformation. Having long been dominated by white male Protestant academics, the twentieth century saw others such as non-white scholars, women, and those from the Jewish and Catholic traditions become prominent voices in biblical criticism. Globalization brought a broader spectrum of worldviews into the field, and other academic disciplines as diverse as Near Eastern studies, psychology, cultural anthropology, and sociology formed new methods of biblical criticism such as social scientific criticism and psychological biblical criticism. Meanwhile, post-modernism and post-critical interpretation began questioning whether biblical criticism had a role and function at all. With these new methods came new goals, as biblical criticism moved from the historical to the literary, and its basic premise changed from neutral judgment to a recognition of the various biases the reader brings to the study of the texts.” --- Send in a voice message: https://podcasters.spotify.com/pod/show/antonio-myers4/message Support this podcast: https://podcasters.spotify.com/pod/show/antonio-myers4/support
Ryan shares the key things he learnt from the recent event he attended. He walks through the framework he uses to leverage events and also talks about how he, and you too, can use chatGPT vision when attending large-scale events like these. Join 2,500+ readers getting weekly practical guidance to scale themselves and their companies using Artificial Intelligence and Revenue Cheat Codes. Explore becoming Superhuman here: https://superhumanrevenue.beehiiv.com/ KEY TAKEAWAYS Always have a focus on new business when attending events Identify 5-7 people you want to meet in advance before going to an event There are large companies spreading misinformation about AI, this could be because they aren't up to date or because they are threatened by large language models Download chatGPT on your phone to unlock all capabilities including using vision Categorize companies by their solution, customer base and revenue and look at the results to see who may be your best partners. ChatGPT can be utilised to take frameworks, information from events and be told to create guides from them, making it bespoke to what you want to use it for. BEST MOMENTS "I always try and learn something insightful and interesting that I can immediately apply when I get back from the event” “I've been a nut about AI, really into it, deep into it, trying to find all the use cases” “Summarization of notes with action items, you can even ask it (chatGPT) to summarize” Ryan Staley Founder and CEO Whale Boss ryan@whalesellingsystem.com www.ryanstaley.io Saas, Saas growth, Scale, Business Growth, B2b Saas, Saas Sales, Enterprise Saas, Business growth strategy, founder, ceo: https://www.whalesellingsystem.com/closingsecretsThis show was brought to you by Progressive Media
“Those that are equipped with and know how to ably use AI are going to be outdoing those lawyers and law firms that do not.”The FutureWork podcast episode 6 features Dr. Lance Eliot, a regular Forbes contributor and AI Fellow at Stanford University and Dazza Greenwood, a renowned Fortune 100 legal tech advisor and the Executive Director of Law.MIT.edu. Both guests have industry-leading research and publications, and they routinely counsel attorneys, CEOs, educators, and business leaders. Lance and Dazza are also on the cutting edge of GenAI trends–developing roadmaps for legal teams, engineers and executives to transform the future.Viewing generative AI as an effective tool for lawyers and not something to fear, Lance and Dazza provide listeners with suggestions for the most effective uses of legal prompt engineering and generative AI as a whole. From summarizing discovery material to identifying ambiguities in a legal document, generative AI can be a huge asset to the legal field. However, they caution that the results are only as good as the prompts.Tune in as Natalie, Lance, and Dazza discuss key steps in creating a framework for the responsible use of generative AI in the practice of law, crucial techniques for how to boost your prompt engineering skills as a lawyer, high value use cases for generative AI in the practice of law, and why lawyers are in a great starting position to use generative AI. Key HighlightsAn effective framework for harnessing the power of generative AI responsibly in the practice of law involves formulating well-constructed prompts, reviewing and critiquing the outputs, iteration, and human oversight.AI is coming into law practices, whether lawyers or law firms want it or not.Prompt engineering is the idea that there are effective ways to craft prompts to carry on conversations with generative AI that are beneficial to the person who is interacting with the generative AI.Summarization is an example of a high value use of generative AI on legal tasks. There are various prompt engineering techniques that lawyers can use to effectively interact with generative AI.
CounselingExam.comAre you ready to transform your therapy sessions? We're inviting you on a journey to discover the subtle yet powerful tool of summarization in our latest episode. Join us, Dr. Linton Hutchinson and Stacy Frost, as we demystify this technique, shedding light on its role in structuring conversations and highlighting key topics for further exploration. We dive deep into the art of summarization, revealing how it can iron out misunderstandings, review client progress, and set treatment goals.As we banter and share personal anecdotes, we unveil when summarization can be most beneficial. From the beginning and end of a session to those overwhelming moments when a client shares a wealth of information - summarization lends a helping hand. By echoing clients' thoughts and feelings, we empower them, fostering a stronger therapeutic rapport. In our lively discussions, we remind you that practice is key to mastering this skill. So, get ready to enhance your therapy toolkit with us. Stay tuned for more insights on therapy skills in our upcoming episodes.If you need to study for your NCMHCE narrative exam, try the free samplers at: CounselingExam.comThis podcast is not associated with the National Board of Certified Counselors (NBCC) or any state or governmental agency responsible for licensure.
Are you ready to transform your therapy sessions? We're inviting you on a journey to discover the subtle yet powerful tool of summarization in our latest episode. Join us, Dr. Linton Hutchinson and Stacy Frost, as we demystify this technique, shedding light on its role in structuring conversations and highlighting key topics for further exploration. We dive deep into the art of summarization, revealing how it can iron out misunderstandings, review client progress, and set treatment goals.As we banter and share personal anecdotes, we unveil when summarization can be most beneficial. From the beginning and end of a session to those overwhelming moments when a client shares a wealth of information - summarization lends a helping hand. By echoing clients' thoughts and feelings, we empower them, fostering a stronger therapeutic rapport. In our lively discussions, we remind you that practice is key to mastering this skill. So, get ready to enhance your therapy toolkit with us. Stay tuned for more insights on therapy skills in our upcoming episodes.If preparing for your National Counseling Exam visit NationalCounselingExam and try our samplers completely free of charge! It's a fantastic way to identify any areas you might want to review. and brush up on.This podcast is not associated with the National Board of Certified Counselors (NBCC) or any state or governmental agency responsible for licensure.
If there is any area where today's Messianic movement tends to absolutely excel, it is with integrating a wide selection of the mainline Jewish traditions and customs for observing the Sabbath. Regardless of their background before coming to Messiah faith, religious or secular, today's Messianic Jews tend to remember Shabbat with the common elements of lighting candles, breaking challah, drinking wine, and attending synagogue services with traditional liturgy and Torah readings. Non-Jewish Believers who have been led by the Lord into the Messianic movement, seeking to embrace more of the Hebraic and Jewish Roots of their faith, have also taken a hold of Shabbat, the opportunity for rest it offers to the people of God, and many of the significant traditions that can make the Sabbath a very holy and sanctified time.
In this episode of The SaaS CFO Podcast, I have the pleasure of hosting Max Brentzel, co-founder and CEO at Spoke AI. Max, hailing from Germany and now based in Berlin, shares his journey in the tech scene and how the city's startup ecosystem has evolved over the years. With a background in economics and international expansion, Max brings a unique perspective to the table. Tune in as he discusses Spoke AI's privacy-first AI products that help users streamline and prioritize their communication across various tools, ultimately saving time and increasing efficiency. Discover how Spoke AI's standalone app within Slack and web app cater to the needs of product managers, summarizing and organizing their busy channels and threads. Max also delves into the importance of user control and the future plans for Spoke AI's premium tier. Don't miss this insightful episode packed with valuable insights for SaaS founders and tech enthusiasts alike. Show Notes [00:01:54] AI products prioritize and summarize communication. [00:03:53] User controls communication data processing for privacy. [00:08:22] Limited company onboarding to ensure reliable Summarization. [00:10:13] Early core team, AI expertise = success. [00:15:27] Launching new product, enclosed beta in May. Exciting features coming to Slack app. Links SaaS Fundraising Story: https://www.thesaasnews.com/news/spoke-ai-raises-2-million-in-pre-seed-round Max Brenssell's LinkedIn: https://www.linkedin.com/in/max-brenssell/ Spoke.ai's LinkedIn: https://www.linkedin.com/company/spoke-ai/ Spoke.ai's Website: https://www.spoke.ai/ Ben's LinkedIn: https://www.linkedin.com/in/benrmurray/
Highlights from this week's conversation include:Amr's extensive background in data (3:23)The evolution of neural networks (9:21)The role of supervised learning in AI (11:17)Explaining Vectara (13:07)Papers that laid the foundation for AI (15:02)Contextualized translation and personalization (20:07)Ease of use and answer-based search (25:01)AI and potential liabilities (35:54)Minimizing difficulties in large language models (36:43)The process of extracting documents in multidimensional space (44:47)Summarization process (46:33)The danger of humans misusing technology (54:59)Final thoughts and takeaways (57:12)The Data Stack Show is a weekly podcast powered by RudderStack, the CDP for developers. Each week we'll talk to data engineers, analysts, and data scientists about their experience around building and maintaining data infrastructure, delivering data and data products, and driving better outcomes across their businesses with data.RudderStack helps businesses make the most out of their customer data while ensuring data privacy and security. To learn more about RudderStack visit rudderstack.com.
“Christianity (/ˌkrɪstɪˈænɪti/) is an Abrahamic monotheistic religion based on the life and teachings of Jesus of Nazareth. It is the world's largest and most widespread religion with roughly 2.4 billion followers representing one-third of the global population.[1][2] Its adherents, known as Christians, are estimated to make up a majority of the population in 157 countries and territories,[3] and believe that Jesus is the Son of God, whose coming as the Messiah was prophesied in the Hebrew Bible (called the Old Testament in Christianity) and chronicled in the New Testament.[4] Christianity remains culturally diverse in its Western and Eastern branches, and doctrinally diverse concerning justification and the nature of salvation, ecclesiology, ordination, and Christology. The creeds of various Christian denominations generally hold in common Jesus as the Son of God—the Logos incarnated—who ministered, suffered, and died on a cross, but rose from the dead for the salvation of humankind; and referred to as the gospel, meaning the "good news". The four canonical gospels of Matthew, Mark, Luke and John describe Jesus's life and teachings, with the Old Testament as the gospels' respected background.” --- Send in a voice message: https://podcasters.spotify.com/pod/show/antonio-myers4/message Support this podcast: https://podcasters.spotify.com/pod/show/antonio-myers4/support
Microsoft's AI research team accidentally exposed 38 terabytes of private data while publishing open-source training data on GitHub, posing a significant security risk. The UK's new AI principles focus on accountability and transparency, seeking views from leading AI developers and governments to ensure the development and use of foundation models evolves in a way that promotes competition and protects consumers. Two new papers explore ways to improve the efficiency and quality of large language models, including a new inference scheme called self-speculative decoding and the ability to prune pretraining data while still retaining performance. A third paper introduces a new type of prompt called the "Chain of Density" or CoD, which generates increasingly dense summaries without increasing their length, resulting in more abstractive and human-preferred summaries. Contact: sergi@earkind.com Timestamps: 00:34 Introduction 01:45 38TB of data accidentally exposed by Microsoft AI researchers 03:05 UK focuses on transparency and access with new AI principles 04:40 Jason Wei Tweet on the role of task-specific LLMs 06:11 Fake sponsor 07:43 Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding 09:20 When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale 10:55 From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting 12:37 Outro
Long time classroom teacher in both elementary and secondary levels, now author and teacher/principal trainer, author of Fair Isn't Always Equal, 2nd Edition, Summarization in any Subject, 2nd Edition, columnist, Differentiation: From Planning to Practice, among other titles, 'proudly a new Grandpa, and "chocolate pecan pie" fan club memberwww.twitter.com/rickwormeli2If you know someone who you would like to recommend as a guest for our show, complete this survey.
“Ethical Porn Sources Finally, I'm going to leave you with a few suggestions of trustworthy ethical porn websites for your enjoyment: Bellesa.co (free) - Described as “made by women, for anyone of any gender who wants to watch something real”, Bellesa is a great go-to feminist website for pornography, erotica, sex toys, and more. Royal Fetish Films ($) - Jet Setting Jasmine and her partner King Noire saw a need for better representation of Black and brown sexuality in the adult entertainment industry, so they created a safe space for not only performers but also viewers to feel more comfortable experimenting and exploring their sexualities while challenging harmful narratives in mainstream pornography. MVTube (free) - MVTube, a subsection of ManyVids, offers free content which creators have agreed to be featured. Performers are paid per views and the platform allows them to gain exposure and find potential long-term customers. XConfessions ($) - The creator, Erika Lust, is a feminist adult filmmaker. The concept behind XConfessions is to turn viewer submissions into erotic short films, so it makes for genuine and always exciting storylines. Make Love Not Porn ($) - Their focus is authentic, real sex - challenging traditional tropes and scripts in pornography, Make Love Not Porn wants to provide “#RealWorldSex in all its glorious, silly, beautiful, messy, reassuring humanness”. OnlyFans ($) - Because content is self-produced, OnlyFans is a great source for mature content consumption on the creators' terms. Performers set their own prices and only go as far as they're comfortable going.” After a shoot I have the right to be paid my agreed-upon fees according to the company's usual method of payment. I have the right not to have to make repeated demands for payment, nor will I have payments unreasonably withheld from me." (https://apacommittee.org/performer-bill-of-rights/#:~:text=The%20Performer%20Bill%20of%20Rights%20details%20what%20performers,are%20conducive%20to%20mental%2C%20emotional%2C%20and%20physical%20health.) --- Send in a voice message: https://podcasters.spotify.com/pod/show/antonio-myers4/message Support this podcast: https://podcasters.spotify.com/pod/show/antonio-myers4/support
“Human rights are moral principles or norms[1] for certain standards of human behavior and are regularly protected in municipal and international law.[2][citation not found] They are commonly understood as inalienable,[3] fundamental rights "to which a person is inherently entitled simply because she or he is a human being"[4] and which are "inherent in all human beings",[5] regardless of their age, ethnic origin, location, language, religion, ethnicity, or any other status.[3] They are applicable everywhere and at every time in the sense of being universal,[1] and they are egalitarian in the sense of being the same for everyone.[3] They are regarded as requiring empathy and the rule of law[6] and imposing an obligation on persons to respect the human rights of others,[1][3] and it is generally considered that they should not be taken away except as a result of due process based on specific circumstances.[3]” --- Send in a voice message: https://podcasters.spotify.com/pod/show/antonio-myers4/message Support this podcast: https://podcasters.spotify.com/pod/show/antonio-myers4/support
Apply all of these boundaries to sex: “HEALTHY BOUNDARIES You can say no or yes, and you are ok when others say no to you. You have a strong sense of identity. You respect yourself. You expect reciprocity in a relationship-you sharing responsibility and power. You know when the problem is yours and when it belongs to someone else. You share personal information gradually in a mutually shared/trusting relationship. You don't tolerate abuse or disrespect. You know your own wants, needs, and feelings. You communicate them clearly in your relationships. You are committed to and responsible for exploring and nurturing your full potential. You are responsible for your own happiness and fulfillment. You allow others to be responsible for their own happiness and fulfillment. You value your opinions and feelings as much as others. You know your limits. You allow others to define their limits. You are able to ask for help when you need it. You don't compromise your values or integrity to avoid rejection.” Compassionate sexual indulgence and compassionate sexual refrainment are both essential parts of heathy eroticism and healthy sensuality. Women do need oral stimulation for ejaculatory pleasure because penetration is not good enough. Don't sleep with anyone who cruelly clowns your oral performance, anal performance, vaginal performance, penetrative sex performance, foreplay performance, and non-penetrative sex performance. --- Send in a voice message: https://podcasters.spotify.com/pod/show/antonio-myers4/message Support this podcast: https://podcasters.spotify.com/pod/show/antonio-myers4/support
“Elite group – led by a Pakhan ("Boss") who is involved in management, organization, and ideology. This is the highest group that controls both the support group and the security group. Security group – led by one of Pakhan's spies. His job is to make sure the organization keeps running, keeps the peace between the organizations and other criminal groups, and paying off the right people. This group works with the Elite group and is equal in power with the Support groups. Is in charge of security and in intelligence. Support group – led by one of Pakhan's spies. His job is to watch over the working unit, and collect money while supervising their criminal activities. This group works with the Elite group and is equal in power with the Security group. They plan a specific crime for a specialized group or choose who carries out the operation. Working Unit – There are four Brigadiers running criminal activity in the working unit, each controlling a Brigade. This is the lowest group working with only the Support group. The group is involved in burglars, thieves, prostitution, extortion, street gangs, and other crimes.” I have seen crooked lawyers, and crooked attorneys endure lengthy prison sentences. Sometimes, my child self sees myself as a human rights Christian. Other times, my child self sees myself as a religious Christian. --- Send in a voice message: https://podcasters.spotify.com/pod/show/antonio-myers4/message Support this podcast: https://podcasters.spotify.com/pod/show/antonio-myers4/support
Summarization is one of the common use cases of different AI models. Multiple tools have come up with a summarization of articles, PDFs, videos, and transcripts.
https://www.solgood.org - Check out our Streaming Service for our full collection of audiobooks, podcasts, short stories, & 10 hour sounds for sleep and relaxation at our website
AI Today Podcast: Artificial Intelligence Insights, Experts, and Opinion
In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define Content Summarization and Analysis and Sentiment Analysis. We explain at a high level what these terms are and how they relate to AI. Show Notes: FREE Intro to CPMAI mini course CPMAI Training and Certification AI Glossary AI Glossary Series – Natural Language Processing (NLP) AI Glossary Series – Conversational Systems, Chatbots, Voice Assistants, Machine Translation AI Today Podcast #104: Patterns of AI – Conversation / Human Interaction Continue reading AI Today Podcast: AI Glossary Series: Content Summarization and Analysis, Sentiment Analysis at Cognilytica.
This week's episode discusses the Gateway Process outlined in recently declassified (2003) CIA Documents regarding Project Stargate. The Gateway Process attempts to explain supernatural phenomena such as astral projection, out-of-body experiences, higher levels of consciousness, reality shifting, and many other strange supernatural things achieved through meditation through the lens of science as we know it today. This leads us into a discussion about the 3 most impactful life-changing meditation experiences that I have had in my life and about meditation in general and the positive impacts it has on your body and mind. Subscribe and leave a 5-star review! ----more---- Our website https://redpillrevolution.co/ Protect your family and support the Red Pill Revolution Podcast with Affordable Life Insurance. This is attached to my license and not a third-party ad! Go to https://agents.ethoslife.com/invite/3504a now! Currently available in AZ, MI, MO, LA, NC, OH, IN, TN, WV Email austin@redpillrevolution.co if you would like to sign up in a different state Leave a donation, sign up for our weekly podcast companion newsletter, and follow along with all things Red Pill Revolution by going to our website: https://redpillrevolution.co ----more---- Full Transcription Welcome to the Revolution. Hello and welcome to Red Pill Revolution. My name is Austin Adams, and thank you very much for listening today. This is episode number 46 of the Red Pill Revolution podcast, and we are going to have a very intriguing conversation. This one we're gonna be touching on. It was something we've kind of touched on before, but we didn't dive into this specific topic, this deep. So what we're gonna be discussing is the CIA documents surrounding the gateway process. Okay, so we'll touch on that. We'll talk a little bit about some of my experiences with meditation, things like kini yoga, some of the interesting stories that I have surrounding that. Then we'll dive a little bit further into some of those other types of meditation, which I find to be really interesting, um, from that kind of. Uh, Western, or I'm sorry, Eastern philosophy and, and those types of things. So the gate, it all starts with the gateway process, though , if you've never heard of the gateway process, it's a unbelievable, unbelievably interesting document that came from the CIA that was released in 2003 surrounding. Some of the most interesting topics that you've ever heard of in your life. Everything from spirit channeling divination to extra sensory perception, to, uh, astrol projection, to, uh, you know, um, basically all of these, you know, out body experiences, states of altered consciousness. And this was all done under the US Army. In the cia. Okay? Um, this US Army's actually the one that released the document. So, um, we will go ahead and jump into it. But before that, , before that, I need you to do one thing for me, and that is just go ahead and hit that little button on your phone. It takes two seconds on your part. It means the world to me. And you already know which button I'm talking about. It starts with a sub and ends with a scribe. All right? That's what I got for you. If you are on Apple Podcasts or Spotify, go ahead and hit that five star review button. If you do not already, follow me on all of these social media channels at Red Pill Revolt, go find me, follow me. You know the deal. All right? And if you haven't hit the subscribe button, just do it. You'll feel better about it this whole time. All right? Gives you a little bit of good karma. All right, speaking of Karma , we have some very interesting conversations today. Um, so we will go ahead and jump into it right now. All right. I don't know about you, but that introduction just gets me a hype for some reason. , if you can't see it, um, even if you're watching this on YouTube, but I'm in the background mouthing it. Getting excited over here. Um, but let's dive into it. The CIA documents about the Gate Way process. All right. Now this gets so deep, it might be hard to follow, but I found some really good engaging articles that take, uh, this wealth of information that's a 26 page document. And 26 pages doesn't seem that deep. Even in each individual. There's like two to three paragraphs on each of the individual things that they're discussing here. Um, but I found a really good way to break it down for you guys, and here it is. In 1945, the United States launched a scientific intelligence initiative titled Operation Stargate. The objective was to recover intelligence on scientific and military, uh, projects conducted under the third, right? What they found was something much stranger. A cash of documents related to, um, which was a scientific academy, and, and think, take indicated a division that was so, basically it was like the Nazi regime had this scientific think take that was dedicated to the study of cult sciences. The extensive research was being conducted on sensory perception, spirit channeling divination in other forms of anomalous phenomenon. The paranormal was being scientifically explored, but from what purpose is unclear. After uncovering these documents, they began to investigate, uh, into altered consciousness and the supernatural, and they continued these investigations for decades. Some of these projects like MK Ultra have been widely reported. Others, not so much. Some have re received little to no exposure since declassification. That one report titled The Analysis and Assessment of the Gateway Process went largely unexamined until recently it was declassified in 2003 by the US Army. In a detail, a scientific technique developed by the Monroe Institute to facilitate astro projection in out body experiences and states of altered Consci. Hmm. Now, if you don't know, we touched on this topic, um, when we talked about the Project Stargate. So there's a whole episode that we did on Project Stargate and Project Stargate was the, uh, CIA's initiative to basically combat and re uh, look into what the Nazi regime did by looking into the astro projections. And so the idea was that they would take people with high levels of psychic energy, right? Or self proclaimed high levels of psychic energy. And if you haven't watched that episode, it's wild, right? We watch videos of them literally putting ping pong balls on people's faces so that they have this like sensory deprivation in order to do these. And there's a movie that's loosely based off of this, which is called The Men Who Stare at Goats. Um, I guess it's a ho movie, so really no reason to watch it . But, but it's interesting that there's a movie nonetheless. So what, what that, uh, Project Stargate was, the whole idea behind that was that they were coming out with a project to basically learn how to spy on other military operations without ever having to leave a single room or do any reconnaissance at all. All of this was going to be done through some type of psychic action, and in this case it was called Astro Projection. And if you don't know what astro projection is, Astro projection is the idea. It's, it's a form of transcendental meditation, which transcendental meditation is something that we'll dive into in a little bit. But it's basically, you know, getting into a deeply meditative. expanding and, and, and taking your consciousness and looking to expand it from outside of your body. And within that you can start to project that to different areas of, of earth and space and time, uh, uh, and timelines, right? It's, it's really wild the things that they did within Project Stargate. There was even one instance during Project Stargate where they had an individual who was projecting their consciousness into a pyramid on, I believe it was like a pyramid on Mars, where they spoke to extraterrestrial entities who were trapped there. And in trying to ask them for help on a different, Like in, in a different time than today, like far, far in the past. It's so crazy. And you can find all these documents, go to cia.gov, um, or, or go to Google and type in CIA reading room and there's all of these documents and just look up Project Stargate. And there's so much shit that you can dive into a project Stargate is so crazy. And this is the document that we're gonna discuss today is a single document of that project. Okay? Now, one way that they went about that project was something that was called Hemi Sync. In Hemi Sync was an initiative that they were trying to basically figure out how to best prime the body to do this astro projection. And, and the, the project Stargate. Or, I'm sorry, the breakdown of the gateway process was an, an, an attempt to explain exactly what was happening, how it was happening, what was happening in the brain, how this was even possible from a, uh, like a worldly perspective. You know, what was going on to make this possible. Okay. Um, so pretty wild stuff. And with that, let's dive a little bit further. It says that some of the projects like MK Ultra have been widely reported on, however, some have received little no exposure since declassification. Right? We talked about that with the US Army coming out with this document in 2003. Um, and it detailed a scientific technique developed by the Monroe Institute to facilitate astro projection out of body experiences in states of altered consciousness. The purpose was to create individuals who could transcend space and time so that they could achieve this through the use of the gateway tapes. Now, the gateway tapes are literally available on Amazon, right? Now it's $190 for the gateway tape. So if you're that interested in this, there's two copies left , I hope after this show there's a couple less. If that looks at zero by the time that this gets released and you guys listen to it, that's pretty awesome. Um, but anyways, you can also find it on YouTube, so don't, maybe don't spend your money . Um, the gateway tapes, I'm pretty sure beginning to end are all on YouTube. And so the Robert Monroe was the one who spearheaded this operation and, and tried to break down what was actually happening during this astro projection and how to actually accomplish this. All right. So Robert Monroe was a radio broadcasting executive in the early 1950s. He formed Ram Enterprises, which was a corporation that produced network radio programs. However, Monroe was interested in exploring how sound frequencies can impact the human mind. He was obsessed with discovering methods of how to, it's called like hypo, um, hypno emia. And it's basically learning how to learn from audio tapes while you're sleeping. Okay? Think of like listening to, you know, uh, pimsler Spanish tapes. Uh, and then eventually after so many weeks of listening to this in your sleep, you wake up and all of a sudden you're fluent in Spanish. That that was kind of his idea. it says that Monroe experimented with frequencies to enhance memory and learning for years. However, in the 1950s, he got more than he bargained for. During one of his experiences in experiments, he experienced paralysis, bodily vibrations and bright lights until he seemingly exited his body floating somewhere near the ceiling. This experience was later publicized in articles and books, and it helped popularize, popularize the term out of body experience or obe. He was frightened, but also intrigued, and he began to pursue this experience, describing it as proof of the spiritual world. As Ram Enterprises grew beyond radio production, they rebranded as Monroe Industry and they developed a research division named the Monroe Institute. There they studied the impact of sound frequencies and patterns on human consciousness. Monroe discovered that the human brain was subject to a frequency following response, which means brainwaves would naturally adapt to mimic the audio frequencies played. However many known brainwave patterns like beta, theta and delta occur at frequencies that are inaudible to the human ear. To circumvent this limitation, Monroe would play different frequencies to the left and the right ears, which would create a beat frequency. A beat frequency is simply the difference between the two played frequencies. For example, if 210 frequencies hurts or hurts, frequency was played in one ear in 220 and the other, it would generate a beat frequency of 10 hertz invoking psychological and mental states that are related to those brave brain wave frequencies. This process would synchronize the amplitude and frequency of brainwaves between both hemispheres. This synchronization is also called Hemi, and it rarely occurs in natural circumstances. Monroe claims that the gateway process could lead to prolonged states of Hemi sync, and he could stimulate states of consciousness by forcing the brain to emulate these frequencies. So, Summarization. He would put headphones on and he would play these certain frequencies. If you've ever done like transcendental meditations or guided meditations, sometimes in order like kini, there's, there's sometimes in the background you'll hear this. Uh, you know, it's like this weird kind of underlying sound and, and, and you can even look up certain, uh, uh, transcendental meditations or guided meditations that have certain frequencies, um, which the CIA has outlined as allowing you to do these out body experiences, Right? So, so what he did is he started the experiments that kind of brought to light and scientifically explained what's happening in these instances. And it goes on to say that by evoking delta brainwaves in one to four hertz range, he could elicit states of meditation or relaxation. Early research at the Monroe Institute suggested that the gateway process had many practical applications including stress relief, pain, anesthetic. Accelerated learning and more. However, it would only later be applied in an attempt to create psychic soldiers under the guidance of the US military military. In 1983, Lieutenant Colonel Wayne in McDonald's submitted a classified report titled, In Analysis and Assessment of the Gateway Process, He was tasked with exploring astro projection and not body experiences and how the gateway process might be used to train soldiers for intelligence gathering purposes. The subject matter can be difficult to understand, but the following is a synopsis of McDonald's report. Aware that this is his investigation was skirting the supernatural McDonald's thought to ground his analysis in scientific study, he connected his reports to the following branches of study, including biomedicine to re, to determine the physical processes and effects that occurred during the gateway processes, including quantum mechanics and attempt to explain the interplay between consciousness in the physical world. Theoretical physics to understand the physical world that would be transcended and Newton's laws of physics to ground his findings and dispel any paranormal connotations. The gateway process was described as a training system designed to bring enhanced strength and focus into am, uh, to the amplitude and frequency of brainwaves output between the left and the right hemisphere, so as to alter consciousness, moving it outside of the physical sphere so as to ultimately escape even the restrictions of time and space. And that draws back to how this was actually applied in Project Stargate, which is wild, which is what we talked about a little bit earlier. And all of this sounds so crazy, but the fact that the CIA dumped. Millions of dollars and manpower into this and, and actually had many, many successful missions, including finding a specific warship in the ocean as a result of one person's, uh, you know, astro projections. Now it goes on to say that, and through these interactions, all energy fields became imprinted and then encoded with inform. Um, it says to understand how human consciousness could escape the physical body. McDonald asserted that the world is a hologram, a theory which is shared by even current day physicists all matter consists of atoms, small nucleic, and are surrounded by large electron energy fields. The energy fields between all matter coexist and interact. And through these interactions, all energy fields become imprinted and encoded with information. Furthermore, complex principles and holographic theory suggests that this imprinting can occur between, and not only is there an interconnectedness between everything we know, but perhaps there is information in our world about dimensions that we have yet to even discover. The holographic theory is further complicated by interaction with human consciousness. We do not passively perceive the world, but through perception, we change it through free will. We can selectively perceive and influence the holographic universe. Similar to popular new age ideas like the Secret in the law of attraction. Now, if you don't know what the secret or the Law of Attraction are, I'm happy to explain. I was given a book by my father, um, great man, and, uh, it was called The Laws of Success. And I was given this book. It was written by Napoleon Hill, and Napoleon Hill is kind of the grandfather of all, uh, you know, motivational speaking today. All, all of the books that you see on, you know, how to, uh, self-improvement basically is a sub chapter of information or stems from a, you know, a certain paragraph even from this book called The Laws of Success and The Laws of Success was Later to Condense, because I have it right here actually. Napoleon Hills Law of Success. All right, here's the book. It is, um, revised and updated by Napoleon Hill, the 21st Century edition, and it is approximately 890 pages. 890 pages. And in this book he described several, several things, including a lot of what this even talks about prior to this actually happening. Right. Um, so. Um, what I see to be interesting about this is, is it talks about the secret. It talks about the law of attraction. It talks about, you know, what, what turned into many of the modern day new age ideas. And if you don't know what the secret is about or what the law of attraction is, it's basically, uh, interplaying the idea. And, and it gets pretty deep if, if you know, how the, the, where our science is going today, which makes it even more interesting. But the principle of the law of attraction is basically that through sheer thought, you can manifest the world, the life, the outcomes that you want in life. Now, I think there's two specific interesting ways to talk about that. The first one being that even if it doesn't have to do with the frequencies of the world, which is, you know, what, uh, is asserted by Napoleon Hill in this book and even asserted through this CIA document. Um, but even if it's not that right, I guess let's, let's talk on that. The idea is that the, the, the world is vibrations, right? And if you understand how science works, and I don't claim to be a scientist, so take everything I'm saying with a grain of salt. But from my understanding, the idea is that everything is movement. Every molecule, every molecule is shaking, right? There's movement happening all around this at all times. The words that you're hearing from me right now are simply vibrations, right? And those vibrations stem from the vibrations that are happening within my own brain, which is causing, you know, this activity that's coming up with thoughts, which is then coming out verbally, which you're hearing through the vibrational frequencies, right? And that includes the light that's, you know, reflecting off of the walls that's giving color. Everything in this universe stems from some type of, uh, you know, movement or frequency as a result. So the idea is that there's, you know, if, if the way that I look at it now, knowing what we know about, you know, where science is going with the idea of multiverses, is that if you align with a certain frequency, right? Even when you're not speaking, even just your thoughts are emitting frequencies into the world and the world picks up on those, whether it's, you know, what you, whether you want to call it God, whether you wanna call it the universe, whatever you want to call it, there is something greater than us that is taking in those vibrational frequencies. And if you put things out enough, the world will start to align with your thoughts, right? And this comes from, you know, whether or not it's, it's this new wave idea of science or whether it's even to me, even if it's not, that, it may even just have to be the trickling down of the conscious into the subconscious, right? If I wake up and tell myself every day, then I'm gonna be a millionaire, right? Let's do the most common one that you'll probably see when people do the secret, right? I'm gonna have all the money in the world. Right. If you just wake up every day and you recite that, and you recite that, and you recite that, and you recite that, right, I'm gonna have a million dollars by this day. I'm gonna have a million dollars by this day. Just specifically by doing that, you are pulling your, you, you are positioning your subconscious in the way that that is what's at the forefront of your mind, even if you're not thinking about it, right? So you start to pick up on cues around you that may get you closer to that goal, right? Because if your brain, if every day that you woke up, you said, I'm hungry, I need to find. , I'm hungry. I need to find food. Right? Your brain's gonna go, Oh, he's hungry. He needs to find food. And so your particular activating system is gonna start to pick up on subtle cues around you, right? That could potentially mean I'm gonna eat, right? So whether it's has to do with, you know, aligning with the proper multiverse, right, or, or universe. Um, and that's an even deeper conversation, but you know, through the manifestation of your own thoughts or whether it just specifically has to do with you saying something enough to where it trickles into your subconscious. I wholeheartedly believe that there is one shape or another in one shape or another. You can frame the universe around you specifically through. thoughts. You know, it's a, a, a really incredible quote is, you know, if you knew the power of your thoughts, you would never have another negative thought in your life, right? If you knew how powerful each individual thought that went through your brain was, you would never think anything that would position you in a way to receive back any negativity. Right? And we're getting a little in the woods with this, but I think it's important to understand this manifestation idea because it comes up later in these documents where it talks about those frequencies. The frequencies that you, you start to align with the, the, the vibrational waves that you're putting out into the universe is what's going to come back to you in one way, shape, or another. Let's go ahead and continue this document. Human beings can manifest certain realities through imagination and willpower. Lastly, McDonald speculates that human consciousness may be able to temporarily escape time and space utilizing the gateway tapes to accelerate brainwave frequencies. These brainwaves may break a physical limitation known as the plank distance. The plank distance is the smallest measurable distance in the physical, the peaks of accelerated brainwaves. And theoretically, the accompanying human consciousness would temporarily enter a sub planky universe. This primor primordial dimension of space predates are known universe, and it is not subject to the limitations of time in space. McDonald theorized that consciousness would blink into the sub planking space and return with knowledge that would otherwise be inaccess. It becomes possible to see how human consciousness brought to a sufficiently altered state could obtain information concerning the past, present, and future. The practice of using the gateway trait tapes is referred to as the gateway process before beginning. Subjects are instructed to visualize a box in place, any extraneous concerns inside of it. This is meant to help improve focus. Then they are instructed to meditate while humming a single tone. After sufficient preparation. The Hemi Sync frequencies are introduced, which is the tapes that have these frequencies, Those, um, you know, whatever that sounds like. It's only through exposure and diligent practice that subjects can reach the furthest possibilities of this practice. McDonald describes the following as possible outcomes of the gateway practice. Improved problem solving, solving by calling on a higher self, which is the expanded consciousness of the subject. Um, patterning and projecting the will into the universal hologram in an attempt to manifest a new reality. Color breathing and energy bar tool techniques are meant to stimulate healing effects on the body through the use of visualization, out of body experiences allow individuals to exit their bodies and explore the physical world and beyond. Okay, now let me talk about one of those specific things that I just talked about, which is the improved problem solving by calling on a higher self. Now, I had an experience. Now I, I'm, I've meditated for a fairly decently long time in my life. I would say probably, I don't know, eight, eight to 10 years. I, I've, and even when I was younger, right, as like, In middle school, you know, I was watching, uh, of, you know, if there was YouTube back then, whatever, wherever I, I watched it , uh, videos about energy and, and, and kind of interested in the Eastern philosophies. And, um, so when I, when I've meditated in the past, I've done several different things, right? When, normally when you meditate, you go through a, a certain steps, right? The normal meditation techniques is, is basically taking something that's considered, you know, to, to take the words of Tim Ferris, which I found to be really powerful. And something that I talk about with my, my young daughter, pretty consistently is the idea of a monkey mind. So there's the idea of the monkey mind. And the monkey mind is the consistent flow of subconscious thoughts that are constantly buzzing through your brain at any given time of the day. Right? It's reminding you of that shit that you forgot to do, that you were supposed to do, that somebody might ask you about in the future. It's reminding you that you said something stupid to that person that you liked last week, and now you can't feel anything but shame about that one thing. And it can't escape your brain. It reminds you that, you know, so and so is out there doing this incredible thing and that you should possibly be capable of doing the same thing. So, and, and you're not living up to your potential. It's reminding you that you know, it's that the song that won't get out of your head, right? It's, it's the constant repetitive music from in Canto, cuz your child watches that. Uh, if you haven't watched that movie, it's interesting, but it drives me nuts. Um, but anyways, back to monkey mind. The monkey mind is the part of your, your, your thought processes that are uncontrolled. It's the things that give you anxiety. It's the thoughts that make you depressed. It's the things that you feel are out of your control, right, That are driving you to be anxious or sad or mad or it, it's basically the, the autopilot of your brain when you decide or when you don't decide to be in control of it. And so what the initial parts of meditation end up being is learning how to submit that monkey mind. And usually it starts with something like this. They'll tell you to sit down, they'll tell you to take a deep breath, they'll tell you to take another deep breath and through your nose, without, through your mouth. And at a certain point they'll tell you the count breaths, right? I want you to count from zero to 10 each full breath being one, two. Whew, three. And you do that until you hit 10, and then you count from 10 down to zero doing the same thing. And so you continue that process, you know, let's say six to 10 times, right? One to two minutes of continuing that process of just thinking about your breath and counting your breath in a way that it completely takes over your consciousness and rids you of any of the poisonous thoughts that are happening because of your monkey mind. And then the next step is to sit still. Do not count and just breathe. But I want you to think of nothing. I want you to have a completely blank slate in your mind, and I want you to relax your body and mind and just think of absolute nothing. And when people generally start this practice, what they'll find is that their monkey mind is so powerful in their true self, their true consciousness, which is the individual who controls what is behind that monkey mind, right? Who subdues that monkey mind and determines that they're going to stop smoking a cigarette, right? And, and determines that they're gonna write that book and, and overcome the obstacles and, and the easy habitual ways of thought patterns and, and patterns of action that are in their way, right? And so by through this process of subduing your monkey mind for 10 minutes and every time that you're, you know, because it will happen every, you'll get frustrated the first time you do it. You'll breathe in, you'll breathe out, and all of a sudden that stupid assignment that you were supposed to do for school will pop into your brain or that task that you were supposed to have done tomorrow for work that you forgot about when you're laying up at night at nine 30, knowing you're not gonna wake up and go do it. and then you breathe and you remember that you're supposed to focus on your breath. You're not supposed to focus on all the stupid stuff that you forgot to do, . And by consistently subduing that monkey mind, you'll find that you get more space for the things that you wanna do in life, right? You'll find that you, you, you're not picking up that cigarette as often or at all. You'll find that you are more in control of your thoughts. You will find that there's this, you'll know, you'll start to notice because it's not gonna go away initially just by starting to do that. But what you'll find is that you'll start to notice your monkey mind more often, and you'll start to disassociate with the thoughts that are consistently going through your mind, that you normally identify with things that drive anxiety, things that drive depression. And after a certain amount of time of doing that, let's call it six months, your anxiety lessons, your depression shrinks away. Because you are starting to notice the patterns that are leading to that, the thought processes that have been carved into your brain since you were a child, that your parents put there for you, or by that your coach told you that you know, you were not good enough or whatever it is. You'll find that you can start to reparent yourself, to reeducate yourself, to retrain yourself, to live a life in a way that you want to because you're no longer being controlled by the whims of your subconscious thoughts that you have no control over, but you're subduing those thoughts and instead replacing them with intentional ideas of positivity, of gratitude, of, you know, things that are good for you, not things that are bad for you. And so through that initial phase o of of meditation, you start to expand your, your true self, your true consciousness. And so that, If normally your brain's being taken over by your monkey mind for, I don't know, call it 85% of the day, that by learning how to submit, make that monkey mind tap out through the intentional practice of meditation that your true self, your true consciousness, who has your best interest in mind, that is not just specifically repeating the, the traumatic experiences that you had because they're comfortable and habitual, you'll find that your life becomes better. You'll find that you have more gratitude for things you'll find less wanting and more gratefulness. Right? Um, you know, I, I, I tell my daughter this, grateful, not want. Right. Um, and, and so, you know, when my, my daughter is, is a lot of energy, right? Lot like I was as a kid, a lot of energy. And, you know, she has constant, you know, bouncing up and down because she wants to be doing something and she does gymnastics like, I don't know, like 16 hours a week, And so she, she has all of this energy that she needs to get out. And what I've found is that it's all that bouncing is going on in her head, is going on in her brain that monkey mind is taking over. And of course it is. She's six years old, right? And so, but what I've taught her is that, you know, I've taught her the idea of the monkey mind and to disassociate herself from the negative subconscious thoughts that drive anxiety and drive those, those negative emotions. And to realize that it's your monkey mind and that all you need to do toue, that monkey mind through practice is by taking a deep breath in and taking a deep breath out and noticing your breath. and simply by doing that as often as you can, you'll find that you're taking control over from that monkey mind. And that's the introduction into meditation. That's the general idea. If you download the app Headspace, if you download the app, Calm, um, any of those popular meditation, uh, apps, what you'll find is that's always step one. Step one is ridding yourself. Not even, you'll never rid yourself of your monkey mind, but you can learn to sub do it and learn to notice it to the extent that you can start to sub do it as often as possible and replace it with positive, helpful thoughts instead of negative, uh, negative emotions and negative repetitive thoughts, right? So that's the intro and that's where you generally start with meditation. Then once you realize how powerful that that is, you'll start to move into more interesting. Once, once you feel the effects of that, you'll go, Wow. This shit really works, . It's crazy. And so you start to see the positive effects and that, and it starts to make you realize the power that you have through intentionality, through sheer willpower. You can rid yourself of your anxiety by rid yourself of that monkey mind, at least as often as possible. Now, the next step that you'll take and, and or can take in that journey is something like K yoga, Something like transcendental meditation is something like, um, you know, these, these different, more, uh, more in depth, more wild types of meditative techniques that yield different interesting results. Okay? So one of those ideas, and where we started from with this was, um, the idea of, um, let's see, where is it? Uh, he talks about. The idea of calling on a higher self, which is the expanded consciousness of the subject. And so an experience that I've had with this, which was truly very po, I've, I've, I've had probably three super unbelievably impactful meditations that have changed their trajectory of my life forever. Um, and again, I'm, I'm generally, I'm a, a type, hyper logical person. It was, it was with some, you know, I have a, I have a draw towards these types of, you know, meditations and yoga and things that I find to be interesting for my personality type. But, um, I tend to be a hyper logical person. But you, once you start to enact these things, it's hard to deny the effects of them. So I did a, I found a, you know, I used to wake up every morning at like six 30 in the morning and I would come downstairs to my, you know, my basement. I would have my yoga mat there. I would lay down and I would do some type of yoga or some type of meditation, and I would alternate. I would do yoga. Then the next morning I'd do meditation. I would do yoga. And then the next morning I do meditation. And I found this transcendental meditation on YouTube. And if I can find it, I will link it in this week's subst stack. And if you haven't joined your subst, you should, uh, it's directly on our website, Red Pill revolution.co. You'll get all the links, all the articles, everything we're talking about today will be directly on the Subst stack. So go there, sign up, give your email, you'll get everything that we're talking about here. Okay? And including, if I can find this me. I will post it in there. It's on YouTube, and I believe it was a 10 megahertz, um, was the, the frequency that was used in it. And so, um, I laid down, and what this had you do is it had you get to the most calm state that you could possibly feel it. And, and you'll see people, like when they're meditating, they touch their fingers together, um, like they're index f or their pointer finger and their thumbs, right? The, the, the traditional, you know, funky, weird meditative sitting stance where most people aren't flexible enough to sit their legs weird. Crissy I am, by the way. Um, but you put your fingers together, right? And, and what I've found is that when I'm in a deeply meditative state, I find that the feeling of my fingertips goes away. It's a really wild phenomenon, but I know I'm there. I know that I've met this, you know, this deeper state of consciousness when I no longer know the room that I'm in. I'm no longer, you know, laying in in the, the shower, right? Sometimes when I meditate, I'm no longer laying on the floor of my office. I'm no longer on a yoga mat. I'm no longer looking at a wall inside of my house. I'm in my own walled garden, my own consciousness that is outside of where I'm at in this world, in this time, right? But if I open my eyes at any given time, sure I'm still in that room, but it does not feel like it at the time. So you lay down. And this, this guided meditation, this transcendental meditation walked me through the steps. And, and the idea was that you laid down your, you're calming yourself to the point where you can realize that your consciousness is a ball of energy, right? Your being, your soul is this ball of energy. And as you relax more, it walks you through the process of realizing there's a window in the room. And as you start to remove yourself, that, that ball, that blue light of energy or whatever color you give it, as you start to remove that from your vessel, from your body, in this meditation, it tells you that there's a window in the room or there's a door. And through this door and through this pathway, You will, if your soul, your consciousness will float up through this window. And as it escapes from the room that you're in right now, you will walk into a long hallway, or at least this is how I visually perfectly remember this meditation, which was maybe a couple years ago at this point. But I vividly imagine, I vividly remember this because I was literally here. So it walked me through. I walked, you know, I floated through this hallway, and on either side of me were these, uh, weird, like capsule looking things. Almost like the, you know, how you would picture the cryogenic chambers that people get frozen in when they go to space. It was kind of weird, you know, But each one of them, each one of these, you know, capsules on each side of me were closed off glassed in windows that I could look into. And each one of them was a, a, a different version of myself, a different, uh, a different variation of my being and a different reality. . It was crazy. Trust me, I, I wouldn't believe this either if I was you, but it, it was, it was really interesting. Think of it, even if it's hard to remember, imagine this as a, think of it like a dream. I was floating through this room, down this hallway that, that turned in this really interest, like perfectly circular angle around this corner that I never had to get to, because by the time that I'd noticed each of these vessels, I looked at each of them and there was almost like as if there was this, you know, monitor on each outside of it, which, which told me the personality traits of this individual that told me their drive, their work ethic, their, um, you know, their attachment to love and, and, and their ability to be compassionate and caring and their, uh, grind, you know, their, their ability to, to go after a goal and their tenacity and their, you know, all of these different personality traits of all these different vessels down this hallway of all these different variations of who I am as a person in different realities. And so I walked along this hallway and I, I looked at each one of these vessels and I, and I felt a, a magnet or a magnetism to a certain one of these, you know, uh, encapsulated versions of myself, . And so I walked up to this glass window and I felt who this version of me was, and I realized that's the best version of me that I need for this time in my life to be a compassionate, empathetic father, to be a good friend, to be a hard worker that's successful working towards my goals. And so I, I found that the color, when I, I realized that I was going to basically embody the traits of this variation of my personality. Um, and so what, what I felt in that moment was the color of the orb that I removed from my body back in my office, laying on the floor on a yoga mat. The, the color of my consciousness that that energy ball that floated through this hallway changed into a different color. It was wild. And as I follow, as I did that, I, it, it called me back. And I, I walked, you know, floated back through this hall as this new variation of who I was and found myself back through that window that I came in from back into The body that I had was given in this reality, but with the renewed sense and qualities and traits of the version of myself that I found in that room, crazy . It was wild, right? So this is like, I, I'm fairly positive it walked me through a majority of that experience and, um, It was so crazy, and right around that time, I had a turning point in, in my, you know, what I did in my life. It, it caused me to rethink the day to day habitual actions that I was taking, the trajectory that I was on for my career, the, the things that I enjoyed doing. It made me question all of that, and it made me embody the traits of, of the compassionate father that I saw myself as, or felt myself as in that different world that, that, that hallway that I walked down. It was such a powerful experience, and to know that I could access that room at any given time that I needed. Right. Whether I needed to, to change my personality traits, to, to be a better father, to be a better husband, to be a harder worker, to, to change my career, to have the balls, to go after a dream, like starting a podcast with the hopes of turning it into a successful career. It took me being a better version of myself than I knew I was in that moment before I left this room that I'm sitting in right now on the floor on a yoga mat. I knew it took more than that to be who I needed to be to get where I wanted to go, and I found who I could be in that meditation, and I brought that wa back with me and it's never left since. It's, it's such a crazy experience. Okay. That, that all to. That I 100% believe that this is possible. Right? Improved problem solving by calling on a higher self, which is expand, which is the expanded consciousness of the subject. I could have found any number of variations of personality traits that I needed to embody to reach my goals, to be a better person, to be who I wanted to be in that room. And I found it, and I brought it back with me and IEM embodied it. Okay? It was wild. It was crazy. You might not believe me, but it, it had a tremendous effect on my life, okay? And by now, you know, I, I don't bullshit. I don't talk. I, I don't just talk to talk. That was a crazy, unbelievable experience that I had. And if somebody told me, and I never meditated before, I wouldn't believe you either. Um, but that was one of the three really impactful meditations, one of the really impactful spiritual journeys that meditation has taken me on. And I'll walk you through the others at some point in this conversation today as well. But that one was crazy. All right, now it goes on to talk about, um, patterning, projecting the will into the universal hologram and the attempt to manifest a new reality. Um, some people refer to that as reality shifting. If you've ever seen the movie Everything Everywhere all the time or some shit like that, it's like everywhere. Everything everywhere all the time. I'm pretty sure that's the name of it. It's probably one of my top three movies it's ever I've ever watched. I love this movie. It's an unbelievable movie. It talks about the multiverse, it talks about different realities. It talks about this reality shifting idea, right? And, and calling on yourself from a different, you know, variation of your reality where you are, you know, have different personality traits, a different career projection, that you have a different. Uh, husband or wife or, you know, all of these different splits that you changed your reality based on a tree of decision making. Right? And I think that's a really interesting concept is, is that every decision that you make in this life splits off into a different un unlimited amount of realities, right? And, and so whether or not, you know, my wife and I met in high school and we're now married 10 years later, right? We, we stayed together that entire time, but on a different reality that didn't happen, right? We didn't meet each other in digital photography class in high school, . And, um, we didn't have three children together and we didn't get married in Paris and we didn't do all of these things. And, and somewhere I'm a lonely, uh, drunk who has no life goals, at all, because I didn't meet my wife in high school, right? And so there's all of these splits that happen. Simultaneous level at any given time based on the reactions that you make to the stimulus that's taken in, right? Even just by talking about this meditation today, even by just having that conversation that we just had, I might have impacted your life in a way that you go home and you're interested now in trying meditation. And just by doing that, you split your reality from being somebody who never tried meditation to somebody who subdues their monkey mind on a daily basis, rids themself of anxiety and depression and lives the up to the full potential of your life that you could possibly have. All because of this one weird, crazy instance that you so happen to click on this podcast and listen to me talk about this. Right? And so I think that idea. I think that almost every decision that you make in your life, it, it branches you off into a different multiverse reality. And by doing so, you specifically manifest your reality through your thoughts because your thoughts are what drive your decisions. Your thoughts literally shape the reality around you at any given time, specifically by pushing you into a different possible reality than you would have been had you make a different, had you made a different decision and a different you in a different world, which is brought to us by string theory, right? The idea that there's all these consistent realities going on simultaneously around the world and time and space really doesn't exist, and all these wild theories that are now basically being accepted by science today come into play. Every decision you make branches off into a different reality. Every decision that you make turns you into a different you that you would've been and somewhere existing at this exact same time as the you that didn't make that decision. That has a different life is a different result of basically every decision and thought that you've ever had. It's a crazy thought, right? It's it's a unbelievably crazy thought, um, and it leads you into the simulation theory and it leads you into all these really interesting thought experiments, right? But it all starts kind of with that idea. Go watch that movie. If you want a little bit of insight into what the idea of the multiverses and an unbelievably entertaining and funny, and hilarious, and serious, and it's probably one of my favorite movies of all time, everything everywhere, all the time. Go watch it all. But that talks about the reality shifting, Right? By by specifically doing, you know, a, a, a, making a different decision in life, you're, you're jumping from this reality into a different one. Okay. Now it says that the, um, let's see. Color breathing and energy bar tool techniques are meant to stimulate healing effects on the body through the use of visualization. Out of body experiences allow individuals to exit their bodies and explore the physical world and beyond. This aspect of the gateway process is what McDonald finds to have been the most potential for use in intelligence operations as it would allow instantaneous information gathering. However, he knows that the process seems to garble and distort information being gathered, limiting its efficacy. The analysis of gateway process is a deep exploration into something seemingly supernatural remote viewing. And out of body experiences would revolutionize information gathering. If individuals could be quickly trained and results could be dependably replicated, the gateway process would be an invaluable tool to intelligence and military. However, the practical applications seem to be an afterthought for McDonald. Instead, the document spends more time establishing a grand theory to explain how out of body experiences might be possible. The holographic world, the influence of will and our conscious minds escaping into a sub planky universe outside of space. Although the simple act of meditation aided by uniquely paired sound frequencies, there is one more odd detail remaining about this document. Page 25 of the document is mysteriously missing. The implication is that this page explored the practical applications in greater depth. However, it has not been included in the declassified version. A petition exists for the public's access, but the CIA has released a statement that they will never receive this page either or they never received it, either. One theory is that McDonald admitted this page to drive individuals to explore the gateway process on their own. If you're one of the intrepid souls looking to put McDonald's theories to the test, links to the Monroe Institute and Gateway tapes are included in the description and will be included in the subs. For those of you who plan to remain in this dimension, please share your thoughts in the comments below. Um, The 25th page has since then found, and I will go through that with you in a moment. But the first thing I need to do is go to red pill revolution.co. Sign up for the subs stack. Okay? If you're signed up for the subs stack and you are in one of the eight states listed, I need you to go in the description. I need you to go to red pill revolution.co, click the menu and get a life insurance quote. Okay? This is my only ask for literally anything, is if you want to support the show, you can do so by getting yourself and your family life insurance. Okay? I currently have eight states. I'm working on getting others. I've had people email me who I am still working on getting the licenses for, um, but it's a little bit of a process. So as soon as I get those, I will email you back and we will get you insured. If you are in one of those eight states that are already listed on that in the description here, you can go directly to the website, red Pill revolution.co, and sign yourself up for life insurance. Now normally what you do when you go to look for life insurance or health insurance is you're gonna put your information into a website. They're gonna trick you into thinking you're getting quotes. You're gonna put your phone number in there, and you are going to get blown the fuck up by every single insurance agent and their mama. They'll never stop calling your phone. You know, I can give you some advice if they start doing that to you because I was an insurance agent for a very long time, and I still have my active license, which is why I can offer you life insurance without being through third party companies. There's no advertisements at all on this podcast. The only thing that I ask is if you're in one of those states, go ahead and head over to the website. Sign yourself up from some life insurance. Protect your family because your ass is going to die. I promise you, 100%. Trust me, I meditated on it . But head over to the website, get a life insurance quote. Go ahead and sign up. If you have any questions, email me. Austin red pill revolution.co. I'd love to help out. I recommend a 15 year term policy at 15 times the amount of your annual salary that should basically get you covered. Um, no reason to get whole life, no reason to do any of that. It's basically a shitty investment. Um, so 15 year term, 15 times your annual income. Anyways, go ahead and hit the subscribe button. I love ya. Thank you for listening. Now let's go ahead and jump back. Into it. All right now, the gateway process, page number 25. Now, before I wanna do that, let's talk about what started me into this process and started me into this conversation because more recently I had a different, probably the most impactful experience of my life on the way that I view my family, the way that I view my friends, and the way that I view basically the humans around me. Now, this happened, I think two weeks ago now, and it's a fair, fairly, uh, you know, um, interesting topic to hear from somebody with a personality like mine. So I was downstairs. I, I had listened to a podcast by Tim Ferris talking to. Gads, uh, Gad Sied, Um, something along those lines. He was also just recently on the Joe Rogan podcast. Uh, let me see if I can find who it was. Um, but basically he is a guy who wrote a bunch of books, uh, Gad Sad, g a d s a A D, and he's a psychologist who has done, uh, meditative retreats and psychedelic experiences with groups of other psychologists or psychiatrists, and in attempt to see the healing effects. Um, And when he talked about these things, he talked about his experience with meditation, right? He talked about going on, uh, you know, doing this retreat that he set up for all these psychiatrists to figure out the, the helpful effects of something like iowaska. And they went to somewhere in the Amazon and they all did iowaska together. And he was told by the shamans that, you know, your energy is so dark that it's affecting everybody in the room. We can't break through to these other individuals because your energy is so deeply disturbed. And come to find out, he had an extremely difficult childhood that he was still processing and all these horrible things that happened to him, which makes sense. And also, he was a psychiatrist or a psychologist, one of the two who had been basically taking on the trauma of everybody, every patient he had ever had without any outlet for dealing with it. And these shamans basically taught him how to deal with the trauma of his patients in a positive way outside of using psychedelics, which was meditation. And so he found, uh, um, he found sad Guru, right? If you don't know who, uh, Sad Guru is, he was also on the Joe Rogan show. Very interesting guy. He's one of the, probably the biggest yogi gurus in the world today. The biggest, as far as like mainstream, yo, you know, American culture goes. And so Sad Guru is a really interesting character and I was interested in listening to the meditation that he put out there that this guy, um, sad. Or gad. Sad. A lot of sad going on here, . Anyways, so I listened to this, this, you know, meditation, this guided meditation, um, this mantra meditation by sad guru. And it talked, you know, it was very, very simple. I was expecting much more out of it than I, you know, not much more out of it, but I was expecting a much more robust meditation than what we, what I got from it. It was a 10 minute meditation where he basically sat there the entire 10 minutes and had you repeat that, the, the consistent mantra after taking a few deep breaths and relaxing your body and relaxing your mind and making you repeat the statement, I am not my body. I am not even my mind. I am not my body. I am not even my mind. I am not my body. I am not even my mind. And he repeated this for about 10 minutes, and at the end of it, it was a weird sound to hear because he started to do this, you know, chant or, uh, You know, sound, you know, the home kind of deal that you would kind of anticipate being, coming from , a yogi teacher, uh, in India. And, uh, the whole room that he was in, I didn't even know he was in the room until, you know, nine minutes into this where you hear it just echo through this whole room with this unbelievably like earth shaking sound. And so after that meditation was done, 11 minutes my YouTube went on to play, you know, just this background music. And I was so deep into this meditative state that I was sitting there and I got, like, pulled into this experience and that it might be a little even emotional to talk about. It was really interesting experience. So I, I was sitting there quietly and I remember, you know, being in a, you know, kind of getting to that meditative state, I couldn't feel my fingertips. I, I felt my oldest daughter. Come up from behind me and hug me and my daughter, you know, she's in first grade, so my, my oldest daughter come up from behind me and hug me. And, and, and so I felt my daughter do it. And then I felt my youngest daughter come up behind me and hug me. And then I felt my son come up from behind me and hug me. And then I felt my wife come up from behind me and hug me. And there was an interesting thing that it was from behind me. It's like, almost like I didn't, I didn't have to give anything to get this love from them, Right? Which is very true. And so they, she came up from behind. I, I felt the feeling of this like compounding feeling of love for my children and my. And then I just kept going. I have a very big family. I, my, my father came up from behind me and hugged me, my mom, my, my stepmom, my sisters. I have six sisters, each one of them all at the same time. Like this crazy, just expression of love, this feeling of everybody, grandparents, friends, all around me at one time in this singular hug and expression of love to me, without me having to reciprocate anything at all. Right? It was this overwhelming feeling of, of love and, and happiness, right? And so that was the first step. The first step was I, I felt every important person in my life at the very one by one in a compounding effect come up to me and hug me in this. And like I said, this is even, you know, that's a powerful feeling to have, right? And so the even exper re-experience that now just thinking about it is, is emotional. And so they, every one of these, just this compounding feeling, the, the best feeling you could ever imagine in your whole life is every person that loves you just coming together and hugging you at the one time into a point where it physically was not possible that all of these people hugged me at the same time, right? It was just the feeling, the emotion that the, the accepting of this love. And so that was the very first thing. The second thing that happened was I started to identify that between each person that came up to me. Some of the older people, not my children, but each person in my life had difficulties at some point or another, or trauma or difficult memories or childhood trauma with somebody else that was hugging me at the time. And so I remember walking step by step, person by person, facilitating basically, uh, a hug or an apology and an accepted apology and acceptance of that. Each person had their own systemic problematic issues that led to actions that affected the other person, right? So like, you know, let's say. Your Uncle Joe was a jerk, or as of a father and, and wasn't properly, You know, this has nothing to do with my family, but your, your uncle was a jerk to your cousin. Right? And, you know, and, and so picture your Uncle Joe standing in front of your, your cousin Jan . They really liked the, the j names and, you know, them just showing this expression of like, apology acceptance and then love. And then I would move to the next person, right? And, and my sister with so and so apology acceptance and love and, you know, my dad with, you know, the person that I feel affected him and, and him standing in front of that person as a child. Apology from that person, acceptance, embrace and love. And, and it just went person by person and person by person. And there was some deeply, you know, in every family there's always some, some difficult shit to deal with, right? And so there was this ongoing thing of every person who came up to me that I felt that embrace from, I facilitated the apology acceptance and love from the person that affected them negatively in their life from the perspective of them as a child, like even my own father. And I know some of the things that he went through and I, I vividly imagined him as a seven year old. In front of the person that, you know, I feel, you know, maybe he deserved or, or wanted, or, or could potentially look for an apology that would help him if he accepted it and then felt that embrace of love. Right? And obviously most of these people have probably gotten past these things, but, you know, for me it was really, really powerful. And, um, you know, there was, there was one person, you know, with multiple people that, that I felt that with, right? Facilitated my own, you know, feeling of being a child and feeling of the effects that that individual's actions had on me as a child. And then feeling the apology, the acceptance of that, the true acceptance of that apology, the understanding of where those actions came from, from like the systemic issues of where that person, what that person grew. In, and then the embrace and the love of that person and, and all the way through to some, you know, every person down the line had somebody in one shape or another that affected them in a negative way. And it was the facilitation of this apology acceptance and love in this meditative state. I'm literally visualizing every single person, one by one, dealing with their trauma, shouldering the burden of that trauma and facilitating the, the acceptance of that apology and the embrace of the love, and then would move on to the next person. It was such a wild experience because it gave me insight into why almost every person affected the other person was because somebody affected them in a negative way, right? If somebody was, um, a bad friend or a bad spouse, or a bad parent, or a bad this, or a bad sister or a brother, or this or that, or whatever, It wasn't because they're a shitty person, it was because they had been affected in some way that made them affect somebody else in another way. So it was like this domino effect of like shittiness of humanity that without the acceptance of the apology and the embrace and love would be carried by every person forever, because it's an ongoing cycle of trauma until you break that cycle. And so it was like, I was literally eight in the morning. I had to leave for work at eight 30 and it was some really heavy, heavy visualizations in this meditation that I was not facilitating this. These weren't thoughts that I was, now I'm thinking this. It was none of that. I was being pulled through. It was like watching a movie in front of me. And even now it's like I just have these butterflies in my stomach because it was such a powerful experience. And so, Through, through all of this. By the end of it, I'm just had f from the very beginning, from the, the feelings of the embrace of every person that loved me simultaneously from the behind. Um, obviously if you really felt that every person loving you is simultaneously at one time, and you truly felt that the way that your spirit is, you know, fulfilled at that time, you just like I did, would start, I just broke down and, you know, it was just such a positive experience. I, I really haven't had too many happy experiences in my life that made me cry and as a man, right. You know, I cried and it was because of the love that I felt. Not something bad that happened to me, not frustration, but at the beginning of this, it was the love that I felt. And then it transitioned to those heavy burdened, you know, Uh, difficult facilitations of trauma and acceptance and apologies and love from each. I knew everybody's story deeply and intensely felt the trauma in, and, and intensely felt the interaction between that person who was affected as a child, literally, vividly imagining that person at that age and seeing the person that loved them, but didn't show it properly at that time. Apologizing, hugging, loving, embracing that person and the acceptance of that apology. So it was like literally burdening, getting, bearing the burden and weight of every individual's trauma in my family simultaneously. And then the positive outcome that happened by the end of it. And so it turned into that, right? And it was like, I was literally just taken on this unbelievable spiritual journey of all of this, you know, love and trauma and apologies and acceptance of those people in my family at one time. And at e
Shavuot is one of three pilgrimage festivals that is commanded in the Torah (Exodus 23:14-17; Deuteronomy 16:16). In Hebrew, its name means “weeks,” derived from the command in Deuteronomy 16:19, “You shall count seven weeks for yourself; you shall begin to count seven weeks from the time you begin to put the sickle to the standing grain.” Many Christians know Shavuot from its Greek-derived name “Pentecost,” as Pentēkostē means “fiftieth,” indicative of the fifty days that are to be counted between Passover and this time.
Certainly, when Believers in Messiah Yeshua sit down to partake of the Passover meal, we are not just remembering the Exodus of the Ancient Israelites and the plagues that God dispensed upon the Egyptians. We are sitting down to remember great events in the salvation history of the world.
The holiday of Purim is a relatively minor festival in the Tanach (Old Testament), yet it portrays a very important story that all of God's people need to understand. Having been dispersed into Babylonian exile in 585 B.C.E., the Jewish people now find themselves under Persian rule. While many find their new Persian rulers more tolerant than the Babylonians, the Jews are still a minority and often find themselves subject to harassment and persecution. In the Book of Esther, King Ahasuerus' (or Xerxes') grand vizier, the evil Haman, devises a plot to kill the Jews when he is not worshipped by Mordecai. But Ahasuerus' new wife, the Jewess Esther, is placed in just the right position at just the right time to see that this scheme does not come to pass. Instead, Haman is executed using the very means that he intended to use against the Jews.
The final part of our discussion where we discuss Dr. Jenifer Denetdale's article, "Chairmen, Presidents, and Princesses: the Navajo Nation, Gender, and the Politics of Tradition". We include our commentary and pivot to the people's experience in a pageant. If you want to read the article, dm us on instagram. (2:22) - Summarization of article by Shandiin. (3:30) - Article commentary (24:04) - Kodee's story about being Mutton King (30:19) -Alysia's story about pageant (38:52) - Shandiin's story about miss navajo 2021 (51:01)- Advice to people who want to participant in a pageant.
Alex, Pat, and Palmer Recap the power 5 conferences up to this point. They also give some of their week 5 locks. Be a friend, Tell a friend.