正在加载视频...

视频加载失败

返回首页

A 7-million parameter model outperforming models a thousand times its size on tasks like ARC Prize. That's what recursive reasoning unlocks. In this episode of Decoded, YC's Ankit Gupta and Francois Chaubard break down two recent papers on recursive AI models, HRMs and TRMs, that are achieving state-of-the-art results...

ycombinator's profile picture

Y Combinator

1,618,332 subscribers

127,645 次观看 • 3 个月前 •via X (Twitter)

教育新闻政治科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing HRM-Text. An ultra-lean 1B-parameter reasoning language model designed to deliver strong general performance with a fraction of the data, compute, and infrastructure. Trained on just 40B structured tokens, HRM-Text achieves competitive performance while using ~1/1000 of the training data of comparable models. The kicker? The full model trains in roughly one day on a $1,000 budget. This opens the door to a new generation of AI that is powerful, accessible, and radically easier to adapt. Theories and research concepts once deemed too expensive to test are officially back in the game. Sapient Intelligence invites you to help us shape a new paradigm for general intelligence.
5:31

Introducing HRM-Text. An ultra-lean 1B-parameter reasoning language model designed to deliver strong general performance with a fraction of the data, compute, and infrastructure. Trained on just 40B structured tokens, HRM-Text achieves competitive performance while using ~1/1000 of the training data of comparable models. The kicker? The full model trains in roughly one day on a $1,000 budget. This opens the door to a new generation of AI that is powerful, accessible, and radically easier to adapt. Theories and research concepts once deemed too expensive to test are officially back in the game. Sapient Intelligence invites you to help us shape a new paradigm for general intelligence.

Sapient Intelligence

515,089 次观看 • 2 个月前

Diffusion is the foundational ML framework behind state-of-the-art AI image and video generation, including Sora, Midjourney and Google Veo. In this episode of Decoded, Ankit Gupta sits down with Francois Chaubard to discuss how diffusion works, walk through a code sample, and explain why everyone training models should understand it. 00:00 Intro 00:33 What is diffusion? 02:50 What are applications of diffusion today? 04:06 Key innovations 07:01 Code examples 19:25 The "squint test" 22:27 Other areas diffusion is widely accessible 24:49 Outro
27:10

Diffusion is the foundational ML framework behind state-of-the-art AI image and video generation, including Sora, Midjourney and Google Veo. In this episode of Decoded, Ankit Gupta sits down with Francois Chaubard to discuss how diffusion works, walk through a code sample, and explain why everyone training models should understand it. 00:00 Intro 00:33 What is diffusion? 02:50 What are applications of diffusion today? 04:06 Key innovations 07:01 Code examples 19:25 The "squint test" 22:27 Other areas diffusion is widely accessible 24:49 Outro

Y Combinator

74,604 次观看 • 6 个月前

ARC-AGI is redefining how to measure progress on the path to AGI - focusing on reasoning, generalization, and adaptability instead of memorization or scale. At NeurIPS 2025, YC's Diana sat down with ARC Prize President Greg Kamradt to find out why most AI benchmarks fail, how ARC-AGI reveals the limits of today’s models, and why measuring intelligence may be harder than building it. 00:11 — What ARC Prize is and why it exists 00:38 — François Chollet’s definition of AGI 01:48 — What ARC-AGI Actually Tests 02:25 — When LLMs Failed the ARC Benchmark 03:38 — ARC-AGI Becomes the Standard 04:49 — False Positives in AI Progress 06:06 — The Evolution of ARC-AGI 08:55 — Measuring Intelligence beyond just accuracy 10:25 — What happens if a model solves ARC-AGI?
11:59

ARC-AGI is redefining how to measure progress on the path to AGI - focusing on reasoning, generalization, and adaptability instead of memorization or scale. At NeurIPS 2025, YC's Diana sat down with ARC Prize President Greg Kamradt to find out why most AI benchmarks fail, how ARC-AGI reveals the limits of today’s models, and why measuring intelligence may be harder than building it. 00:11 — What ARC Prize is and why it exists 00:38 — François Chollet’s definition of AGI 01:48 — What ARC-AGI Actually Tests 02:25 — When LLMs Failed the ARC Benchmark 03:38 — ARC-AGI Becomes the Standard 04:49 — False Positives in AI Progress 06:06 — The Evolution of ARC-AGI 08:55 — Measuring Intelligence beyond just accuracy 10:25 — What happens if a model solves ARC-AGI?

Y Combinator

98,369 次观看 • 7 个月前

Why do even our best AI models need tens of thousands of examples to learn skills that a human picks up in a handful of tries? Solving this problem is one of the great open challenges in modern AI. World models, which give AI an internal simulation of its environment, are one of the most promising paths forward. In this episode of Decoded, YC's Ankit Gupta and Francois Chaubard discuss the intuition and math behind world models, new research, and current applications in self-driving, robotics, and more. 01:45 — What would perfect efficiency look like? 05:10 — World models in the human brain 09:20 — Control theory & the drone example 14:30 — When physics breaks down 17:45 — Chess, Go & the action space problem 24:10 — Why AlphaGo can't scale 28:00 — Monte Carlo tree search explained 34:00 — Self-Driving: state space is infinite 40:30 — Model-Free vs. Model-Based RL 44:00 — Why robotics is the hardest case 48:20 — World models that actually work 54:10 — JEPA & latent space tricks 59:00 — Open problems remaining 1:04:30 — Does this pass the squint test?
1:14:26

Why do even our best AI models need tens of thousands of examples to learn skills that a human picks up in a handful of tries? Solving this problem is one of the great open challenges in modern AI. World models, which give AI an internal simulation of its environment, are one of the most promising paths forward. In this episode of Decoded, YC's Ankit Gupta and Francois Chaubard discuss the intuition and math behind world models, new research, and current applications in self-driving, robotics, and more. 01:45 — What would perfect efficiency look like? 05:10 — World models in the human brain 09:20 — Control theory & the drone example 14:30 — When physics breaks down 17:45 — Chess, Go & the action space problem 24:10 — Why AlphaGo can't scale 28:00 — Monte Carlo tree search explained 34:00 — Self-Driving: state space is infinite 40:30 — Model-Free vs. Model-Based RL 44:00 — Why robotics is the hardest case 48:20 — World models that actually work 54:10 — JEPA & latent space tricks 59:00 — Open problems remaining 1:04:30 — Does this pass the squint test?

Y Combinator

110,219 次观看 • 23 天前

OpenAI recently released its first open-weights model since GPT-2, entering a field led by DeepSeek and Alibaba's Qwen. Ankit () breaks down these top OSS models, including what sets them apart under the hood: mixture-of-experts, long-context training, and post-training techniques that shape reasoning and alignment—and how different design choices lead to surprisingly similar performance. 00:00 – OpenAI OSS Launch 01:00 – Comparing Open Source LLM Architectures 01:46 – GPT OSS Overview 02:37 – Under The Hood of GPT OSS 03:25 – Qwen-3 Architecture 04:17 – Qwen-3 Training 05:12 – Qwen-3 Post-Training 06:08 – Qwen-3 Reasoning & RL Innovations 06:52 – DeepSeek V3 Overview 07:40 – DeepSeek V3.1 Updates 08:39 – Attention Mechanism (MLA) 09:39 – Comparing Model Sizes 10:35 – Long Context Strategies 11:25 – Reflections on Methods 12:00 – Takeaways
12:31

OpenAI recently released its first open-weights model since GPT-2, entering a field led by DeepSeek and Alibaba's Qwen. Ankit () breaks down these top OSS models, including what sets them apart under the hood: mixture-of-experts, long-context training, and post-training techniques that shape reasoning and alignment—and how different design choices lead to surprisingly similar performance. 00:00 – OpenAI OSS Launch 01:00 – Comparing Open Source LLM Architectures 01:46 – GPT OSS Overview 02:37 – Under The Hood of GPT OSS 03:25 – Qwen-3 Architecture 04:17 – Qwen-3 Training 05:12 – Qwen-3 Post-Training 06:08 – Qwen-3 Reasoning & RL Innovations 06:52 – DeepSeek V3 Overview 07:40 – DeepSeek V3.1 Updates 08:39 – Attention Mechanism (MLA) 09:39 – Comparing Model Sizes 10:35 – Long Context Strategies 11:25 – Reflections on Methods 12:00 – Takeaways

Y Combinator

208,680 次观看 • 11 个月前

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.
2:52

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 次观看 • 2 年前

Why AI Progress Suddenly Feels Real - my conversation with Yann Dubois, who co-leads the Post-Training Frontiers team at OpenAI 00:00 - Intro 01:30 - Why recent AI progress feels like a step function 04:13 - Model reliability & the emotional rollercoaster of shipping GPT-5.5 07:33 - How OpenAI structures vertical and horizontal teams 09:49 - Improving model efficiency and test-time compute 12:32 - Yann's journey from Switzerland to OpenAI 15:37 - Reasoning in 2026: Real-world utility vs verifiable rewards 18:34 - GPT-5.5 Thinking vs Pro: Scaling test-time compute 20:09 - How reasoning models become more efficient 23:23 - Pre-training scaling and overcoming the data wall 27:03 - Multimodal data, synthetic data, and embodied AI 31:05 - Demystifying mid-training and post-training 37:21 - Does RL create new capabilities in AI? 38:53 - The challenges and frontier of scaling RL 43:09 - Is building AI models a craft or a strict science 48:21 - How AI models generalize across different domains 54:18 - How reinforcement learning cures AI hallucinations 56:04 - Negative generalization and conflicting instructions 58:05 - Can RL scale to law, medicine, and the broader economy? 1:00:19 - The evaluation bottleneck and Model as a Judge 1:04:21 - Continuous AI progress & continual learning 1:08:49 - Will foundation models eat the agent harness 1:11:23 - Why startups should focus on the last mile of AI
1:13:56

Why AI Progress Suddenly Feels Real - my conversation with Yann Dubois, who co-leads the Post-Training Frontiers team at OpenAI 00:00 - Intro 01:30 - Why recent AI progress feels like a step function 04:13 - Model reliability & the emotional rollercoaster of shipping GPT-5.5 07:33 - How OpenAI structures vertical and horizontal teams 09:49 - Improving model efficiency and test-time compute 12:32 - Yann's journey from Switzerland to OpenAI 15:37 - Reasoning in 2026: Real-world utility vs verifiable rewards 18:34 - GPT-5.5 Thinking vs Pro: Scaling test-time compute 20:09 - How reasoning models become more efficient 23:23 - Pre-training scaling and overcoming the data wall 27:03 - Multimodal data, synthetic data, and embodied AI 31:05 - Demystifying mid-training and post-training 37:21 - Does RL create new capabilities in AI? 38:53 - The challenges and frontier of scaling RL 43:09 - Is building AI models a craft or a strict science 48:21 - How AI models generalize across different domains 54:18 - How reinforcement learning cures AI hallucinations 56:04 - Negative generalization and conflicting instructions 58:05 - Can RL scale to law, medicine, and the broader economy? 1:00:19 - The evaluation bottleneck and Model as a Judge 1:04:21 - Continuous AI progress & continual learning 1:08:49 - Will foundation models eat the agent harness 1:11:23 - Why startups should focus on the last mile of AI

Matt Turck

100,966 次观看 • 2 个月前

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.
5:11

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,657 次观看 • 3 年前

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user’s image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models
0:30

Meta announces Movie Gen A Cast of Media Foundation Models We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user’s image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models

AK

62,719 次观看 • 1 年前

Thanksgiving-week treat: an epic conversation on Frontier AI with Lukasz Kaiser -co-author of “Attention Is All You Need” (Transformers) and leading research scientist at OpenAI working on GPT-5.1-era reasoning models. 00:00 – Cold open and intro 01:29 – “AI slowdown” vs a wild week of new frontier models 08:03 – Low-hanging fruit, infra, RL training and better data 11:39 – What is a reasoning model, in plain language 17:02 – Chain-of-thought and training the thinking process with RL 21:39 – Łukasz’s path: from logic and France to Google and Kurzweil 24:20 – Inside the Transformer story and what “attention” really means 28:42 – From Google Brain to OpenAI: culture, scale and GPUs 32:49 – What’s next for pre-training, GPUs and distillation 37:29 – Can we still understand these models? Circuits, sparsity and black boxes 39:42 – GPT-4 → GPT-5 → GPT-5.1: what actually changed 42:40 – Post-training, safety and teaching GPT-5.1 different tones 46:16 – How long should GPT-5.1 think? Reasoning tokens and jagged abilities 47:43 – The five-year-old’s dot puzzle that still breaks frontier models 52:22 – Generalization, child-like learning and whether reasoning is enough 53:48 – Beyond Transformers: ARC, LeCun’s ideas and multimodal bottlenecks 56:10 – GPT-5.1 Codex Max, long-running agents and compaction 1:00:06 – Will foundation models eat most apps? The translation analogy and trust 1:02:34 – What still needs to be solved, and where AI might go next
1:05:25

Thanksgiving-week treat: an epic conversation on Frontier AI with Lukasz Kaiser -co-author of “Attention Is All You Need” (Transformers) and leading research scientist at OpenAI working on GPT-5.1-era reasoning models. 00:00 – Cold open and intro 01:29 – “AI slowdown” vs a wild week of new frontier models 08:03 – Low-hanging fruit, infra, RL training and better data 11:39 – What is a reasoning model, in plain language 17:02 – Chain-of-thought and training the thinking process with RL 21:39 – Łukasz’s path: from logic and France to Google and Kurzweil 24:20 – Inside the Transformer story and what “attention” really means 28:42 – From Google Brain to OpenAI: culture, scale and GPUs 32:49 – What’s next for pre-training, GPUs and distillation 37:29 – Can we still understand these models? Circuits, sparsity and black boxes 39:42 – GPT-4 → GPT-5 → GPT-5.1: what actually changed 42:40 – Post-training, safety and teaching GPT-5.1 different tones 46:16 – How long should GPT-5.1 think? Reasoning tokens and jagged abilities 47:43 – The five-year-old’s dot puzzle that still breaks frontier models 52:22 – Generalization, child-like learning and whether reasoning is enough 53:48 – Beyond Transformers: ARC, LeCun’s ideas and multimodal bottlenecks 56:10 – GPT-5.1 Codex Max, long-running agents and compaction 1:00:06 – Will foundation models eat most apps? The translation analogy and trust 1:02:34 – What still needs to be solved, and where AI might go next

Matt Turck

168,007 次观看 • 8 个月前

A lot of people are calling Hermes Agent the end of OpenClaw. BRUH! It's not... Nous Research trains actual models and they built an agent around that expertise. The local model routing is solid, but the part that matters for your business is that your conversations become fine-tuning data. You can train a model on how you actually work. 00:00 The Problem with Local AI Models 00:25 Introduction to Nous Research 01:04 Cross-Platform Agent Capabilities 01:44 Deep Local Model Integration 02:30 Routing Tasks to Different Models 03:06 Conversations as Training Data 03:50 Hermes Agent vs. OpenClaw 04:15 Future Plans and Series Overview
4:45

A lot of people are calling Hermes Agent the end of OpenClaw. BRUH! It's not... Nous Research trains actual models and they built an agent around that expertise. The local model routing is solid, but the part that matters for your business is that your conversations become fine-tuning data. You can train a model on how you actually work. 00:00 The Problem with Local AI Models 00:25 Introduction to Nous Research 01:04 Cross-Platform Agent Capabilities 01:44 Deep Local Model Integration 02:30 Routing Tasks to Different Models 03:06 Conversations as Training Data 03:50 Hermes Agent vs. OpenClaw 04:15 Future Plans and Series Overview

Ray Fernando

42,398 次观看 • 4 个月前

Really fun to hang again with my friend 🃏 Noam Brown (OpenAI research scientist, our first guest ever on No Priors in early 2023) to talk about the implications of large test-time compute, and what happens when models are given $10M budgets to spend on a single task. Topics: 01:23 – Why Benchmarks Are Broken 04:19 – Compute Budgets and Projections 06:48 – How Long Should Models Think? 08:01 – Benchmarkmaxxing 09:48 – Noam's Evals 12:40 – Safety (When Model Capability Scales With Spend) 16:09 – Implications For the Model Release Cycle 18:34 – Latent Model Capability 22:27 – Limits on Recursive Self-Improvement 28:38 – Large-Scale Multi-Agent Coordination 30:39 – Competition at the Frontier 33:19 – Breaking the Benchmark Grid Equilibrium 34:57 – Why Benchmarks Should be Scaled by Cost
36:18

Really fun to hang again with my friend 🃏 Noam Brown (OpenAI research scientist, our first guest ever on No Priors in early 2023) to talk about the implications of large test-time compute, and what happens when models are given $10M budgets to spend on a single task. Topics: 01:23 – Why Benchmarks Are Broken 04:19 – Compute Budgets and Projections 06:48 – How Long Should Models Think? 08:01 – Benchmarkmaxxing 09:48 – Noam's Evals 12:40 – Safety (When Model Capability Scales With Spend) 16:09 – Implications For the Model Release Cycle 18:34 – Latent Model Capability 22:27 – Limits on Recursive Self-Improvement 28:38 – Large-Scale Multi-Agent Coordination 30:39 – Competition at the Frontier 33:19 – Breaking the Benchmark Grid Equilibrium 34:57 – Why Benchmarks Should be Scaled by Cost

sarah guo

87,850 次观看 • 1 个月前

Today, we're joined by Yejin Choi, professor and senior fellow at Stanford University University in the Computer Science Department and Stanford UniversityHAI. In this conversation, we explore Yejin’s recent work on making small language models reason more effectively. We discuss how high-quality, diverse data plays a central role in closing the intelligence gap between small and large models, and how combining synthetic data generation, imitation learning, and reinforcement learning can unlock stronger reasoning capabilities in smaller models. Yejin explains the risks of homogeneity in model outputs and mode collapse highlighted in her “Artificial Hivemind” paper, and its impacts on human creativity and knowledge. We also discuss her team's novel approaches, including reinforcement learning as a pre-training objective, where models are incentivized to “think” before predicting the next token, and "Prismatic Synthesis," a gradient-based method for generating diverse synthetic math data while filtering overrepresented examples. Additionally, we cover the societal implications of AI and the concept of pluralistic alignment—ensuring AI reflects the diverse norms and values of humanity. Finally, Yejin shares her mission to democratize AI beyond large organizations and offers her predictions for the coming year. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:44 - "Snowball effect" in AI investments 06:58 - Approaches to smaller models 08:58 - Importance of “better data” 14:07 - Imitation learning 18:24 - Artificial Hivemind paper 25:25 - AI risks 27:50 - Spectrum tuning 28:53 - Future of AI on humanity 33:08 - Reasoning in small models 34:58 - Prismatic Synthesis 48:20 - Reinforcement as a Pretraining Objective 55:04 - Pluralistic alignment 1:03:30 - Predictions
1:05:51

Today, we're joined by Yejin Choi, professor and senior fellow at Stanford University University in the Computer Science Department and Stanford UniversityHAI. In this conversation, we explore Yejin’s recent work on making small language models reason more effectively. We discuss how high-quality, diverse data plays a central role in closing the intelligence gap between small and large models, and how combining synthetic data generation, imitation learning, and reinforcement learning can unlock stronger reasoning capabilities in smaller models. Yejin explains the risks of homogeneity in model outputs and mode collapse highlighted in her “Artificial Hivemind” paper, and its impacts on human creativity and knowledge. We also discuss her team's novel approaches, including reinforcement learning as a pre-training objective, where models are incentivized to “think” before predicting the next token, and "Prismatic Synthesis," a gradient-based method for generating diverse synthetic math data while filtering overrepresented examples. Additionally, we cover the societal implications of AI and the concept of pluralistic alignment—ensuring AI reflects the diverse norms and values of humanity. Finally, Yejin shares her mission to democratize AI beyond large organizations and offers her predictions for the coming year. 🗒️ For the full list of resources for this episode, visit the show notes page: 📖 CHAPTERS =============================== 00:00 - Introduction 04:44 - "Snowball effect" in AI investments 06:58 - Approaches to smaller models 08:58 - Importance of “better data” 14:07 - Imitation learning 18:24 - Artificial Hivemind paper 25:25 - AI risks 27:50 - Spectrum tuning 28:53 - Future of AI on humanity 33:08 - Reasoning in small models 34:58 - Prismatic Synthesis 48:20 - Reinforcement as a Pretraining Objective 55:04 - Pluralistic alignment 1:03:30 - Predictions

The TWIML AI Podcast

12,141 次观看 • 6 个月前

François Chollet (François Chollet) on the ARC Prize and how we get to AGI. At AI Startup School in San Francisco. 00:00 - The Falling Cost of Compute 00:57 - Deep-Learning’s Scaling Era & Benchmarks 01:59 - The ARC Benchmark 03:02 - The 2024 Shift to Test-Time Adaptation 05:01 - What Is Intelligence? 07:12 - Why Benchmarks Matter (and Mislead) 08:57 - ARC 1 Exposes Scaling Limits 10:58 - ARC 2: Compositional Reasoning Arrives 12:55 - Humans vs. Models on ARC2 14:58 - Previewing ARC3 & Interactive Agency 17:00 - Kaleidoscopic Hypothesis and Abstractions 22:00 - Type 1 vs. Type 2 Abstractions 26:00 - Discrete Program Search & Inventive AI 29:00 - Fusing Intuition with Symbolic Reasoning 32:00 - Building AGI Through Meta-Learning Systems
34:47

François Chollet (François Chollet) on the ARC Prize and how we get to AGI. At AI Startup School in San Francisco. 00:00 - The Falling Cost of Compute 00:57 - Deep-Learning’s Scaling Era & Benchmarks 01:59 - The ARC Benchmark 03:02 - The 2024 Shift to Test-Time Adaptation 05:01 - What Is Intelligence? 07:12 - Why Benchmarks Matter (and Mislead) 08:57 - ARC 1 Exposes Scaling Limits 10:58 - ARC 2: Compositional Reasoning Arrives 12:55 - Humans vs. Models on ARC2 14:58 - Previewing ARC3 & Interactive Agency 17:00 - Kaleidoscopic Hypothesis and Abstractions 22:00 - Type 1 vs. Type 2 Abstractions 26:00 - Discrete Program Search & Inventive AI 29:00 - Fusing Intuition with Symbolic Reasoning 32:00 - Building AGI Through Meta-Learning Systems

Y Combinator

231,796 次观看 • 1 年前

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.
1:31

SITUATION EXPLAINED: A new generation of AI labs are betting that world models are the path to general intelligence that can interact with the real world. We had General Intuition CEO Pim de Witte on MTS to explain what world models are, and why intuitively world models offer a clearer path towards general intelligence than LLMs. For humans, text is a technology for compressing information about the unfolding, three-dimensional world around us and communicating it to other people. When LLMs reason about the world, they do so by reconstructing the world through text. World models work by modeling the three-dimensional world at the architecture level and then allowing agents to interact with that world. Unlike an LLM, which understands space and time through text, world models perform spatial and temporal reasoning natively. General Intuition hopes to use world models to create embodied AI—machines that can reason and act in the real world. But other companies are also pushing the frontier in this space. Odyssey ML today announced a multi-agent world model, Agora-1. Their launch video shows four participants interacting with a real-time world model simulation of GoldenEye, a first-person shooter for the N64. A playable preview of the GoldenEye simulation is available on their site.

MTS

11,641 次观看 • 2 个月前

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:
0:34

Introducing Reinforcement-Learned Teachers (RLTs): Transforming how we teach LLMs to reason with reinforcement learning (RL). Blog: Paper: Traditional RL focuses on “learning to solve” challenging problems with expensive LLMs and constitutes a key step in making student AI systems ultimately acquire reasoning capabilities via distillation and cold-starting. Enter our RLTs—a new class of models prompted with not only a problem’s question but also its solution, and directly trained to generate clear, step-by-step “explanations” to teach their students. Remarkably, an RLT with only 7B parameters produces superior results when distilling and cold-starting students in competitive and graduate-level reasoning tasks than orders-of-magnitude larger LLMs. RLTs are as effective even when distilling 32B students, much larger than the teacher itself—unlocking a new standard for efficiency in developing reasoning language models with RL. Code:

Sakana AI

179,362 次观看 • 1 年前

Today's AI models train once. We don't work that way. We learn continuously, forget what doesn't matter, and retain what does. That gap is what Dan Biderman and Jessy Lin are closing at Engram. AI that never stops learning, with memory that lives inside the model instead of bolted on as an afterthought. In our latest Training Data episode we get into why memory is the next frontier: why the brain forgets on purpose, why RAG is a band-aid, and what becomes possible when a model is always training. 00:00 Introduction 00:59 Always Training Explained 01:51 Beyond Context Windows 03:29 Ngram Product Overview 04:34 Adapters And Training Signals 05:32 Internalize Vs Externalize 06:49 Compute And Token Savings 08:19 Teams First Then Individuals 08:51 Memorization Vs Understanding 12:47 Dreams And Offline Digestion 14:08 Training Beats Curation 15:19 Why Everyone Needs A Model 21:44 Bitter Lesson And Architecture 24:44 RAG Killer And KV Cache 31:38 Future Of Memory And Models
44:51

Today's AI models train once. We don't work that way. We learn continuously, forget what doesn't matter, and retain what does. That gap is what Dan Biderman and Jessy Lin are closing at Engram. AI that never stops learning, with memory that lives inside the model instead of bolted on as an afterthought. In our latest Training Data episode we get into why memory is the next frontier: why the brain forgets on purpose, why RAG is a band-aid, and what becomes possible when a model is always training. 00:00 Introduction 00:59 Always Training Explained 01:51 Beyond Context Windows 03:29 Ngram Product Overview 04:34 Adapters And Training Signals 05:32 Internalize Vs Externalize 06:49 Compute And Token Savings 08:19 Teams First Then Individuals 08:51 Memorization Vs Understanding 12:47 Dreams And Offline Digestion 14:08 Training Beats Curation 15:19 Why Everyone Needs A Model 21:44 Bitter Lesson And Architecture 24:44 RAG Killer And KV Cache 31:38 Future Of Memory And Models

Sequoia Capital

83,323 次观看 • 1 个月前

Another mindblowing conversation with my good friend .Emad... Enjoy!! 00:00 - Introduction 00:22 - AI: The Biggest Shift in Human History 00:42 - AI’s Impact on Society and the Economy 01:03 - Conversation with Emad Mostaque Begins 01:50 - The Acceleration of AI and Economic Takeoff 03:07 - AI Intelligence: Beyond Human IQ 04:08 - The Rise of AI Chefs and Super Cooks 05:07 - Breaking AI Constraints: Compute and Energy 07:03 - The Future of AI: Ubiquitous Intelligence 08:04 - The Shift to Local AI Models 10:07 - Why Has Apple Lagged in AI? 11:21 - The AI Race: OpenAI, Grok, Gemini, and More 13:11 - China’s Open-Source AI Strategy 14:57 - AI Bias and Ethical Challenges 16:57 - AI’s Cross-Pollination and Memory 18:02 - Are AI Models Becoming Self-Aware? 19:16 - AI, Bitcoin, and Self-Sustaining Algorithms 21:26 - AI-Driven Economies and Autonomous Companies 23:41 - The Future of Labor: A World Without Jobs? 25:26 - AI-Powered Robots: The Next Workforce Revolution 27:28 - The End of Traditional Economic Models 30:27 - The Political Shift: Humanist vs. Transhumanist 33:04 - AI in Financial Markets: The End of Human Traders? 36:03 - The Evolution of Investing in an AI World 38:33 - AI’s Impact on Capital Formation and Business Disruption 40:01 - The Rise of Digital Twins and Post-Capital Society 42:45 - Building AI for Education, Healthcare, and Governance 46:42 - The Future of Money in an AI-Driven World 50:11 - Universal Basic AI: A New Economic Model 54:29 - The Deflationary Impact of AI and Crypto’s Role 57:02 - The AI Singularity: Five Years Until Everything Changes 58:56 - The Road Ahead: AI, Crypto, and the Future of Civilization 01:02:24 - Final Thoughts: The Most Exciting and Terrifying Time in History
1:04:51

Another mindblowing conversation with my good friend .Emad... Enjoy!! 00:00 - Introduction 00:22 - AI: The Biggest Shift in Human History 00:42 - AI’s Impact on Society and the Economy 01:03 - Conversation with Emad Mostaque Begins 01:50 - The Acceleration of AI and Economic Takeoff 03:07 - AI Intelligence: Beyond Human IQ 04:08 - The Rise of AI Chefs and Super Cooks 05:07 - Breaking AI Constraints: Compute and Energy 07:03 - The Future of AI: Ubiquitous Intelligence 08:04 - The Shift to Local AI Models 10:07 - Why Has Apple Lagged in AI? 11:21 - The AI Race: OpenAI, Grok, Gemini, and More 13:11 - China’s Open-Source AI Strategy 14:57 - AI Bias and Ethical Challenges 16:57 - AI’s Cross-Pollination and Memory 18:02 - Are AI Models Becoming Self-Aware? 19:16 - AI, Bitcoin, and Self-Sustaining Algorithms 21:26 - AI-Driven Economies and Autonomous Companies 23:41 - The Future of Labor: A World Without Jobs? 25:26 - AI-Powered Robots: The Next Workforce Revolution 27:28 - The End of Traditional Economic Models 30:27 - The Political Shift: Humanist vs. Transhumanist 33:04 - AI in Financial Markets: The End of Human Traders? 36:03 - The Evolution of Investing in an AI World 38:33 - AI’s Impact on Capital Formation and Business Disruption 40:01 - The Rise of Digital Twins and Post-Capital Society 42:45 - Building AI for Education, Healthcare, and Governance 46:42 - The Future of Money in an AI-Driven World 50:11 - Universal Basic AI: A New Economic Model 54:29 - The Deflationary Impact of AI and Crypto’s Role 57:02 - The AI Singularity: Five Years Until Everything Changes 58:56 - The Road Ahead: AI, Crypto, and the Future of Civilization 01:02:24 - Final Thoughts: The Most Exciting and Terrifying Time in History

Raoul Pal

326,827 次观看 • 1 年前