Loading video...

Video Failed to Load

Go Home

When is harness optimization enough? When does post-training make sense? What will determine who becomes the new AI hyperscaler? Yash Patil, co-founder of Applied Compute, was the perfect person to discuss this and more. Yash worked on Codex at OpenAI before leaving to co-found Applied Compute with fellow OpenAI...

jacobeffron's profile picture

Jacob Effron

4,867 subscribers

21,237 views • 2 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

2 Comments

Yash Patil's profile picture
Yash Patil2 days ago

@appliedcompute Thank you so much for having me @jacobeffron!

Jacob Effron's profile picture
Jacob Effron2 days ago

@appliedcompute Really enjoyed our conversation!

Related Videos

"A modelless company is sitting on shifting sand." Yash Patil (Yash Patil) is the founder and CEO of Applied Compute, a company that trains custom models on company data and serves them in production. His conviction: every organization has its own definition of what good looks like, and a company that doesn't own its model is one system card away from finding out what it can no longer do. (0:00) Introduction (3:50) Betting on custom AI models (12:30) Yash's early influences and first projects (19:29) Inside OpenAI during Sam Altman's firing (28:18) What Yash admires about Sam Altman (29:43) Teaching models to reason (35:39) The core insight behind Applied Compute (45:55) Why model training never ends (51:25) The culture and people of Applied Compute (1:03:48) Final meditations Thank you to the partners who make this possible Brex: The intelligent finance platform. Guru_HQ: The AI source of truth for work. Persona: Trusted identity verification for any use case.
1:08:05

"A modelless company is sitting on shifting sand." Yash Patil (Yash Patil) is the founder and CEO of Applied Compute, a company that trains custom models on company data and serves them in production. His conviction: every organization has its own definition of what good looks like, and a company that doesn't own its model is one system card away from finding out what it can no longer do. (0:00) Introduction (3:50) Betting on custom AI models (12:30) Yash's early influences and first projects (19:29) Inside OpenAI during Sam Altman's firing (28:18) What Yash admires about Sam Altman (29:43) Teaching models to reason (35:39) The core insight behind Applied Compute (45:55) Why model training never ends (51:25) The culture and people of Applied Compute (1:03:48) Final meditations Thank you to the partners who make this possible Brex: The intelligent finance platform. Guru_HQ: The AI source of truth for work. Persona: Trusted identity verification for any use case.

Mario Gabriele

105,446 views • 3 months ago

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

101,314 views • 4 months ago

RL is a powerful mechanism for training company-specific models on their unique work and data. This is what we do at Applied Compute. A key challenge is how to make RL efficient, because we need runs to be fast (delivered in days), cheap (scalable unit economics), and predictable (not just fast, but reliably fast). Here are some takeaways: • Synchronous RL is wasteful with time and compute. • Asynchronous RL is more efficient but introduces staleness, which causes learning instabilities. • Modeling and simulations can help analytically solve for what configuration leads to optimal efficiency. This allows us to rapidly prototype training configurations, without burning expensive compute cycles on trial runs. Two of our co-founders, Rhythm Garg and Linden Li, discussed some of this research at AI Engineer recently, with a focus on the following subproblem: what is the highest throughput way to do RL given a maximum staleness and compute budget?
20:12

RL is a powerful mechanism for training company-specific models on their unique work and data. This is what we do at Applied Compute. A key challenge is how to make RL efficient, because we need runs to be fast (delivered in days), cheap (scalable unit economics), and predictable (not just fast, but reliably fast). Here are some takeaways: • Synchronous RL is wasteful with time and compute. • Asynchronous RL is more efficient but introduces staleness, which causes learning instabilities. • Modeling and simulations can help analytically solve for what configuration leads to optimal efficiency. This allows us to rapidly prototype training configurations, without burning expensive compute cycles on trial runs. Two of our co-founders, Rhythm Garg and Linden Li, discussed some of this research at AI Engineer recently, with a focus on the following subproblem: what is the highest throughput way to do RL given a maximum staleness and compute budget?

Applied Compute

45,652 views • 10 months ago

BG2. Ep 17. Double $NVDA! System Level Comp Moat, “Insane Demand”, Inference Explosion 1 B x, Memphis Supercluster, OpenAI, & more. Brad Gerstner Clark Tang Bill Gurley (00:00) Intro (1:50) The Evolution of AGI and Personal Assistants (06:03) NVIDIA's Competitive Moat (15:51 ) The Future of Inference and Training in AI (19:01) Building the AI Infrastructure (31:35) Inventing a New Market in an AI Future (38:40) The Impact of OpenAI (43:25) The Future of AI Models (46.44) and Memphis Supercluster (51:21) Distributed Computing and Inference Scaling (55:54) Inference Time Reasoning and Its Importance (01:00:46) AI's Role in Growing Business and Improving Productivity (01:08:00) Ensuring Safe AI Development (01:12:31) The Balance of Open Source and Closed Source AI
1:21:13

BG2. Ep 17. Double $NVDA! System Level Comp Moat, “Insane Demand”, Inference Explosion 1 B x, Memphis Supercluster, OpenAI, & more. Brad Gerstner Clark Tang Bill Gurley (00:00) Intro (1:50) The Evolution of AGI and Personal Assistants (06:03) NVIDIA's Competitive Moat (15:51 ) The Future of Inference and Training in AI (19:01) Building the AI Infrastructure (31:35) Inventing a New Market in an AI Future (38:40) The Impact of OpenAI (43:25) The Future of AI Models (46.44) and Memphis Supercluster (51:21) Distributed Computing and Inference Scaling (55:54) Inference Time Reasoning and Its Importance (01:00:46) AI's Role in Growing Business and Improving Productivity (01:08:00) Ensuring Safe AI Development (01:12:31) The Balance of Open Source and Closed Source AI

Bg2 Pod

488,753 views • 2 years ago

My interview with Greg Brockman (Greg Brockman), Cofounder and President of OpenAI. 0:00 Intro 1:06 Scaling Sora 2:18 Are transformer models the future? 4:29 Building with AMD 5:50 Other kinds of compute 7:28 Bottlenecks 9:17 Deciding where to invest 11:38 Decoupling of the internet 16:29 Why ChatGPT is different 17:59 Proactive AI 19:39 Compressing Intelligence 20:48 ChatGPT’s Longest Thought Ever 21:13 Sora 2 29:47 Is my job in danger? 31:51 Building on top of OpenAI 34:11 Humans in the loop 35:36 Fully generated software 39:25 Agentic Commerce Protocol 40:41 What does 2026 look like? 42:43 AGI
43:44

My interview with Greg Brockman (Greg Brockman), Cofounder and President of OpenAI. 0:00 Intro 1:06 Scaling Sora 2:18 Are transformer models the future? 4:29 Building with AMD 5:50 Other kinds of compute 7:28 Bottlenecks 9:17 Deciding where to invest 11:38 Decoupling of the internet 16:29 Why ChatGPT is different 17:59 Proactive AI 19:39 Compressing Intelligence 20:48 ChatGPT’s Longest Thought Ever 21:13 Sora 2 29:47 Is my job in danger? 31:51 Building on top of OpenAI 34:11 Humans in the loop 35:36 Fully generated software 39:25 Agentic Commerce Protocol 40:41 What does 2026 look like? 42:43 AGI

Matthew Berman

45,086 views • 1 year ago

Enterprise AI deployments today are frozen in time. Model capabilities stagnate in production. The problem compounds because companies aren’t static either. Every time your company improves, the model falls further behind. The bottleneck is continual learning. How does a model do something once and improve from feedback? The future of enterprise AI is Specific Intelligence: custom models teams own, trained on a company’s choices, interaction by interaction, using internal knowledge general models cannot access. Applied Compute helps companies train, serve, own, and improve custom models. Thanks Apoorv Agrawal for having Yash Patil at MS&E 435 to talk about the future of model training.
2:16

Enterprise AI deployments today are frozen in time. Model capabilities stagnate in production. The problem compounds because companies aren’t static either. Every time your company improves, the model falls further behind. The bottleneck is continual learning. How does a model do something once and improve from feedback? The future of enterprise AI is Specific Intelligence: custom models teams own, trained on a company’s choices, interaction by interaction, using internal knowledge general models cannot access. Applied Compute helps companies train, serve, own, and improve custom models. Thanks Apoorv Agrawal for having Yash Patil at MS&E 435 to talk about the future of model training.

Applied Compute

12,871 views • 4 months ago

Much of the AI narrative revolves around architecture research, compute scaling & buying human data. Very few understand the deep technical discipline of "data research," which has driven many of the gains in model capabilities. Vivek Gopalan sits down with Mahesh Sathiamoorthy @ COLM2026 & Alex Dimakis, founders of Bespoke Labs, a company defining the category of data research. (00:00) Introducing Mahesh and Alex (03:40) Teaching a 1000 person ML class at Berkeley / changes in CS education in the age of AI (06:10) Open source data for frontier model training, OpenThoughts & training models for data curation (12:00) Why multiple-answer yields more performant models, benefits of keeping unverifiable examples in datasets (17:20) RL scaling laws / introduction to Bespoke (19:45) "Environment-driven Development" (28:35) New capabilities in frontier models & coding agents (34:30) Market outlook for RL environments (42:30) Exciting recent research and how we arrived at today's state of RL (50:00) Bespoke's Series A
51:14

Much of the AI narrative revolves around architecture research, compute scaling & buying human data. Very few understand the deep technical discipline of "data research," which has driven many of the gains in model capabilities. Vivek Gopalan sits down with Mahesh Sathiamoorthy @ COLM2026 & Alex Dimakis, founders of Bespoke Labs, a company defining the category of data research. (00:00) Introducing Mahesh and Alex (03:40) Teaching a 1000 person ML class at Berkeley / changes in CS education in the age of AI (06:10) Open source data for frontier model training, OpenThoughts & training models for data curation (12:00) Why multiple-answer yields more performant models, benefits of keeping unverifiable examples in datasets (17:20) RL scaling laws / introduction to Bespoke (19:45) "Environment-driven Development" (28:35) New capabilities in frontier models & coding agents (34:30) Market outlook for RL environments (42:30) Exciting recent research and how we arrived at today's state of RL (50:00) Bespoke's Series A

8VC

48,451 views • 3 months ago

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

84,809 views • 3 months ago

When should you start post-training your own models? Fireworks CEO Lin Qiao’s answer: after product-market fit. Not because it's hard... but because only after PMF is the data coming off your product surface worth training on. Lin joined us for our Sequoia Capital "Own Your Intelligence" event to host a workshop on all things post-training; what works, what breaks, and how not to let the model outsmart you. Must listen!! 00:00 Introduction 00:37 What Fireworks sees across thousands of AI applications 02:47 Off-the-shelf APIs and the problem of keeping your taste 03:58 What "owning your intelligence" actually means 05:43 The progression: prompting → RAG → SFT → preferences → RL 07:20 Why this mirrors how humans learn 09:03 Matching the technique to the problem you actually have 10:46 Where teams get stuck: data quality and vibe evals 12:28 Reward hacking: the model that wrote zero lines of code 13:59 Training-to-serving alignment (and why quality drops) 15:55 Post-training in healthcare and security 17:31 From coding to every co-work domain 19:35 Incumbents, cost burden, and not scaling into bankruptcy 21:26 How much control do you want? 23:24 Q&A: What makes a good reward signal 25:00 Q&A: When to start thinking about post-training
28:28

When should you start post-training your own models? Fireworks CEO Lin Qiao’s answer: after product-market fit. Not because it's hard... but because only after PMF is the data coming off your product surface worth training on. Lin joined us for our Sequoia Capital "Own Your Intelligence" event to host a workshop on all things post-training; what works, what breaks, and how not to let the model outsmart you. Must listen!! 00:00 Introduction 00:37 What Fireworks sees across thousands of AI applications 02:47 Off-the-shelf APIs and the problem of keeping your taste 03:58 What "owning your intelligence" actually means 05:43 The progression: prompting → RAG → SFT → preferences → RL 07:20 Why this mirrors how humans learn 09:03 Matching the technique to the problem you actually have 10:46 Where teams get stuck: data quality and vibe evals 12:28 Reward hacking: the model that wrote zero lines of code 13:59 Training-to-serving alignment (and why quality drops) 15:55 Post-training in healthcare and security 17:31 From coding to every co-work domain 19:35 Incumbents, cost burden, and not scaling into bankruptcy 21:26 How much control do you want? 23:24 Q&A: What makes a good reward signal 25:00 Q&A: When to start thinking about post-training

Sonya Huang 🐥

28,212 views • 1 month ago

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?
26:21

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?

Pat Grady

66,691 views • 1 month ago

At OpenAI, Chief Scientist Jakub Pachocki helps lead the research roadmap to AGI including a research intern-level AI system by September 2026 and a fully automated AI researcher by March 2028. I sat down with Jakub to check on those timelines and ask him all of my top-of-mind AI questions including: ▪️ How OpenAI thinks about extending RL beyond code and math ▪️ The current state of alignment research as more powerful models loom ▪️ The future of continual learning ▪️ How startups should think about building their own models/harnesses And he also shared some great stories around OpenAI’s pioneering work on math. YouTube: Spotify: Apple: 0:00 Intro 1:53 Research Intern Capability Timelines 4:59 Math Breakthroughs 7:59 RL Beyond Verifiable Tasks 12:32 RL vs In-Context 19:01 Allocating Compute Internally 28:18 AI for Science 31:40 Pattern Matching 33:23 Solving the Hardest Math Problems 37:40 Chain of Thought Monitoring 44:33 Generalization and Value Alignment in Models 47:57 Inside OpenAI 51:55 Quickfire
58:45

At OpenAI, Chief Scientist Jakub Pachocki helps lead the research roadmap to AGI including a research intern-level AI system by September 2026 and a fully automated AI researcher by March 2028. I sat down with Jakub to check on those timelines and ask him all of my top-of-mind AI questions including: ▪️ How OpenAI thinks about extending RL beyond code and math ▪️ The current state of alignment research as more powerful models loom ▪️ The future of continual learning ▪️ How startups should think about building their own models/harnesses And he also shared some great stories around OpenAI’s pioneering work on math. YouTube: Spotify: Apple: 0:00 Intro 1:53 Research Intern Capability Timelines 4:59 Math Breakthroughs 7:59 RL Beyond Verifiable Tasks 12:32 RL vs In-Context 19:01 Allocating Compute Internally 28:18 AI for Science 31:40 Pattern Matching 33:23 Solving the Hardest Math Problems 37:40 Chain of Thought Monitoring 44:33 Generalization and Value Alignment in Models 47:57 Inside OpenAI 51:55 Quickfire

Jacob Effron

138,504 views • 6 months ago

I sat down with Silas Alberti, Head of Research Cognition, to chat about the intersection of RL and inference -- from training frontier coding models to running inference at scale. Watch till the end for bonus doggo! :o 0:00 — Intros 1:04 — What's hardest to get right in an RL run 3:39 — How Cognition started using Modal 4:03 — What to weigh when buying inference 4:58 — The latency/throughput Pareto frontier 7:14 — DFlash reveal (!!) 8:44 — Why faster runtime matters 9:56 — Memory-bound vs. compute-bound 10:57 — Tree-based speculation 14:20 — Hot take: RL and inference optimization converging 15:28 — Online training of the speculator 16:22 — "Auto inference" 17:27 — Agents competing on optimization problems 18:27 — What inference providers still get wrong
19:36

I sat down with Silas Alberti, Head of Research Cognition, to chat about the intersection of RL and inference -- from training frontier coding models to running inference at scale. Watch till the end for bonus doggo! :o 0:00 — Intros 1:04 — What's hardest to get right in an RL run 3:39 — How Cognition started using Modal 4:03 — What to weigh when buying inference 4:58 — The latency/throughput Pareto frontier 7:14 — DFlash reveal (!!) 8:44 — Why faster runtime matters 9:56 — Memory-bound vs. compute-bound 10:57 — Tree-based speculation 14:20 — Hot take: RL and inference optimization converging 15:28 — Online training of the speculator 16:22 — "Auto inference" 17:27 — Agents competing on optimization problems 18:27 — What inference providers still get wrong

gongy

82,022 views • 2 months ago

Why AI Can Now Make Discoveries - my conversation with Dan Roberts, Lead of the Foundations of Reinforcement Learning team at OpenAI 00:00 Intro: AI's wild week in mathematics 01:21 What OpenAI's Foundations of RL team does 03:08 Dan's journey: from black holes and quantum gravity to frontier AI 07:04 Are AI systems becoming useful for real science 08:21 The AI math moment: Erdős, OpenAI, DeepMind, and Anthropic 08:52 Why the OpenAI result was an act of exploration 10:25 OpenAI vs. DeepMind: informal reasoning vs. formal proof 12:13 RL 101: learning by doing, not just watching 15:10 Why reinforcement learning works 15:58 How RL breaks: sparse feedback and long-horizon tasks 17:03 RLHF: how human feedback shaped early language models 18:48 Move 37, self-play, and the search for novel strategies 22:16 Explore vs. exploit in scientific discovery 24:49 Why RL may now be "the cake," not the cherry on top 25:46 Why RL started working with large language models 27:29 Is RL "sucking supervision through a straw"? 28:47 Why language may be the grounding layer for intelligence 31:46 A contrarian take on the Bitter Lesson 32:41 What test-time compute actually is 34:50 How RL gives models the ability to think 35:40 Verifiable rewards, math, coding, and the messy real world 38:00 What physics can teach us about AI 42:08 Is there a thermodynamics of AI? 43:08 From Erdős problems to Einstein-level AI 45:16 Is AI already doing original science? 45:51 How far are we from AI automating AI research 47:41 Why Dan is excited about the future of science
49:06

Why AI Can Now Make Discoveries - my conversation with Dan Roberts, Lead of the Foundations of Reinforcement Learning team at OpenAI 00:00 Intro: AI's wild week in mathematics 01:21 What OpenAI's Foundations of RL team does 03:08 Dan's journey: from black holes and quantum gravity to frontier AI 07:04 Are AI systems becoming useful for real science 08:21 The AI math moment: Erdős, OpenAI, DeepMind, and Anthropic 08:52 Why the OpenAI result was an act of exploration 10:25 OpenAI vs. DeepMind: informal reasoning vs. formal proof 12:13 RL 101: learning by doing, not just watching 15:10 Why reinforcement learning works 15:58 How RL breaks: sparse feedback and long-horizon tasks 17:03 RLHF: how human feedback shaped early language models 18:48 Move 37, self-play, and the search for novel strategies 22:16 Explore vs. exploit in scientific discovery 24:49 Why RL may now be "the cake," not the cherry on top 25:46 Why RL started working with large language models 27:29 Is RL "sucking supervision through a straw"? 28:47 Why language may be the grounding layer for intelligence 31:46 A contrarian take on the Bitter Lesson 32:41 What test-time compute actually is 34:50 How RL gives models the ability to think 35:40 Verifiable rewards, math, coding, and the messy real world 38:00 What physics can teach us about AI 42:08 Is there a thermodynamics of AI? 43:08 From Erdős problems to Einstein-level AI 45:16 Is AI already doing original science? 45:51 How far are we from AI automating AI research 47:41 Why Dan is excited about the future of science

Matt Turck

69,801 views • 4 months ago

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

168,186 views • 10 months ago

My conversation with OpenAI co-founder Greg Brockman This is the most detailed first-person account of the 72 hours after Sam Altman was fired. We also go deep on what comes next: the global race to AGI, why ChatGPT stopped showing reasoning, how much of OpenAI's own code is now written by AI ("it's hard to know what percent is not"), and the untold story of how OpenAI actually started in 2015. 00:00:00 Introduction 00:00:49 Meeting Sam Altman and Starting OpenAI 00:02:40 Building the Founding Team 00:04:25 DeepMind's Lead Over OpenAI 00:04:54 Changing OpenAI to a For-Profit Model 00:06:05 Breakthrough Moments at OpenAI 00:08:22 What Dota 2 Meant for OpenAI 00:10:04 Reasoning Versus Prediction 00:11:59 Tensions Grow at OpenAI 00:15:44 Sam Altman's Firing 00:17:49 Greg Quits OpenAI 00:19:56 Sam Explores Deal with Microsoft's Satya 00:20:28 Petition for Altman's Return 00:23:43 Ilya Sutskever Leaves OpenAI 00:24:59 Lessons Learned after Sam Ousting 00:28:22 The Thing Ilya Said that Greg Can't Forget 00:32:22 Is AI Going Parabolic? 00:33:24 How Much of OpenAI's Code is Written by AI? 00:36:21 Do AI Chatbots Tell Us What We Want to Hear? 00:38:06 The Global AI Race to Reach AGI 00:38:40 What Happens if US Doesn't Reach AGI First? 00:39:49 Are Countries Stealing AI Advancements? 00:40:38 Why ChatGPT No Longer Shows Reasoning 00:41:47 The Finite Constraints of Compute 00:43:38 On Investing Early in Data Centers 00:46:31 The Future of Data Center Specialization 00:47:52 How to Decide Whose Queries to Serve 00:49:08 OpenAI on Consumer vs Enterprise Models 00:53:05 Data Centers in Space? 01:00:56 What Should AI Regulation Look Like? 01:04:33 The Future of AI-Powered Entrepreneurship 01:04:44 AI and Job Loss 01:07:15 The Skills Young People Should Invest In 01:11:30 What Does Success Look Like For You? Full episode on X below. Also find it on: • YouTube: • Spotify: • Apple:
1:11:41

My conversation with OpenAI co-founder Greg Brockman This is the most detailed first-person account of the 72 hours after Sam Altman was fired. We also go deep on what comes next: the global race to AGI, why ChatGPT stopped showing reasoning, how much of OpenAI's own code is now written by AI ("it's hard to know what percent is not"), and the untold story of how OpenAI actually started in 2015. 00:00:00 Introduction 00:00:49 Meeting Sam Altman and Starting OpenAI 00:02:40 Building the Founding Team 00:04:25 DeepMind's Lead Over OpenAI 00:04:54 Changing OpenAI to a For-Profit Model 00:06:05 Breakthrough Moments at OpenAI 00:08:22 What Dota 2 Meant for OpenAI 00:10:04 Reasoning Versus Prediction 00:11:59 Tensions Grow at OpenAI 00:15:44 Sam Altman's Firing 00:17:49 Greg Quits OpenAI 00:19:56 Sam Explores Deal with Microsoft's Satya 00:20:28 Petition for Altman's Return 00:23:43 Ilya Sutskever Leaves OpenAI 00:24:59 Lessons Learned after Sam Ousting 00:28:22 The Thing Ilya Said that Greg Can't Forget 00:32:22 Is AI Going Parabolic? 00:33:24 How Much of OpenAI's Code is Written by AI? 00:36:21 Do AI Chatbots Tell Us What We Want to Hear? 00:38:06 The Global AI Race to Reach AGI 00:38:40 What Happens if US Doesn't Reach AGI First? 00:39:49 Are Countries Stealing AI Advancements? 00:40:38 Why ChatGPT No Longer Shows Reasoning 00:41:47 The Finite Constraints of Compute 00:43:38 On Investing Early in Data Centers 00:46:31 The Future of Data Center Specialization 00:47:52 How to Decide Whose Queries to Serve 00:49:08 OpenAI on Consumer vs Enterprise Models 00:53:05 Data Centers in Space? 01:00:56 What Should AI Regulation Look Like? 01:04:33 The Future of AI-Powered Entrepreneurship 01:04:44 AI and Job Loss 01:07:15 The Skills Young People Should Invest In 01:11:30 What Does Success Look Like For You? Full episode on X below. Also find it on: • YouTube: • Spotify: • Apple:

Shane Parrish

450,952 views • 5 months ago

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.
1:05

Today we're announcing Base Labs, a dedicated research organization focused on advancing open-source AI. We believe in a healthy, open frontier model ecosystem. To enable this, we are working on: - Blue-sky research on continual learning, the science of RL, and how models learn across their full lifecycle, with every experiment and recipe shared openly. - The BaseHub Data Foundry: the highest-quality open RL environments, training data, and real-world benchmarks, built for anyone to train and benchmark on. - Post-post training: taking open-source models and making them better, safer, and more aligned through continual post-training, built on our research, and deployed with our frontier safety stack so organizations can use open-source models with confidence. - Making models cheaper and more performant through our model performance research. This is a mission-driven research effort, not a commercial product. We believe the health of the open-source AI ecosystem matters and that the best way to advance it is to do science in the open. We’re hiring engineers, researchers, and research fellows to advance this mission.

Base Labs

243,522 views • 1 month ago

Here's my conversation with Lucas Atkins and the team at Arcee.ai on their path to training and releasing Trinity Large today. From going all in on open models built end to end in the US 6 months ago to having the model in hand is no easy feet. I loved this conversation on how to design a startup around open models and take a bold step to scale it up. I'm openly an Arcee fan, watching them take risk and pull it off. We discuss: - The state (and future) of open vs. closed models, - The business of selling open models for on-prem deployments, - The story of Arcee AI & going “all-in” on this training run, - The ATOM project, - Building frontier model training teams in 6 months, - and other great topics. I really loved this one, and think you well too. Chapters: 00:00:00 Intro: Arcee AI, Trinity Models & Trinity Large 00:08:26 Transitioning a Company to Pre-training 00:13:00 Technical Decisions: Muon and MoE 00:18:41 Scaling and MoE Training Pain 00:23:14 Post-training and RL Strategies 00:28:09 Team Structure and Data Scaling 00:31:31 The Trinity Manifesto: US Open Weights 00:42:31 Specialized Models and Distillation 00:47:12 Infrastructure and Hosting 400B 00:50:53 Open Source as a Business Moat 00:56:31 Predictions: Best Model in 2026 01:02:29 Lightning Round & Conclusions More great open model builder podcasts coming soon!
1:12:15

Here's my conversation with Lucas Atkins and the team at Arcee.ai on their path to training and releasing Trinity Large today. From going all in on open models built end to end in the US 6 months ago to having the model in hand is no easy feet. I loved this conversation on how to design a startup around open models and take a bold step to scale it up. I'm openly an Arcee fan, watching them take risk and pull it off. We discuss: - The state (and future) of open vs. closed models, - The business of selling open models for on-prem deployments, - The story of Arcee AI & going “all-in” on this training run, - The ATOM project, - Building frontier model training teams in 6 months, - and other great topics. I really loved this one, and think you well too. Chapters: 00:00:00 Intro: Arcee AI, Trinity Models & Trinity Large 00:08:26 Transitioning a Company to Pre-training 00:13:00 Technical Decisions: Muon and MoE 00:18:41 Scaling and MoE Training Pain 00:23:14 Post-training and RL Strategies 00:28:09 Team Structure and Data Scaling 00:31:31 The Trinity Manifesto: US Open Weights 00:42:31 Specialized Models and Distillation 00:47:12 Infrastructure and Hosting 400B 00:50:53 Open Source as a Business Moat 00:56:31 Predictions: Best Model in 2026 01:02:29 Lightning Round & Conclusions More great open model builder podcasts coming soon!

Nathan Lambert

26,872 views • 8 months ago

A conversation with John Schulman on the first year LLMs could have been useful, building research teams, and where RL goes from here. 00:20 - Speedrunning ChatGPT 09:22 - Archetypes of research managers 11:56 - Was OpenAI inspired by Bell Labs? 16:54 - The absence of value functions 18:23 - Continual learning 21:09 - Brittle generalization 24:05 - Co-training generators and verifiers, GANs 27:06 - John’s personal use of AI for research 28:54 - Day in the life 33:01 - Slowdowns in consequential ML ideas 36:21 - "Peer review" within the labs 39:19 - Distribution shift in researchers 43:33 - Future of RL 45:33 - Will the labs coordinate if the world needs them to? 44:46 - Forecasting ills in AGI and engineering 47:53 - Thinking Machines
51:25

A conversation with John Schulman on the first year LLMs could have been useful, building research teams, and where RL goes from here. 00:20 - Speedrunning ChatGPT 09:22 - Archetypes of research managers 11:56 - Was OpenAI inspired by Bell Labs? 16:54 - The absence of value functions 18:23 - Continual learning 21:09 - Brittle generalization 24:05 - Co-training generators and verifiers, GANs 27:06 - John’s personal use of AI for research 28:54 - Day in the life 33:01 - Slowdowns in consequential ML ideas 36:21 - "Peer review" within the labs 39:19 - Distribution shift in researchers 43:33 - Future of RL 45:33 - Will the labs coordinate if the world needs them to? 44:46 - Forecasting ills in AGI and engineering 47:53 - Thinking Machines

Michael Truell

600,553 views • 9 months ago