[AIEWF Preview] Containing Agent Chaos — Solomon Hykes

Solving Poker and Diplomacy, Debating RL+Reasoning with Ilya, what's *wrong* with the System 1/2 analogy, and where Test-Time Compute hits a wall Timestamps 00:00 Intro – Diplomacy, Cicero & World Championship 02:00 Reverse Centaur: How AI Improved Noam’s Human Play 05:00 Turing Test Failures in Chat: Hallucinations & Steerability 07:30 Reasoning Models & Fast vs. Slow Thinking Paradigm 11:00 System 1 vs. System 2 in Visual Tasks (GeoGuessr, Tic-Tac-Toe) 14:00 The Deep Research Existence Proof for Unverifiable Domains 17:30 Harnesses, Tool Use, and Fragility in AI Agents 21:00 The Case Against Over-Reliance on Scaffolds and Routers 24:00 Reinforcement Fine-Tuning and Long-Term Model Adaptability 28:00 Ilya’s Bet on Reasoning and the O-Series Breakthrough 34:00 Noam’s Dev Stack: Codex, Windsurf & AGI Moments 38:00 Building Better AI Developers: Memory, Reuse, and PR Reviews 41:00 Multi-Agent Intelligence and the “AI Civilization” Hypothesis 44:30 Implicit World Models and Theory of Mind Through Scaling 48:00 Why Self-Play Breaks Down Beyond Go and Chess 54:00 Designing Better Benchmarks for Fuzzy Tasks 57:30 The Real Limits of Test-Time Compute: Cost vs. Time 1:00:30 Data Efficiency Gaps Between Humans and LLMs 1:03:00 Training Pipeline: Pretraining, Midtraining, Posttraining 1:05:00 Games as Research Proving Grounds: Poker, MTG, Stratego 1:10:00 Closing Thoughts – Five-Year View and Open Research Directions Chapters 00:00:00 Intro & Guest Welcome 00:00:33 Diplomacy AI & Cicero Insights 00:03:49 AI Safety, Language Models, and Steerability 00:05:23 O Series Models: Progress and Benchmarks 00:08:53 Reasoning Paradigm: Thinking Fast and Slow in AI 00:14:02 Design Questions: Harnesses, Tools, and Test Time Compute 00:20:32 Reinforcement Fine-tuning & Model Specialization 00:21:52 The Rise of Reasoning Models at OpenAI 00:29:33 Data Efficiency in Machine Learning 00:33:21 Coding & AI: Codex, Workflows, and Developer Experience 00:41:38 Multi-Agent AI: Collaboration, Competition, and Civilization 00:45:14 Poker, Diplomacy & Exploitative vs. Optimal AI Strategy 00:52:11 World Models, Multi-Agent Learning, and Self-Play 00:58:50 Generative Media: Image & Video Models 01:00:44 Robotics: Humanoids, Iteration Speed, and Embodiment 01:04:25 Rapid Fire: Research Practices, Benchmarks, and AI Progress 01:14:19 Games, Imperfect Information, and AI Research Directions

Chris Lattner of Modular (https://modular.com) joined us (again!) to talk about how they are breaking the CUDA monopoly, what it took to match NVIDIA performance with AMD, and how they are building a company of "elite nerds". X: https://x.com/latentspacepod Substack: https://latent.space 00:00:00 Introductions 00:00:12 Overview of Modular and the Shape of Compute 00:02:27 Modular’s R&D Phase 00:06:55 From CPU Optimization to GPU Support 00:11:14 MAX: Modular’s Inference Framework 00:12:52 Mojo Programming Language 00:18:25 MAX Architecture: From Mojo to Cluster-Scale Inference 00:29:16 Open Source Contributions and Community Involvement 00:32:25 Modular's Differentiation from VLLM and SGLang 00:41:37 Modular’s Business Model and Monetization Strategy 00:53:17 DeepSeek’s Impact and Low-Level GPU Programming 01:00:00 Inference Time Compute and Reasoning Models 01:02:31 Personal Reflections on Leading Modular 01:08:27 Daily Routine and Time Management as a Founder 01:13:24 Using AI Coding Tools and Staying Current with Research 01:14:47 Personal Projects and Work-Life Balance 01:17:05 Hiring, Open Source, and Community Engagement

Emmanuel Amiesen is lead author of “Circuit Tracing: Revealing Computational Graphs in Language Models” (https://transformer-circuits.pub/2025/attribution-graphs/methods.html ), which is part of a duo of MechInterp papers that Anthropic published in March (alongside https://transformer-circuits.pub/2025/attribution-graphs/biology.html ). We recorded the initial conversation a month ago, but then held off publishing until the open source tooling for the graph generation discussed in this work was released last week: https://www.anthropic.com/research/open-source-circuit-tracing This is a 2 part episode - an intro covering the open source release, then a deeper dive into the paper — with guest host Vibhu Sapra (https://x.com/vibhuuuus ) and Mochi the MechInterp Pomsky (https://x.com/mochipomsky ). Thanks to Vibhu for making this episode happen! While the original blogpost contained some fantastic guided visualizations (which we discuss at the end of this pod!), with the notebook and Neuronpedia visualization (https://www.neuronpedia.org/gemma-2-2b/graph ) released this week, you can now explore on your own with Neuronpedia, as we show you in the video version of this pod. Chapters 00:00 Intro & Guest Introductions 01:00 Anthropic's Circuit Tracing Release 06:11 Exploring Circuit Tracing Tools & Demos 13:01 Model Behaviors and User Experiments 17:02 Behind the Research: Team and Community 24:19 Main Episode Start: Mech Interp Backgrounds 25:56 Getting Into Mech Interp Research 31:52 History and Foundations of Mech Interp 37:05 Core Concepts: Superposition & Features 39:54 Applications & Interventions in Models 45:59 Challenges & Open Questions in Interpretability 57:15 Understanding Model Mechanisms: Circuits & Reasoning 01:04:24 Model Planning, Reasoning, and Attribution Graphs 01:30:52 Faithfulness, Deception, and Parallel Circuits 01:40:16 Publishing Risks, Open Research, and Visualization 01:49:33 Barriers, Vision, and Call to Action

Solomon most famously created Docker and now runs Dagger… which has something special to share with you on Thursday. Catch Dagger at: - Tuesday: Dagger’s workshop https://www.ai.engineer/schedule#ship-agents-that-ship-a-hands-on-workshop-for-swe-agent-builders - Wednesday: Dagger’s talk: https://www.ai.engineer/schedule#how-to-trust-an-agent-with-software-delivery - Thursday: Solomon’s Keynote https://www.ai.engineer/schedule#containing-agent-chaos Chapters 00:00 Introduction & Guest Background 00:29 What is Dagger? Post-Development Automation 01:08 Dagger’s Community & Platform Engineers 02:32 AI Agents and Developer Workflows 03:40 Environment Isolation & The Power of Containers 06:28 The Need for Standards in Agent Environments 07:25 Design Constraints & Challenges for Dev Environments 11:26 Limitations of Current Tools & Agent-Native UX 14:11 Modularity, Customization, and the Lego Analogy 16:24 Convergence of CICD and Agentic Systems 17:41 Ephemeral Apps, Resource Constraints, and Local Execution 21:01 Adoption, Ecosystem, and the Role of Open Source 23:30 Dagger’s Modular Approach & Integration Philosophy 25:38 Looking Ahead: Workshops, Keynotes, and the Future of Agentic Infrastructure

One of the new tracks at next week’s AI Engineer conference in SF is a new focus on LLMs + Robotics, ft. household names like Waymo and Physical Intelligence. However there are many other companies applying LLMs and VLMs in the real world! CloudChef, the first industrial-scale kitchen robotics company with one-shot demonstration learning and an incredibly simple business model, will be serving tasty treats all day with Zippy (https://www.cloudchef.co/zippy ) their AI Chef platform. This is a lightning pod with CEO Nikhil Abraham to preview what Zippy is capable of! https://www.cloudchef.co/platform See a real chef comparison: https://www.youtube.com/watch?v=INDhZ7LwSeo&t=64s See it in the AI Engineer Expo at SF next week: https://ai.engineer Chapters 00:00 Welcome and Introductions 00:58 What is Cloud Chef? 01:36 How the Robots Work: Culinary Intelligence 05:57 Commercial Applications and Early Success 07:02 The Software-First Approach 10:09 Business Model and Pricing 13:10 Demonstration Learning: Training the Robots 16:03 Call to Action and Engineering Opportunities 18:45 Final Thoughts and Technical Details

We are joined by Eno Reyes and Matan Grinberg, the co-founders of Factory.ai. They are building droids for autonomous software engineering, handling everything from code generation to incident response for production outages. After raising a $15M Series A from Sequoia, they just released their product in GA! https://factory.ai/ https://x.com/latentspacepod Chapters 00:00:00 Introductions 00:00:35 Meeting at Langchain Hackathon 00:04:02 Building Factory despite early model limitations 00:06:56 What is Factory AI? 00:08:55 Delegation vs Collaboration in AI Development Tools 00:10:06 Naming Origins of 'Factory' and 'Droids' 00:12:17 Defining Droids: Agent vs Workflow 00:14:34 Live Demo 00:17:37 Enterprise Context and Tool Integration in Droids 00:20:26 Prompting, Clarification, and Agent Communication 00:22:28 Project Understanding and Proactive Context Gathering 00:24:10 Why SWE-Bench Is Dead 00:28:47 Model Fine-tuning and Generalization Challenges 00:31:07 Why Factory is Browser-Based, Not IDE-Based 00:33:51 Test-Driven Development and Agent Verification 00:36:17 Retrieval vs Large Context Windows for Cost Efficiency 00:38:02 Enterprise Metrics: Code Churn and ROI 00:40:48 Executing Large Refactors and Migrations with Droids 00:45:25 Model Speed, Parallelism, and Delegation Bottlenecks 00:50:11 Observability Challenges and Semantic Telemetry 00:53:44 Hiring 00:55:19 Factory's design and branding approach 00:58:34 Closing Thoughts and Future of AI-Native Development

In an otherwise heavy week packed with Microsoft Build, Google I/O, and OpenAI io, the worst kept secret in biglab land was the launch of Claude 4, particularly the triumphant return of Opus, which many had been clamoring for. We will leave the specific Claude 4 recap to AINews, however we think that both Gemini’s progress on Deep Think this week and Claude 4 represent the next frontier of progress on inference time compute/reasoning (at last until GPT5 ships this summer). Will Brown’s talk at AIE NYC and open source work on verifiers have made him one of the most prominent voices able to publicly discuss (aka without the vaguepoasting LoRA they put on you when you join a biglab) the current state of the art in reasoning models and where current SOTA research directions lead. We discussed his latest paper on Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment and he has previewed his AIEWF talk on Agentic RL for those with the temerity to power thru bad meetup audio. Chapters 00:00 Introduction and Episode Overview 02:01 Discussion on Cloud 4 and its Features 04:31 Reasoning and Tool Use in AI Models 07:01 Extended Thinking in Claude and Model Differences 09:31 Speculation on Claude's Extended Thinking 11:01 Challenges and Controversies in AI Model Training 13:31 Technical Highlights and Code Trustworthiness 16:01 Token Costs and Incentives in AI Models 18:31 Thinking Budgets and AI Effort 21:01 Safety and Ethics in AI Model Development 23:31 Anthropic's Approach to AI Safety 26:01 LLM Arena and Evaluation Challenges 28:31 Developing Taste and Direction in AI Research 31:01 Recent Research and Multi-Turn RL 33:31 Tools and Incentives in AI Model Development 36:01 Challenges in Evaluating AI Model Outputs 38:31 Model-Based Rewards and Future Directions 41:01 Wrap-up and Future Plans

ChatGPT Codex is here - the first cloud hosted Autonomous Software Engineer (A-SWE) from OpenAI. We sat down for a quick pod with two core devs on the ChatGPT Codex team: Josh Ma and Alexander Embiricos to get the inside scoop on the origin story of Codex, from WHAM to its future roadmap. Follow them: https://github.com/joshma and https://x.com/embirico Chapters - 00:00 Introduction to the Latent Space Podcast - 00:59 The Launch of ChatGPT Codex - 03:08 Personal Journeys into AI Development - 05:50 The Evolution of Codex and AI Agents - 08:55 Understanding the Form Factor of Codex - 11:48 Building a Software Engineering Agent - 14:53 Best Practices for Using AI Agents - 17:55 The Importance of Code Structure for AI - 21:10 Navigating Human and AI Collaboration - 23:58 Future of AI in Software Development - 28:18 Planning and Decision-Making in AI Development - 31:37 User, Developer, and Model Dynamics - 35:28 Building for the Future: Long-Term Vision - 39:31 Best Practices for Using AI Tools - 42:32 Understanding the Compute Platform - 48:01 Iterative Deployment and Future Improvements

More info: https://docs.anthropic.com/en/docs/claude-code/overview The AI coding wars have now split across four battlegrounds: 1. AI IDEs: with two leading startups in Windsurf ($3B acq. by OpenAI) and Cursor ($9B valuation) and a sea of competition behind them (like Cline, Github Copilot, etc). 2. Vibe coding platforms: Bolt.new, Lovable, v0, etc. all experiencing fast growth and getting to the tens of millions of revenue in months. 3. The teammate agents: Devin, Cosine, etc. Simply give them a task, and they will get back to you with a full PR (with mixed results) 4. The cli-based agents: after Aider’s initial success, we are now seeing many other alternatives including two from the main labs: OpenAI Codex and Claude Code. The main draw is that 1) they are composable 2) they are pay as you go based on tokens used. Since we covered all three of the first categories, today’s guests are Boris and Cat, the lead engineer and PM for Claude Code. If you only take one thing away from this episode, it’s this piece from Boris: Claude Code is not a product as much as it’s a Unix utility. This fits very well with Anthropic’s product principle: “do the simple thing first.” Whether it’s the memory implementation (a markdown file that gets auto-loaded) or the approach to prompt summarization (just ask Claude to summarize), they always pick the smallest building blocks that are useful, understandable, and extensible. Even major features like planning (“/think”) and memory (#tags in markdown) fit the same idea of having text I/O as the core interface. This is very similar to the original UNIX design philosophy: Claude Code is also the most direct way to consume Sonnet for coding, rather than going through all the hidden prompting and optimization than the other products do. You will feel that right away, as the average spend per user is $6/day on Claude Code compared to $20/mo for Cursor, for example. Apparently, there are some engineers inside of Anthropic that have spent >$1,000 in one day! If you’re building AI developer tools, there’s also a lot of alpha on how to design a cli tool, interactive vs non-interactive modes, and how to balance feature creation. Enjoy! Timestamps [00:00:00] Intro [00:01:59] Origins of Claude Code [00:04:32] Anthropic’s Product Philosophy [00:07:38] What should go into Claude Code? [00:09:26] Claude.md and Memory Simplification [00:10:07] Claude Code vs Aider [00:11:23] Parallel Workflows and Unix Utility Philosophy [00:12:51] Cost considerations and pricing model [00:14:51] Key Features Shipped Since Launch [00:16:28] Claude Code writes 80% of Claude Code [00:18:01] Custom Slash Commands and MCP Integration [00:21:08] Terminal UX and Technical Stack [00:27:11] Code Review and Semantic Linting [00:28:33] Non-Interactive Mode and Automation [00:36:09] Engineering Productivity Metrics [00:37:47] Balancing Feature Creation and Maintenance [00:41:59] Memory and the Future of Context [00:50:10] Sandboxing, Branching, and Agent Planning [01:01:43] Future roadmap [01:11:00] Why Anthropic Excels at Developer Tools

Note from your hosts: we were off this week for ICLR and RSA! This week we’re bringing you one of the top episodes from our lightning podcast series, the shorter format, Youtube-only side podcast we do for breaking news and faster turnaround. Please support our work on YouTube! https://www.youtube.com/playlist?list=PLWEAb1SXhjlc5qgVK4NgehdCzMYCwZtiB The explosion of embedding-based applications created a new challenge: efficiently storing, indexing, and searching these high-dimensional vectors at scale. This gap gave rise to the vector database category, with companies like Pinecone leading the charge in 2022-2023 by defining specialized infrastructure for vector operations. The category saw explosive growth following ChatGPT's launch in late 2022, as developers rushed to build AI applications using Retrieval-Augmented Generation (RAG). This surge was partly driven by a widespread misconception that embedding-based similarity search was the only viable method for retrieving context for LLMs!!! The resulting "vector database gold rush" saw massive investment and attention directed toward vector search infrastructure, even though traditional information retrieval techniques remained equally valuable for many RAG applications. https://x.com/jobergum/status/1872923872007217309 Chapters 00:00 Introduction to Trondheim and Background 03:03 The Rise and Fall of Vector Databases 06:08 Convergence of Search Technologies 09:04 Embeddings and Their Importance 12:03 Building Effective Search Systems 15:00 RAG Applications and Recommendations 17:55 The Role of Knowledge Graphs 20:49 Future of Embedding Models and Innovations