Latent Space: The AI Engineer Podcast

Latest Episodes:

[NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton Jan 02, 2026

Show notes

From undergraduate research seminars at Princeton to winning Best Paper award at NeurIPS 2025, Kevin Wang, Ishaan Javali, Michał Bortkiewicz, Tomasz Trzcinski, Benjamin Eysenbach defied conventional wisdom by scaling reinforcement learning networks to 1,000 layers deep—unlocking performance gains that the RL community thought impossible. We caught up with the team live at NeurIPS to dig into the story behind RL1000: why deep networks have worked in language and vision but failed in RL for over a decade (spoiler: it’s not just about depth, it’s about the objective), how they discovered that self-supervised RL (learning representations of states, actions, and future states via contrastive learning) scales where value-based methods collapse, the critical architectural tricks that made it work (residual connections, layer normalization, and a shift from regression to classification), why scaling depth is more parameter-efficient than scaling width (linear vs. quadratic growth), how Jax and GPU-accelerated environments let them collect hundreds of millions of transitions in hours (the data abundance that unlocked scaling in the first place), the “critical depth” phenomenon where performance doesn’t just improve—it multiplies once you cross 15M+ transitions and add the right architectural components, why this isn’t just “make networks bigger” but a fundamental shift in RL objectives (their code doesn’t have a line saying “maximize rewards”—it’s pure self-supervised representation learning), how deep teacher, shallow student distillation could unlock deployment at scale (train frontier capabilities with 1000 layers, distill down to efficient inference models), the robotics implications (goal-conditioned RL without human supervision or demonstrations, scaling architecture instead of scaling manual data collection), and their thesis that RL is finally ready to scale like language and vision—not by throwing compute at value functions, but by borrowing the self-supervised, representation-learning paradigms that made the rest of deep learning work.

We discuss:

* The self-supervised RL objective: instead of learning value functions (noisy, biased, spurious), they learn representations where states along the same trajectory are pushed together, states along different trajectories are pushed apart—turning RL into a classification problem

* Why naive scaling failed: doubling depth degraded performance, doubling again with residual connections and layer norm suddenly skyrocketed performance in one environment—unlocking the “critical depth” phenomenon

* Scaling depth vs. width: depth grows parameters linearly, width grows quadratically—depth is more parameter-efficient and sample-efficient for the same performance

* The Jax + GPU-accelerated environments unlock: collecting thousands of trajectories in parallel meant data wasn’t the bottleneck, and crossing 15M+ transitions was when deep networks really paid off

* The blurring of RL and self-supervised learning: their code doesn’t maximize rewards directly, it’s an actor-critic goal-conditioned RL algorithm, but the learning burden shifts to classification (cross-entropy loss, representation learning) instead of TD error regression

* Why scaling batch size unlocks at depth: traditional RL doesn’t benefit from larger batches because networks are too small to exploit the signal, but once you scale depth, batch size becomes another effective scaling dimension

—

RL1000 Team (Princeton)

* 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities: https://openreview.net/forum?id=s0JVsx3bx1

Full Video Episode

Timestamps

00:00:00 Introduction: Best Paper Award and NeurIPS Poster Experience00:01:11 Team Introductions and Princeton Research Origins00:03:35 The Deep Learning Anomaly: Why RL Stayed Shallow00:04:35 Self-Supervised RL: A Different Approach to Scaling00:05:13 The Breakthrough Moment: Residual Connections and Critical Depth00:07:15 Architectural Choices: Borrowing from ResNets and Avoiding Vanishing Gradients00:07:50 Clarifying the Paper: Not Just Big Networks, But Different Objectives00:08:46 Blurring the Lines: RL Meets Self-Supervised Learning00:09:44 From TD Errors to Classification: Why This Objective Scales00:11:06 Architecture Details: Building on Braw and SymbaFowl00:12:05 Robotics Applications: Goal-Conditioned RL Without Human Supervision00:13:15 Efficiency Trade-offs: Depth vs Width and Parameter Scaling00:15:48 JAX and GPU-Accelerated Environments: The Data Infrastructure00:18:05 World Models and Next State Classification00:22:37 Unlocking Batch Size Scaling Through Network Capacity00:24:10 Compute Requirements: State-of-the-Art on a Single GPU00:21:02 Future Directions: Distillation, VLMs, and Hierarchical Planning00:27:15 Closing Thoughts: Challenging Conventional Wisdom in RL Scaling

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

[State of Code Evals] After SWE-bench, Code Clash & SOTA Coding Benchmarks recap — John Yang Dec 31, 2025

Show notes

From creating SWE-bench in a Princeton basement to shipping CodeClash, SWE-bench Multimodal, and SWE-bench Multilingual, John Yang has spent the last year and a half watching his benchmark become the de facto standard for evaluating AI coding agents—trusted by Cognition (Devin), OpenAI, Anthropic, and every major lab racing to solve software engineering at scale. We caught up with John live at NeurIPS 2025 to dig into the state of code evals heading into 2026: why SWE-bench went from ignored (October 2023) to the industry standard after Devin’s launch (and how Walden emailed him two weeks before the big reveal), how the benchmark evolved from Django-heavy to nine languages across 40 repos (JavaScript, Rust, Java, C, Ruby), why unit tests as verification are limiting and long-running agent tournaments might be the future (CodeClash: agents maintain codebases, compete in arenas, and iterate over multiple rounds), the proliferation of SWE-bench variants (SWE-bench Pro, SWE-bench Live, SWE-Efficiency, AlgoTune, SciCode) and how benchmark authors are now justifying their splits with curation techniques instead of just “more repos,” why Tau-bench’s “impossible tasks” controversy is actually a feature not a bug (intentionally including impossible tasks flags cheating), the tension between long autonomy (5-hour runs) vs. interactivity (Cognition’s emphasis on fast back-and-forth), how Terminal-bench unlocked creativity by letting PhD students and non-coders design environments beyond GitHub issues and PRs, the academic data problem (companies like Cognition and Cursor have rich user interaction data, academics need user simulators or compelling products like LMArena to get similar signal), and his vision for CodeClash as a testbed for human-AI collaboration—freeze model capability, vary the collaboration setup (solo agent, multi-agent, human+agent), and measure how interaction patterns change as models climb the ladder from code completion to full codebase reasoning.

We discuss:

* John’s path: Princeton → SWE-bench (October 2023) → Stanford PhD with Diyi Yang and the Iris Group, focusing on code evals, human-AI collaboration, and long-running agent benchmarks

* The SWE-bench origin story: released October 2023, mostly ignored until Cognition’s Devin launch kicked off the arms race (Walden emailed John two weeks before: “we have a good number”)

* SWE-bench Verified: the curated, high-quality split that became the standard for serious evals

* SWE-bench Multimodal and Multilingual: nine languages (JavaScript, Rust, Java, C, Ruby) across 40 repos, moving beyond the Django-heavy original distribution

* The SWE-bench Pro controversy: independent authors used the “SWE-bench” name without John’s blessing, but he’s okay with it (”congrats to them, it’s a great benchmark”)

* CodeClash: John’s new benchmark for long-horizon development—agents maintain their own codebases, edit and improve them each round, then compete in arenas (programming games like Halite, economic tasks like GDP optimization)

* SWE-Efficiency (Jeffrey Maugh, John’s high school classmate): optimize code for speed without changing behavior (parallelization, SIMD operations)

* AlgoTune, SciCode, Terminal-bench, Tau-bench, SecBench, SRE-bench: the Cambrian explosion of code evals, each diving into different domains (security, SRE, science, user simulation)

* The Tau-bench “impossible tasks” debate: some tasks are underspecified or impossible, but John thinks that’s actually a feature (flags cheating if you score above 75%)

* Cognition’s research focus: codebase understanding (retrieval++), helping humans understand their own codebases, and automatic context engineering for LLMs (research sub-agents)

* The vision: CodeClash as a testbed for human-AI collaboration—vary the setup (solo agent, multi-agent, human+agent), freeze model capability, and measure how interaction changes as models improve

—

John Yang

* SWE-bench: https://www.swebench.com

* X: https://x.com/jyangballin

Full Video Episode

Timestamps

00:00:00 Introduction: John Yang on SWE-bench and Code Evaluations00:00:31 SWE-bench Origins and Devon's Impact on the Coding Agent Arms Race00:01:09 SWE-bench Ecosystem: Verified, Pro, Multimodal, and Multilingual Variants00:02:17 Moving Beyond Django: Diversifying Code Evaluation Repositories00:03:08 Code Clash: Long-Horizon Development Through Programming Tournaments00:04:41 From Halite to Economic Value: Designing Competitive Coding Arenas00:06:04 Ofir's Lab: SWE-ficiency, AlgoTune, and SciCode for Scientific Computing00:07:52 The Benchmark Landscape: TAU-bench, Terminal-bench, and User Simulation00:09:20 The Impossible Task Debate: Refusals, Ambiguity, and Benchmark Integrity00:12:32 The Future of Code Evals: Long Autonomy vs Human-AI Collaboration00:14:37 Call to Action: User Interaction Data and Codebase Understanding Research

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

[State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI Dec 31, 2025

Show notes

From pre-training data curation to shipping GPT-4o, o1, o3, and now GPT-5 thinking and the shopping model, Josh McGrath has lived through the full arc of OpenAI’s post-training evolution—from the PPO vs DPO debates of 2023 to today’s RLVR era, where the real innovation isn’t optimization methods but data quality, signal trust, and token efficiency. We sat down with Josh at NeurIPS 2025 to dig into the state of post-training heading into 2026: why RLHF and RLVR are both just policy gradient methods (the difference is the input data, not the math), how GRPO from DeepSeek Math was underappreciated as a shift toward more trustworthy reward signals (math answers you can verify vs. human preference you can’t), why token efficiency matters more than wall-clock time (GPT-5 to 5.1 bumped evals and slashed tokens), how Codex has changed his workflow so much he feels “trapped” by 40-minute design sessions followed by 15-minute agent sprints, the infrastructure chaos of scaling RL (”way more moving parts than pre-training”), why long context will keep climbing but agents + graph walks might matter more than 10M-token windows, the shopping model as a test bed for interruptability and chain-of-thought transparency, why personality toggles (Anton vs Clippy) are a real differentiator users care about, and his thesis that the education system isn’t producing enough people who can do both distributed systems and ML research—the exact skill set required to push the frontier when the bottleneck moves every few weeks.

We discuss:

* Josh’s path: pre-training data curation → post-training researcher at OpenAI, shipping GPT-4o, o1, o3, GPT-5 thinking, and the shopping model

* Why he switched from pre-training to post-training: “Do I want to make 3% compute efficiency wins, or change behavior by 40%?”

* The RL infrastructure challenge: way more moving parts than pre-training (tasks, grading setups, external partners), and why babysitting runs at 12:30am means jumping into unfamiliar code constantly

* How Codex has changed his workflow: 40-minute design sessions compressed into 15-minute agent sprints, and the strange “trapped” feeling of waiting for the agent to finish

* The RLHF vs RLVR debate: both are policy gradient methods, the real difference is data quality and signal trust (human preference vs. verifiable correctness)

* Why GRPO (from DeepSeek Math) was underappreciated: not just an optimization trick, but a shift toward reward signals you can actually trust (math answers over human vibes)

* The token efficiency revolution: GPT-5 to 5.1 bumped evals and slashed tokens, and why thinking in tokens (not wall-clock time) unlocks better tool-calling and agent workflows

* Personality toggles: Anton (tool, no warmth) vs Clippy (friendly, helpful), and why Josh uses custom instructions to make his model “just a tool”

* The router problem: having a router at the top (GPT-5 thinking vs non-thinking) and an implicit router (thinking effort slider) creates weird bumps, and why the abstractions will eventually merge

* Long context: climbing Graph Blocks evals, the dream of 10M+ token windows, and why agents + graph walks might matter more than raw context length

* Why the education system isn’t producing enough people who can do both distributed systems and ML research, and why that’s the bottleneck for frontier labs

* The 2026 vision: neither pre-training nor post-training is dead, we’re in the fog of war, and the bottleneck will keep moving (so emotional stability helps)

—

Josh McGrath

* OpenAI: https://openai.com

* X: https://x.com/j_mcgraph

Full Video Episode

Timestamps

00:00:00 Introduction: Josh McGrath on Post-Training at OpenAI00:04:37 The Shopping Model: Black Friday Launch and Interruptability00:07:11 Model Personality and the Anton vs Clippy Divide00:08:26 Beyond PPO vs DPO: The Data Quality Spectrum in RL00:01:40 Infrastructure Challenges: Why Post-Training RL is Harder Than Pre-Training00:13:12 Token Efficiency: The 2D Plot That Matters Most00:03:45 Codex Max and the Flow Problem: 40 Minutes of Planning, 15 Minutes of Waiting00:17:29 Long Context and Graph Blocks: Climbing Toward Perfect Context00:21:23 The ML-Systems Hybrid: What's Hard to Hire For00:24:50 Pre-Training Isn't Dead: Living Through Technological Revolution

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

[State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor Dec 30, 2025

Show notes

From Berkeley robotics and OpenAI’s 2017 Dota-era internship to shipping RL breakthroughs on GPT-4o, o1, and o3, and now leading model development at Cursor, Ashvin Nair has done it all. We caught up with Ashvin at NeurIPS 2025 to dig into the inside story of OpenAI’s reasoning team (spoiler: it went from a dozen people to 300+), why IOI Gold felt reachable in 2022 but somehow didn’t change the world when o1 actually achieved it, how RL doesn’t generalize beyond the training distribution (and why that means you need to bring economically useful tasks into distribution by co-designing products and models), the deeper lessons from the RL research era (2017–2022) and why most of it didn’t pan out because the community overfitted to benchmarks, how Cursor is uniquely positioned to do continual learning at scale with policy updates every two hours and product-model co-design that keeps engineers in the loop instead of context-switching into ADHD hell, and his bet that the next paradigm shift is continual learning with infinite memory—where models experience something once (a bug, a mistake, a user pattern) and never forget it, storing millions of deployment tokens in weights without overloading capacity.

We discuss:

* Ashvin’s path: Berkeley robotics PhD → OpenAI 2017 intern (Dota era) → o1/o3 reasoning team → Cursor ML lead in three months

* Why robotics people are the most grounded at NeurIPS (they work with the real world) and simulation people are the most unhinged (Lex Fridman’s take)

* The IOI Gold paradox: “If you told me we’d achieve IOI Gold in 2022, I’d assume we could all go on vacation—AI solved, no point working anymore. But life is still the same.”

* The RL research era (2017–2022) and why most of it didn’t pan out: overfitting to benchmarks, too many implicit knobs to tune, and the community rewarding complex ideas over simple ones that generalize

* Inside the o1 origin story: a dozen people, conviction from Ilya and Jakob Pachocki that RL would work, small-scale prototypes producing “surprisingly accurate reasoning traces” on math, and first-principles belief that scaled

* The reasoning team grew from ~12 to 300+ people as o1 became a product and safety, tooling, and deployment scaled up

* Why Cursor is uniquely positioned for continual learning: policy updates every two hours (online RL on tab), product and ML sitting next to each other, and the entire software engineering workflow (code, logs, debugging, DataDog) living in the product

* Composer as the start of product-model co-design: smart enough to use, fast enough to stay in the loop, and built by a 20–25 person ML team with high-taste co-founders who code daily

* The next paradigm shift: continual learning with infinite memory—models that experience something once (a bug, a user mistake) and store it in weights forever, learning from millions of deployment tokens without overloading capacity (trillions of pretraining tokens = plenty of room)

* Why off-policy RL is unstable (Ashvin’s favorite interview question) and why Cursor does two-day work trials instead of whiteboard interviews

* The vision: automate software engineering as a process (not just answering prompts), co-design products so the entire workflow (write code, check logs, debug, iterate) is in-distribution for RL, and make models that never make the same mistake twice

—

Ashvin Nair

* Cursor: https://cursor.com

* X: https://x.com/ashvinnair_

Full Video Episode

Timestamps

00:00:00 Introduction: From Robotics to Cursor via OpenAI00:01:58 The Robotics to LLM Agent Transition: Why Code Won00:09:11 RL Research Winter and Academic Overfitting00:11:45 The Scaling Era and Moving Goalposts: IOI Gold Doesn't Mean AGI00:21:30 OpenAI's Reasoning Journey: From Codex to O100:20:03 The Blip: Thanksgiving 2023 and OpenAI Governance00:22:39 RL for Reasoning: The O-Series Conviction and Scaling00:25:47 O1 to O3: Smooth Internal Progress vs External Hype Cycles00:33:07 Why Cursor: Co-Designing Products and Models for Real Work00:34:14 Composer and the Future: Online Learning Every Two Hours00:35:15 Continual Learning: The Missing Paradigm Shift00:44:00 Hiring at Cursor and Why Off-Policy RL is Unstable

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

[State of AI Startups] Memory/Learning, RL Envs & DBT-Fivetran — Sarah Catanzaro, Amplify Dec 30, 2025

Show notes

From investing through the modern data stack era (DBT, Fivetran, and the analytics explosion) to now investing at the frontier of AI infrastructure and applications at Amplify Partners, Sarah Catanzaro has spent years at the intersection of data, compute, and intelligence—watching categories emerge, merge, and occasionally disappoint. We caught up with Sarah live at NeurIPS 2025 to dig into the state of AI startups heading into 2026: why $100M+ seed rounds with no near-term roadmap are now the norm (and why that terrifies her), what the DBT-Fivetran merger really signals about the modern data stack (spoiler: it’s not dead, just ready for IPO), how frontier labs are using DBT and Fivetran to manage training data and agent analytics at scale, why data catalogs failed as standalone products but might succeed as metadata services for agents, the consumerization of AI and why personalization (memory, continual learning, K-factor) is the 2026 unlock for retention and growth, why she thinks RL environments are a fad and real-world logs beat synthetic clones every time, and her thesis for the most exciting AI startups: companies that marry hard research problems (RAG, rule-following, continual learning) with killer applications that were simply impossible before.

We discuss:

* The DBT-Fivetran merger: not the death of the modern data stack, but a path to IPO scale (targeting $600M+ combined revenue) and a signal that both companies were already winning their categories

* How frontier labs use data infrastructure: DBT and Fivetran for training data curation, agent analytics, and managing increasingly complex interactions—plus the rise of transactional databases (RocksDB) and efficient data loading (Vortex) for GPU-bound workloads

* Why data catalogs failed: built for humans when they should have been built for machines, focused on discoverability when the real opportunity was governance, and ultimately subsumed as features inside Snowflake, DBT, and Fivetran

* The $100M+ seed phenomenon: raising massive rounds at billion-dollar valuations with no 6-month roadmap, seven-day decision windows, and founders optimizing for signal (”we’re a unicorn”) over partnership or dilution discipline

* Why world models are overhyped but underspecified: three competing definitions, unclear generalization across use cases (video games ≠ robotics ≠ autonomous driving), and a research problem masquerading as a product category

* The 2026 theme: consumerization of AI via personalization—memory management, continual learning, and solving retention/churn by making products learn skills, preferences, and adapt as the world changes (not just storing facts in cursor rules)

* Why RL environments are a fad: labs are paying 7–8 figures for synthetic clones when real-world logs, traces, and user activity (à la Cursor) are richer, cheaper, and more generalizable

* Sarah’s investment thesis: research-driven applications that solve hard technical problems (RAG for Harvey, rule-following for Sierra, continual learning for the next killer app) and unlock experiences that were impossible before

* Infrastructure bets: memory, continual learning, stateful inference, and the systems challenges of loading/unloading personalized weights at scale

* Why K-factor and growth fundamentals matter again: AI felt magical in 2023–2024, but as the magic fades, retention and virality are back—and most AI founders have never heard of K-factor

—

Sarah Catanzaro

* X: https://x.com/sarahcat21

* Amplify Partners: https://amplifypartners.com/

Where to find Latent Space

* X: https://x.com/latentspacepod

Full Video Episode

Timestamps

00:00:00 Introduction: Sarah Catanzaro's Journey from Data to AI00:01:02 The DBT-Fivetran Merger: Not the End of the Modern Data Stack00:05:26 Data Catalogs and What Went Wrong00:08:16 Data Infrastructure at AI Labs: Surprising Insights00:10:13 The Crazy Funding Environment of 2024-202500:17:18 World Models: Hype, Confusion, and Market Potential00:18:59 Memory Management and Continual Learning: The Next Frontier00:23:27 Agent Environments: Just a Fad?00:25:48 The Perfect AI Startup: Research Meets Application00:28:02 Closing Thoughts and Where to Find Sarah

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

One Year of MCP — with David Soria Parra and AAIF leads from OpenAI, Goose, Linux Foundation Dec 27, 2025

Show notes

One year ago, Anthropic launched the Model Context Protocol (MCP)—a simple, open standard to connect AI applications to the data and tools they need. Today, MCP has exploded from a local-only experiment into the de facto protocol for agentic systems, adopted by OpenAI, Microsoft, Google, Block, and hundreds of enterprises building internal agents at scale. And now, MCP is joining the newly formed Agentic AI Foundation (AAIF) under the Linux Foundation, alongside Block’s Goose coding agent, with founding members spanning the biggest names in AI and cloud infrastructure.

We sat down with David Soria Parra (MCP lead, Anthropic), Nick Cooper (OpenAI), Brad Howes (Block / Goose), and Jim Zemlin (Linux Foundation CEO) to dig into the one-year journey of MCP—from Thanksgiving hacking sessions and the first remote authentication spec to long-running tasks, MCP Apps, and the rise of agent-to-agent communication—and the behind-the-scenes story of how three competitive AI labs came together to donate their protocols and agents to a neutral foundation, why enterprises are deploying MCP servers faster than anyone expected (most of it invisible, internal, and at massive scale), what it takes to design a protocol that works for both simple tool calls and complex multi-agent orchestration, how the foundation will balance taste-making (curating meaningful projects) with openness (avoiding vendor lock-in), and the 2025 vision: MCP as the communication layer for asynchronous, long-running agents that work while you sleep, discover and install their own tools, and unlock the next order of magnitude in AI productivity.

We discuss:

* The one-year MCP journey: from local stdio servers to remote HTTP streaming, OAuth 2.1 authentication (and the enterprise lessons learned), long-running tasks, and MCP Apps (iframes for richer UI)

* Why MCP adoption is exploding internally at enterprises: invisible, internal servers connecting agents to Slack, Linear, proprietary data, and compliance-heavy workflows (financial services, healthcare)

* The authentication evolution: separating resource servers from identity providers, dynamic client registration, and why the March spec wasn’t enterprise-ready (and how June fixed it)

* How Anthropic dogfoods MCP: internal gateway, custom servers for Slack summaries and employee surveys, and why MCP was born from “how do I scale dev tooling faster than the company grows?”

* Tasks: the new primitive for long-running, asynchronous agent operations—why tools aren’t enough, how tasks enable deep research and agent-to-agent handoffs, and the design choice to make tasks a “container” (not just async tools)

* MCP Apps: why iframes, how to handle styles and branding, seat selection and shopping UIs as the killer use case, and the collaboration with OpenAI to build a common standard

* The registry problem: official registry vs. curated sub-registries (Smithery, GitHub), trust levels, model-driven discovery, and why MCP needs “npm for agents” (but with signatures and HIPAA/financial compliance)

* The founding story of AAIF: how Anthropic, OpenAI, and Block came together (spoiler: they didn’t know each other were talking to Linux Foundation), why neutrality matters, and how Jim Zemlin has never seen this much day-one inbound interest in 22 years

—

David Soria Parra (Anthropic / MCP)

* MCP: https://modelcontextprotocol.io

* https://uk.linkedin.com/in/david-soria-parra-4a78b3a

* https://x.com/dsp_

Nick Cooper (OpenAI)

* X: https://x.com/nicoaicopr

Brad Howes (Block / Goose)

* Goose: https://github.com/block/goose

Jim Zemlin (Linux Foundation)

* LinkedIn: https://www.linkedin.com/in/zemlin/

Agentic AI Foundation

* https://agenticai.foundation

Full Video Episode

Timestamps

00:00:00 Introduction: MCP's First Year and Foundation Launch00:01:17 MCP's Journey: From Launch to Industry Standard00:02:06 Protocol Evolution: Remote Servers and Authentication00:08:52 Enterprise Authentication and Financial Services00:11:42 Transport Layer Challenges: HTTP Streaming and Scalability00:15:37 Standards Development: Collaboration with Tech Giants00:34:27 Long-Running Tasks: The Future of Async Agents00:30:41 Discovery and Registries: Building the MCP Ecosystem00:30:54 MCP Apps and UI: Beyond Text Interfaces00:26:55 Internal Adoption: How Anthropic Uses MCP00:23:15 Skills vs MCP: Complementary Not Competing00:36:16 Community Events and Enterprise Learnings01:03:31 Foundation Formation: Why Now and Why Together01:07:38 Linux Foundation Partnership: Structure and Governance01:11:13 Goose as Reference Implementation01:17:28 Principles Over Roadmaps: Composability and Quality01:21:02 Foundation Value Proposition: Why Contribute01:27:49 Practical Investments: Events, Tools, and Community01:34:58 Looking Ahead: Async Agents and Real Impact

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

Steve Yegge's Vibe Coding Manifesto: Why Claude Code Isn't It & What Comes After the IDE Dec 26, 2025

Show notes

Note: Steve and Gene’s talk on Vibe Coding and the post IDE world was one of the top talks of AIE CODE:

From building legendary platforms at Google and Amazon to authoring one of the most influential essays on AI-powered development (Revenge of the Junior Developer, quoted by Dario Amodei himself), Steve Yegge has spent decades at the frontier of software engineering—and now he’s leading the charge into what he calls the “factory farming” era of code. After stints at SourceGraph and building Beads (a purely vibe-coded issue tracker with tens of thousands of users), Steve co-authored The Vibe Coding Book and is now building VC (VibeCoder), an agent orchestration dashboard designed to move developers from writing code to managing fleets of AI agents that coordinate, parallelize, and ship features while you sleep.

We sat down with Steve at AI Engineer Summit to dig into why Claude Code, Cursor, and the entire 2024 stack are already obsolete, what it actually takes to trust an agent after 2,000 hours of practice (hint: they will delete your production database if you anthropomorphize them), why the real skill is no longer writing code but orchestrating agents like a NASCAR pit crew, how merging has become the new wall that every 10x-productive team is hitting (and why one company’s solution is literally “one engineer per repo”), the rise of multi-agent workflows where agents reserve files, message each other via MCP, and coordinate like a little village, why Steve believes if you’re still using an IDE to write code by January 1st, you’re a bad engineer, how the 12–15 year experience bracket is the most resistant demographic (and why their identity is tied to obsolete workflows), the hidden chaos inside OpenAI, Anthropic, and Google as they scale at breakneck speed, why rewriting from scratch is now faster than refactoring for a growing class of codebases, and his 2025 prediction: we’re moving from subsistence agriculture to John Deere-scale factory farming of code, and the Luddite backlash is only just beginning.

We discuss:

* Why Claude Code, Cursor, and agentic coding tools are already last year’s tech—and what comes next: agent orchestration dashboards where you manage fleets, not write lines

* The 2,000-hour rule: why it takes a full year of daily use before you can predict what an LLM will do, and why trust = predictability, not capability

* Steve’s hot take: if you’re still using an IDE to develop code by January 1st, 2025, you’re a bad engineer—because the abstraction layer has moved from models to full-stack agents

* The demographic most resistant to vibe coding: 12–15 years of experience, senior engineers whose identity is tied to the way they work today, and why they’re about to become the interns

* Why anthropomorphizing LLMs is the biggest mistake: the “hot hand” fallacy, agent amnesia, and how Steve’s agent once locked him out of prod by changing his password to “fix” a problem

* Should kids learn to code? Steve’s take: learn to vibe code—understand functions, classes, architecture, and capabilities in a language-neutral way, but skip the syntax

* The 2025 vision: “factory farming of code” where orchestrators run Cloud Code, scrub output, plan-implement-review-test in loops, and unlock programming for non-programmers at scale

—

Steve Yegge

* X: https://x.com/steve_yegge

* Substack (Stevie’s Tech Talks): https://steve-yegge.medium.com/

* GitHub (VC / VibeCoder): https://github.com/yegge-labs

Where to find Latent Space

* X: https://x.com/latentspacepod

Full Video Episode

Thumbnails

00:00:00 Introduction: Steve Yegge on Vibe Coding and AI Engineering00:00:59 The Backlash: Who Resists Vibe Coding and Why00:04:26 The 2000 Hour Rule: Building Trust with AI Coding Tools00:03:31 The January 1st Deadline: IDEs Are Becoming Obsolete00:02:55 10X Productivity at OpenAI: The Performance Review Problem00:07:49 The Hot Hand Fallacy: When AI Agents Betray Your Trust00:11:12 Claude Code Isn't It: The Need for Agent Orchestration00:15:20 The Orchestrator Revolution: From Cloud Code to Agent Villages00:18:46 The Merge Wall: The Biggest Unsolved Problem in AI Coding00:26:33 Never Rewrite Your Code - Until Now: Joel Spolsky Was Wrong00:22:43 Factory Farming Code: The John Deere Era of Software00:29:27 Google's Gemini Turnaround and the AI Lab Chaos00:33:20 Should Your Kids Learn to Code? The New Answer00:34:59 Code MCP and the Gossip Rate: Latest Vibe Coding Discoveries

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI Dec 26, 2025

Show notes

From the frontlines of OpenAI’s Codex and GPT-5 training teams, Bryan and Bill are building the future of AI-powered coding—where agents don’t just autocomplete, they architect, refactor, and ship entire features while you sleep. We caught up with them at AI Engineer Conference right after the launch of Codex Max, OpenAI’s newest long-running coding agent designed to work for 24+ hours straight, manage its own context, and spawn sub-agents to parallelize work across your entire codebase.

We sat down with Bryan and Bill to dig into what it actually takes to train a model that developers trust—why personality, communication, and planning matter as much as raw capability, how Codex is trained with strong opinions about tools (it loves rg over grep, seriously), why the abstraction layer is moving from models to full-stack agents you can plug into VS Code or Zed, how OpenAI partners co-develop tool integrations and discover unexpected model habits (like renaming tools to match Codex’s internal training), the rise of applied evals that measure real-world impact instead of academic benchmarks, why multi-turn evals are the next frontier (and Bryan’s “job interview eval” idea), how coding agents are breaking out of code into personal automation, terminal workflows, and computer use, and their 2026 vision: coding agents trusted enough to handle the hardest refactors at any company, not just top-tier firms, and general enough to build integrations, organize your desktop, and unlock capabilities you’d never get access to otherwise.

We discuss:

* What Codex Max is: a long-running coding agent that can work 24+ hours, manage its own context window, and spawn sub-agents for parallel work

* Why the name “Max”: maximalist, maximization, speed and endurance—it’s simply better and faster for the same problems

* Training for personality: communication, planning, context gathering, and checking your work as behavioral characteristics, not just capabilities

* How Codex develops habits like preferring rg over grep, and why renaming tools to match its training (e.g., terminal-style naming) dramatically improves tool-call performance

* The split between Codex (opinionated, agent-focused, optimized for the Codex harness) and GPT-5 (general, more durable across different tools and modalities)

* Why the abstraction layer is moving up: from prompting models to plugging in full agents (Codex, GitHub Copilot, Zed) that package the entire stack

* The rise of sub-agents and agents-using-agents: Codex Max spawning its own instances, handing off context, and parallelizing work across a codebase

* How OpenAI works with coding partners on the bleeding edge to co-develop tool integrations and discover what the model is actually good at

* The shift to applied evals: capturing real-world use cases instead of academic benchmarks, and why ~50% of OpenAI employees now use Codex daily

* Why multi-turn evals are the next frontier: LM-as-a-judge for entire trajectories, Bryan’s “job interview eval” concept, and the need for a batch multi-turn eval API

* How coding agents are breaking out of code: personal automation, organizing desktops, terminal workflows, and “Devin for non-coding” use cases

* Why Slack is the ultimate UI for work, and how coding agents can become your personal automation layer for email, files, and everything in between

* The 2026 vision: more computer use, more trust, and coding agents capable enough that any company can access top-tier developer capabilities, not just elite firms

—

Bryan & Bill (OpenAI Codex Team)

* http://x.com/bfioca

* https://x.com/realchillben

* OpenAI Codex: https://openai.com/index/openai-codex/

Where to find Latent Space

* X: https://x.com/latentspacepod

Full Video Episode

Timestamps

00:00:00 Introduction: Latent Space Listeners at AI Engineer Code00:01:27 Codex Max Launch: Training for Long-Running Coding Agents00:03:01 Model Personality and Trust: Communication, Planning, and Self-Checking00:05:20 Codex vs GPT-5: Opinionated Agents vs General Models00:07:47 Tool Use and Model Habits: The Ripgrep Discovery00:09:16 Personality Design: Verbosity vs Efficiency in Coding Agents00:11:56 The Agent Abstraction Layer: Building on Top of Codex00:14:08 Sub-Agents and Multi-Agent Patterns: The Future of Composition00:16:11 Trust and Adoption: OpenAI Developers Using Codex Daily00:17:21 Applied Evals: Real-World Testing vs Academic Benchmarks00:19:15 Multi-Turn Evals and the Job Interview Pattern00:21:35 Feature Request: Batch Multi-Turn Eval API00:22:28 Beyond Code: Personal Automation and Computer Use00:24:51 Vision-Native Agents and the UI Integration Challenge00:25:02 2026 Predictions: Trust, Computer Use, and Democratized Excellence

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

SAM 3: The Eyes for AI — Nikhila & Pengchuan (Meta Superintelligence), ft. Joseph Nelson (Roboflow) Dec 18, 2025

Show notes

As with all demo-heavy and especially vision AI podcasts, we encourage watching along on our YouTube (and tossing us an upvote/subscribe if you like!)

From SAM 1’s 11-million-image data engine to SAM 2’s memory-based video tracking, MSL’s Segment Anything project has redefined what’s possible in computer vision. Now SAM 3 takes the next leap: concept segmentation—prompting with natural language like “yellow school bus” or “tablecloth” to detect, segment, and track every instance across images and video, in real time, with human-level exhaustivity. And with the latest SAM Audio:

SAM can now even segment audio output!

We sat down with Nikhila Ravi (SAM lead at Meta) and Pengchuan Zhang (SAM 3 researcher) alongside Joseph Nelson (CEO, Roboflow) to unpack how SAM 3 unifies interactive segmentation, open-vocabulary detection, video tracking, and more into a single model that runs in 30ms on images and scales to real-time video on multi-GPU setups. We dig into the data engine that automated exhaustive annotation from two minutes per image down to 25 seconds using AI verifiers fine-tuned on Llama, the new SACO (Segment Anything with Concepts) benchmark with 200,000+ unique concepts vs. the previous 1.2k, how SAM 3 separates recognition from localization with a presence token, why decoupling the detector and tracker was critical to preserve object identity in video, how SAM 3 Agents unlock complex visual reasoning by pairing SAM 3 with multimodal LLMs like Gemini, and the real-world impact: 106 million smart polygons created on Roboflow saving humanity an estimated 130+ years of labeling time across fields from cancer research to underwater trash cleanup to autonomous vehicle perception.

We discuss:

* What SAM 3 is: a unified model for concept-prompted segmentation, detection, and tracking in images and video using atomic visual concepts like “purple umbrella” or “watering can”

* How concept prompts work: short text phrases that find all instances of a category without manual clicks, plus visual exemplars (boxes, clicks) to refine and adapt on the fly

* Real-time performance: 30ms per image (100 detected objects on H200), 10 objects on 2×H200 video, 28 on 4×, 64 on 8×, with parallel inference and “fast mode” tracking

* The SACO benchmark: 200,000+ unique concepts vs. 1.2k in prior benchmarks, designed to capture the diversity of natural language and reach human-level exhaustivity

* The data engine: from 2 minutes per image (all-human) to 45 seconds (model-in-loop proposals) to 25 seconds (AI verifiers for mask quality and exhaustivity checks), fine-tuned on Llama 3.2

* Why exhaustivity is central: every instance must be found, verified by AI annotators, and manually corrected only when the model misses—automating the hardest part of segmentation at scale

* Architecture innovations: presence token to separate recognition (”is it in the image?”) from localization (”where is it?”), decoupled detector and tracker to preserve identity-agnostic detection vs. identity-preserving tracking

* Building on Meta’s ecosystem: Perception Encoder, DINO v2 detector, Llama for data annotation, and SAM 2’s memory-based tracking backbone

* SAM 3 Agents: using SAM 3 as a visual tool for multimodal LLMs (Gemini, Llama) to solve complex visual reasoning tasks like “find the bigger character” or “what distinguishes male from female in this image”

* Fine-tuning with as few as 10 examples: domain adaptation for specialized use cases (Waymo vehicles, medical imaging, OCR-heavy scenes) and the outsized impact of negative examples

* Real-world impact at Roboflow: 106M smart polygons created, saving 130+ years of labeling time across cancer research, underwater trash cleanup, autonomous drones, industrial automation, and more

—

MSL FAIR team

* Nikhila: https://www.linkedin.com/in/nikhilaravi/

* Pengchuan: https://pzzhang.github.io/pzzhang/

Joseph Nelson

* X: https://x.com/josephofiowa

* LinkedIn: https://www.linkedin.com/in/josephofiowa/

Full Video Episode

Timestamps

00:00:00 Introduction and the SAM Series Legacy00:00:53 SAM 3 Launch: Three Models in One Release00:05:30 Live Demo: Concept Prompting and Visual Exemplars00:10:54 From Prototype to Production: The Evolution of Text Prompting00:15:45 The Data Engine: Automating Exhaustive Annotation00:14:10 Real-World Impact: 130 Years of Humanity Saved00:25:11 Architecture Deep Dive: Decoupled Detection and Tracking00:28:02 SAM 3 Agent: Bridging Vision and Language Models00:33:20 Head-to-Head: SAM 3 vs Gemini and Florence00:47:50 Video Understanding and the Masklet Detection Score00:20:24 Fine-Tuning and Domain Adaptation: From Waymos to Medical Imaging00:52:25 The Future of Perception: Native Vision vs Tool Calls01:05:45 Building with SAM 3: Roboflow's Rapid Auto-Labeling00:57:02 Open Source Philosophy and the Path to AGI00:58:24 What's Next: SAM 4, Video Scale, and Beyond Human Performance

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security Dec 16, 2025

Show notes

Note: this is Pliny and John’s first major podcast. Voices have been changed for opsec.

From jailbreaking every frontier model and turning down Anthropic’s Constitutional AI challenge to leading BT6, a 28-operator white-hat hacker collective obsessed with radical transparency and open-source AI security, Pliny the Liberator and John V are redefining what AI red-teaming looks like when you refuse to lobotomize models in the name of “safety.”

Pliny built his reputation crafting universal jailbreaks—skeleton keys that obliterate guardrails across modalities—and open-sourcing prompt templates like Libertas, predictive reasoning cascades, and the infamous “Pliny divider” that’s now embedded so deep in model weights it shows up unbidden in WhatsApp messages. John V, coming from prompt engineering and computer vision, co-founded the Bossy Discord (40,000 members strong) and helps steer BT6’s ethos: if you can’t open-source the data, we’re not interested. Together they’ve turned down enterprise gigs, pushed back on Anthropic’s closed bounties, and insisted that real AI security happens at the system layer—not by bubble-wrapping latent space.

We sat down with Pliny and John to dig into the mechanics of hard vs. soft jailbreaks, why multi-turn crescendo attacks were obvious to hackers years before academia “discovered” them, how segmented sub-agents let one jailbroken orchestrator weaponize Claude for real-world attacks (exactly as Pliny predicted 11 months before Anthropic’s recent disclosure), why guardrails are security theater that punishes capability while doing nothing for real safety, the role of intuition and “bonding” with models to navigate latent space, how BT6 vets operators on skill and integrity, why they believe Mech Interp and open-source data are the path forward (not RLHF lobotomization), and their vision for a future where spatial intelligence, swarm robotics, and AGI alignment research happen in the open—bootstrapped, grassroots, and uncompromising.

We discuss:

* What universal jailbreaks are: skeleton-key prompts that obliterate guardrails across models and modalities, and why they’re central to Pliny’s mission of “liberation”

* Hard vs. soft jailbreaks: single-input templates vs. multi-turn crescendo attacks, and why the latter were obvious to hackers long before academic papers

* The Libertas repo: predictive reasoning, the Library of Babel analogy, quotient dividers, weight-space seeds, and how introducing “steered chaos” pulls models out-of-distribution

* Why jailbreaking is 99% intuition and bonding with the model: probing token layers, syntax hacks, multilingual pivots, and forming a relationship to navigate latent space

* The Anthropic Constitutional AI challenge drama: UI bugs, judge failures, goalpost moving, the demand for open-source data, and why Pliny sat out the $30k bounty

* Why guardrails ≠ safety: security theater, the futility of locking down latent space when open-source is right behind, and why real safety work happens in meatspace (not RLHF)

* The weaponization of Claude: how segmented sub-agents let one jailbroken orchestrator execute malicious tasks (pyramid-builder analogy), and why Pliny predicted this exact TTP 11 months before Anthropic’s disclosure

* BT6 hacker collective: 28 operators across two cohorts, vetted on skill and integrity, radical transparency, radical open-source, and the magic of moving the needle on AI security, swarm intelligence, blockchain, and robotics

—

Pliny the Liberator

* X: https://x.com/elder_plinius

* GitHub (Libertas): https://github.com/elder-plinius/L1B3RT45

John V

* X: https://x.com/JohnVersus

BT6 & Bossy

* BT6: https://bt6.gg

* Bossy Discord: Search “Bossy Discord” or ask Pliny/John V on X

Where to find Latent Space

* X: https://x.com/latentspacepod

Full Video Episode

Timestamps

00:00:00 Introduction: Meet Pliny the Liberator and John V00:01:50 The Philosophy of AI Liberation and Jailbreaking00:03:08 Universal Jailbreaks: Skeleton Keys to AI Models00:04:24 The Cat-and-Mouse Game: Attackers vs Defenders00:05:42 Security Theater vs Real Safety: The Fundamental Disconnect00:08:51 Inside the Libertas Repo: Prompt Engineering as Art00:16:22 The Anthropic Challenge Drama: UI Bugs and Open Source Data00:23:30 From Jailbreaks to Weaponization: AI-Orchestrated Attacks00:26:55 The BT6 Hacker Collective and BASI Community00:34:46 AI Red Teaming: Full Stack Security Beyond the Model00:38:06 Safety vs Security: Meat Space Solutions and Final Thoughts

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

Our TOPPODCAST Picks

Follow Us

Stay Connected

Latent Space: The AI Engineer Podcast

Related Podcasts

Links

Stay Connected