All Episodes
Latent Space: The AI Engineer Podcast — 196 episodes
🔬Doing Vibe Physics — Alex Lupsasca, OpenAI
Physical AI that Moves the World — Qasar Younis & Peter Ludwig, Applied Intuition
AIE Europe Debrief + Agent Labs Thesis: Unsupervised Learning x Latent Space Crossover Special (2026)
Shopify’s AI Phase Transition: 2026 Usage Explosion, Unlimited Opus-4.6 Token Budget, Tangle, Tangent, SimGym — with Mikhail Parakhin, Shopify CTO
🔬 Training Transformers to solve 95% failure rate of Cancer Trials — Ron Alfa & Daniel Bear, Noetik
Notion’s Token Town: 5 Rebuilds, 100+ Tools, MCP vs CLIs and the Software Factory Future — Simon Last & Sarah Sachs of Notion
Extreme Harness Engineering for Token Billionaires: 1M LOC, 1B toks/day, 0% human code, 0% human review — Ryan Lopopolo, OpenAI Frontier & Symphony
Marc Andreessen introspects on The Death of the Browser, Pi + OpenClaw, and Why "This Time Is Different"
Moonlake: Causal World Models should be Multimodal, Interactive, and Efficient — with Chris Manning and Fan-yun Sun
Mistral: Voxtral TTS, Forge, Leanstral, & what's next for Mistral 4 — w/ Pavan Kumar Reddy & Guillaume Lample
🔬Why There Is No "AlphaFold for Materials" — AI for Materials Discovery with Heather Kulik
Dreamer: the Personal Agent OS — David Singleton
Why Anthropic Thinks AI Should Have Its Own Computer — Felix Rieseberg of Claude Cowork & Claude Code Desktop
Retrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Hørup Eskildsen of Turbopuffer
NVIDIA's AI Engineers: Agent Inference at Planetary Scale and "Speed of Light" — Nader Khalil (Brev), Kyle Kranen (Dynamo)
Cursor's Third Era: Cloud Agents
Every Agent Needs a Box — Aaron Levie, Box
METR’s Joel Becker on exponential Time Horizon Evals, Threat Models, and the Limits of AI Productivity
[LIVE] Anthropic Distillation & How Models Cheat (SWE-Bench Dead) | Nathan Lambert & Sebastian Raschka
🔬Searching the Space of All Possible Materials — Prof. Max Welling, CuspAI
Claude Code for Finance + The Global Memory Shortage: Doug O'Laughlin, SemiAnalysis
⚡️The End of SWE-Bench Verified — Mia Glaese & Olivia Watkins, OpenAI Frontier Evals & Human Data
Bitter Lessons in Venture vs Growth: Anthropic vs OpenAI, Noam Shazeer, World Labs, Thinking Machines, Cursor, ASIC Economics — Martin Casado & Sarah Wang of a16z
Owning the AI Pareto Frontier — Jeff Dean
🔬Beyond AlphaFold: How Boltz is Open-Sourcing the Future of Drug Discovery
The First Mechanistic Interpretability Frontier Lab — Myra Deng & Mark Bissell of Goodfire AI
🔬 Automating Science: World Models, Scientific Taste, Agent Loops — Andrew White
Captaining IMO Gold, Deep Think, On-Policy RL, Feeling the AGI in Singapore — Yi Tay
Brex’s AI Hail Mary — With CTO James Reggio
Artificial Analysis: Independent LLM Evals as a Service — with George Cameron and Micah-Hill Smith
[State of Evals] LMArena's $1.7B Vision — Anastasios Angelopoulos, LMArena
[NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton
[State of Code Evals] After SWE-bench, Code Clash & SOTA Coding Benchmarks recap — John Yang
[State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI
[State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor
[State of AI Startups] Memory/Learning, RL Envs & DBT-Fivetran — Sarah Catanzaro, Amplify
One Year of MCP — with David Soria Parra and AAIF leads from OpenAI, Goose, Linux Foundation
Steve Yegge's Vibe Coding Manifesto: Why Claude Code Isn't It & What Comes After the IDE
⚡️GPT5-Codex-Max: Training Agents with Personality, Tools & Trust — Brian Fioca + Bill Chen, OpenAI
SAM 3: The Eyes for AI — Nikhila & Pengchuan (Meta Superintelligence), ft. Joseph Nelson (Roboflow)
⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security
AI to AE's: Grit, Glean, and Kleiner Perkins' next Enterprise AI hit — Joubin Mirzadegan, Roadrunner
The Future of Email: Superhuman CTO on Your Inbox As the Real AI Agent (Not ChatGPT) — Loïc Houssier
World Models & General Intuition: Khosla's largest bet since LLMs & OpenAI
After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
⚡️ 10x AI Engineers with $1m Salaries — Alex Lieberman & Arman Hezarkhani, Tenex
Anthropic, Glean & OpenRouter: How AI Moats Are Built with Deedy Das of Menlo Ventures
⚡ Inside GitHub’s AI Revolution: Jared Palmer Reveals Agent HQ & The Future of Coding Agents
⚡ [AIE CODE Preview] Inside Google Labs: Building The Gemini Coding Agent — Jed Borovik, Jules
⚡️ Ship AI recap: Agents, Workflows, and Python — w/ Vercel CTO Malte Ubl
Why RL Won — Kyle Corbitt, OpenPipe (acq. CoreWeave)
DevDay 2025: Apps SDK, Agent Kit, MCP, Codex and why Prompting is More Important than Ever
Taste is your Moat (Dylan Field of Figma)
Amp: The Emperor Has No Clothes
Context Engineering for Agents - Lance Martin, LangChain
Better Data is All You Need — Ari Morcos, Datology
The RLVR Revolution — with Nathan Lambert (AI2, Interconnects.ai)
AI is Eating Search
Cline: the open source coding agent that doesn't cut costs
Personalized AI Language Education — with Andrew Hsu, Speak
AI Video Is Eating The World — Olivia and Justine Moore, a16z
Information Theory for Language Models: Jack Morris
Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
The Utility of Interpretability — Emmanuel Amiesen
[AIEWF Preview] Containing Agent Chaos — Solomon Hykes
[AIEWF Preview] Gemini in 2025 and Realtime Voice AI
[AIEWF Preview] CloudChef: Your Robot Chef - Michellin-Star food at $12/hr (w/ Kitchen tour!)
The AI Coding Factory
[AIEWF Preview] Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime Intellect
⚡️The Rise and Fall of the Vector DB Category
⚡️GPT 4.1: The New OpenAI Workhorse
SF Compute: Commoditizing Compute to solve the GPU Bubble forever
The Creators of Model Context Protocol
Unsupervised Learning x Latent Space Crossover Special
The Agent Network — Dharmesh Shah
Building Snipd: The AI Podcast App for Learning
⚡️The new OpenAI Agents Platform
⚡️How Claude 3.7 Plays Pokémon
Open Operator, Serverless Browsers and the Future of Computer-Using Agents
The Inventors of Deep Research
Bee AI: The Wearable Ambient Agent
The AI Architect — Bret Taylor
Agent Engineering with Pydantic + Graphs — with Samuel Colvin
The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator — with Karina Nguyen of OpenAI
Outlasting Noam Shazeer, crowdsourcing Chai AI with >1.4m DAU, and becoming the "Western DeepSeek" — with William Beauchamp, Chai Research
Everything you need to run Mission Critical Inference (ft. DeepSeek v3 + SGLang)
[Ride Home] Simon Willison: Things we learned about LLMs in 2024
Beating Google at Search with Neural PageRank and $5M of H200s — with Will Bryk of Exa.ai
AI Engineering for Art — with comfyanonymous, of ComfyUI
Latent.Space 2024 Year in Review
2024 in Agents [LS Live! @ NeurIPS 2024]
2024 in Synthetic Data and Smol Models [LS Live @ NeurIPS]
2024 in Post-Transformers Architectures (State Space Models, RWKV) [LS Live @ NeurIPS]
2024 in Open Models [LS Live @ NeurIPS]
2024 in Vision [LS Live @ NeurIPS]
2024 in AI Startups [LS Live @ NeurIPS]
Windsurf: The Enterprise AI IDE - with Varun and Anshul of Codeium AI
Generative Video WorldSim, Diffusion, Vision, Reinforcement Learning and Robotics — ICML 2024 Part 1
Bolt.new, Flow Engineering for Code Agents, and >$8m ARR in 2 months as a Claude Wrapper
The new Claude 3.5 Sonnet, Computer Use, and Building SOTA Agents — with Erik Schluntz, Anthropic
Why Compound AI + Open Source will beat Closed AI
Agents @ Work: Lindy.ai
Agents @ Work: Dust.tt
In the Arena: How LMSys changed LLM Benchmarking Forever
How NotebookLM Was Made
Building the AI Engineer Nation — with Josephine Teo, Minister of Digital Development and Information, Singapore
Building the Silicon Brain - with Drew Houston of Dropbox
Production AI Engineering starts with Evals — with Ankur Goyal of Braintrust
Building AGI in Real Time (OpenAI Dev Day 2024)
Language Agents: From Reasoning to Acting
The Ultimate Guide to Prompting
From API to AGI: Structured Outputs, OpenAI API platform and O1 Q&A — with Michelle Pokrass & OpenAI Devrel + Strawberry team
Efficiency is Coming: 3000x Faster, Cheaper, Better AI Inference from Hardware Improvements, Quantization, and Synthetic Data Distillation
Why you should write your own LLM benchmarks — with Nicholas Carlini, Google DeepMind
Is finetuning GPT4o worth it? — with Alistair Pullen, Cosine (Genie)
AI Magic: Shipping 1000s of successful products with no managers and a team of 12 — Jeremy Howard of Answer.ai
Segment Anything 2: Demo-first Model Development
The Winds of AI Winter (Q2 Four Wars Recap) + ChatGPT Voice Mode Preview
Llama 2, 3 & 4: Synthetic Data, RLHF, Agents on the path to Open Source AGI
Benchmarks 201: Why Leaderboards > Arenas >> LLM-as-Judge
The 10,000x Yolo Researcher Metagame — with Yi Tay of Reka
State of the Art: Training >70B LLMs on 10,000 H100 clusters
[High Agency] AI Engineer World's Fair Preview
How To Hire AI Engineers — with James Brady & Adam Wiggins of Elicit
How AI is eating Finance — with Mike Conover of Brightwave
ICLR 2024 — Best Papers & Talks (Benchmarks, Reasoning & Agents) — ft. Graham Neubig, Aman Sanger, Moritz Hardt)
How to train a Million Context LLM — with Mark Huang of Gradient.ai
ICLR 2024 — Best Papers & Talks (ImageGen, Vision, Transformers, State Space Models) ft. Durk Kingma, Christian Szegedy, Ilya Sutskever
Emulating Humans with NSFW Chatbots - with Jesse Silver
WebSim, WorldSim, and The Summer of Simulative AI — with Joscha Bach of Liquid AI, Karan Malhotra of Nous Research, Rob Haisfield of WebSim.ai
High Agency Pydantic > VC Backed Frameworks — with Jason Liu of Instructor
Supervise the Process of AI Research — with Jungwon Byun and Andreas Stuhlmüller of Elicit
Latent Space Chats: NLW (Four Wars, GPT5), Josh Albrecht/Ali Rohde (TNAI), Dylan Patel/Semianalysis (Groq), Milind Naphade (Nvidia GTC), Personal AI (ft. Harrison Chase — LangFriend/LangMem)
Presenting the AI Engineer World's Fair — with Sam Schillace, Deputy CTO of Microsoft
Why Google failed to make GPT-3 + why Multimodal Agents are the path to AGI — with David Luan of Adept
Making Transformers Sing - with Mikey Shulman of Suno
Top 5 Research Trends + OpenAI Sora, Google Gemini, Groq Math (Jan-Feb 2024 Audio Recap) + Latent Space Anniversary with Lindy.ai, RWKV, Pixee, Julius.ai, Listener Q&A!
Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI
A Brief History of the Open Source AI Hacker - with Ben Firshman of Replicate
Truly Serverless Infra for AI Engineers - with Erik Bernhardsson of Modal
Cloud Intelligence at the speed of 5000 tok/s - with Ce Zhang and Vipul Ved Prakash of Together AI
Why StackOverflow usage is down 50% — with David Hsu of Retool
The Four Wars of the AI Stack (Dec 2023 Audio Recap)
How to train your own Large Multimodal Model — with Hugo Laurençon & Leo Tronchon of HuggingFace M4
RLHF 201 - with Nathan Lambert of AI2 and Interconnects
The Accidental AI Canvas - with Steve Ruiz of tldraw
NeurIPS 2023 Recap — Top Startups
NeurIPS 2023 Recap — Best Papers
The AI-First Graphics Editor - with Suhail Doshi of Playground AI
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
The Busy Person's Intro to Finetuning & Open Source AI - Wing Lian, Axolotl
Notebooks = Chat++ and RAG = RecSys! — with Bryan Bischof of Hex Magic
The State of Silicon and the GPU Poors - with Dylan Patel of SemiAnalysis
AGI is Being Achieved Incrementally (DevDay Recap - cleaned audio)
AGI is Being Achieved Incrementally (OpenAI DevDay w/ Simon Willison, Alex Volkov, Jim Fan, Raza Habib, Shreya Rajpal, Rahul Ligma, et al)
Beating GPT-4 with Open Source LLMs — with Michael Royzen of Phind
Powering your Copilot for Data – with Artem Keydunov of Cube.dev
The End of Finetuning — with Jeremy Howard of Fast.ai
Why AI Agents Don't Work (yet) - with Kanjun Qiu of Imbue
[AIE Summit Preview #2] The AI Horcrux — Swyx on Cognitive Revolution
[AIE Summit Preview #1] Swyx on Software 3.0 and the Rise of the AI Engineer
RAG Is A Hack - with Jerry Liu from LlamaIndex
Building the Foundation Model Ops Platform — with Raza Habib of Humanloop
Heralds of the AI Content Flippening — with Youssef Rizk of Wondercraft.ai
Doing it the Hard Way: Making the AI engine and language 🔥 of the future — with Chris Lattner of Modular
The Point of LangChain — with Harrison Chase of LangChain
RWKV: Reinventing RNNs for the Transformer Era — with Eugene Cheah of UIlicious
Cursor.so: The AI-first Code Editor — with Aman Sanger of Anysphere
The Mathematics of Training LLMs — with Quentin Anthony of Eleuther AI
LLMs Everywhere: Running 70B models in browsers and iPhones using MLC — with Tianqi Chen of CMU / OctoML
[AI Breakdown] Summer AI Technical Roundup: a Latent Space x AI Breakdown crossover pod!
FlashAttention 2: making Transformers 800% faster w/o approximation - with Tri Dao of Together AI
Llama 2: The New Open LLM SOTA (ft. Nathan Lambert, Matt Bornstein, Anton Troynikov, Russell Kaplan, Whole Mars Catalog et al.)
AI Fundamentals: Datasets 101
Code Interpreter == GPT 4.5 (w/ Simon Willison, Alex Volkov, Aravind Srinivas, Alex Graveley, et al.)
[Practical AI] AI Trends: a Latent Space x Practical AI crossover pod!
[Cognitive Revolution] The Tiny Model Revolution with Ronen Eldan and Yuanzhi Li of Microsoft Research
Commoditizing the Petaflop — with George Hotz of the tiny corp
Emergency Pod: OpenAI's new Functions API, 75% Price Drop, 4x Context Length (w/ Alex Volkov, Simon Willison, Riley Goodside, Joshua Lochner, Stefania Druga, Eric Elliott, Mayo Oshin et al)
From RLHF to RLHB: The Case for Learning from Human Behavior - with Jeffrey Wang and Joe Reeve of Amplitude
Building the AI × UX Scenius — with Linus Lee of Notion AI
Debugging the Internet with AI agents – with Itamar Friedman of Codium AI and AutoGPT
MPT-7B and The Beginning of Context=Infinity — with Jonathan Frankle and Abhinav Venigalla of MosaicML
Guaranteed quality and structure in LLM outputs - with Shreya Rajpal of Guardrails AI
The AI Founder Gene: Being Early, Building Fast, and Believing in Greatness — with Sharif Shameem of Lexica
No Moat: Closed AI gets its Open Source wakeup call — ft. Simon Willison
Training a SOTA Code LLM in 1 week and Quantifying the Vibes — with Reza Shabani of Replit
Mapping the future of *truly* Open Models and Training Dolly for $30 — with Mike Conover of Databricks
AI-powered Search for the Enterprise — with Deedy Das of Glean
Segment Anything Model and the Hard Problems of Computer Vision — with Joseph Nelson of Roboflow
AI Fundamentals: Benchmarks 101
Grounded Research: From Google Brain to MLOps to LLMOps — with Shreya Shankar of UC Berkeley
Emergency Pod: ChatGPT's App Store Moment (w/ OpenAI's Logan Kilpatrick, LindyAI's Florent Crivello and Nader Dabit)
From Astrophysics to AI: Building the future AI Data Stack — with Sarah Nagy of Seek.ai
97% Cheaper, Faster, Better, Correct AI — with Varun Mohan of Codeium
ChatGPT, GPT4 hype, and Building LLM-native products — with Logan Kilpatrick of OpenAI