
Latent Space
The podcast & newsletter where 170,000+ AI Engineers gather to talk models, tools and ideas. Breaking news today you will use at work tomorrow! Full show notes and newsletter at https://latent.space
Episodes


Inside Abridge: The AI Listening to 100 Million Doctor Visits — Abridge's Janie Lee & Chai Asawa

⚡️ Matt Pocock - Why Engineering Fundamentals matter MORE now

🔬How GPT‑5 derived new results in theoretical physics and quantum gravity — Alex Lupsasca, OpenAI
AI has reached a superhuman milestone in theoretical physics, enabling the rapid resolution of complex problems that previously stumped experts for over a year. Alex Lupsasca, a professor at Vanderbilt University and fellow at OpenAI, details how GPT models now function as creative collaborators, accelerating research ...

⚡️ Competing with ChatGPT and Sierra, building a $10M ARR company — Yasser Elsaid, Founder, Chatbase

The $15B Physical AI Company: Simulation, Autonomy OS, Neural Sim, & 1K Engineers—Applied Intuition
Physical AI development requires a fundamental shift in how software interacts with hardware, moving beyond traditional firmware toward consolidated, safety-critical operating systems. Applied Intuition founders Peter Ludwig and Qasar Younis emphasize that deploying intelligence into moving machines—from autonomous tru...

AI-Native Engineering: 100% adoption, 5x search throughput, unlimited tokens — Mikhail Parakhin
Shopify CTO Mikhail Parakhin details the company's aggressive AI integration, emphasizing that effective AI engineering requires more than just high token consumption. Success hinges on efficient agentic workflows, such as rigorous critique loops where models verify each other's code to minimize production bugs. The co...

🔬 Training Transformers to solve 95% failure rate of Cancer Trials — Ron Alfa & Daniel Bear, Noetik

⚡️ How to turn Documents into Knowledge: Graphs in Modern AI — Emil Eifrem, CEO Neo4J

Notion’s Sarah Sachs & Simon Last on Custom Agents, Evals, and the Future of Work
Notion’s approach to AI agent development centers on building robust, permissioned, and highly integrated systems that function as a "software factory." By iterating through multiple agentic frameworks, the team has moved from rigid, few-shot prompt-based systems to flexible, goal-driven architectures that allow teams ...

⚡️ The best engineers don't write the most code. They delete the most code. — Stay Sassy

Extreme Harness Engineering: 1M LOC, 1B toks/day, 0% human code or review — Ryan Lopopolo, OpenAI
Ryan Lopopolo, a member of the Frontier product exploration team at OpenAI, details the methodology behind "Harness engineering," an emerging discipline focused on deploying autonomous AI agents to manage complex software development lifecycles. By enforcing strict constraints—such as prohibiting manual code writing an...

Marc Andreessen introspects on Death of the Browser, Pi + OpenClaw, and Why "This Time Is Different"
Artificial intelligence represents an "80-year overnight success," culminating decades of foundational research into neural networks and transformer architectures. While the field historically oscillates between utopian and apocalyptic cycles, current breakthroughs in reasoning, agents, and self-improvement signify a p...

Moonlake: Interactive, Multimodal World Models — with Chris Manning and Fan-yun Sun

The Stove Guy: Sam D'Amico Shows New AI Cooking Features on America's Most Powerful Stove at Impulse

Mistral: Voxtral TTS, Forge, Leanstral, & Mistral 4 — w/ Pavan Kumar Reddy & Guillaume Lample

🔬There Is No AlphaFold for Materials — AI for Materials Discovery with Heather Kulik

Dreamer: the Agent OS for Everyone — David Singleton

Anthropic’s Felix Rieseberg on AI Coworkers, Local-First Agents, and the Future of Knowledge Work
The Latent Space podcast features Felix Rieseberg, a product manager at Anthropic, discussing Claude Cowork, a user-friendly version of Cloud Code. Rieseberg highlights the platform's ability to empower non-technical users by enabling them to execute tasks and solve problems through AI. A key decision in developing Cow...

⚡️Monty: the ultrafast Python interpreter by Agents for Agents — Samuel Colvin, Pydantic
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.
