Latent Space

⚡️Composio: 10,000+ tools that evolve for Agents — Karan Vaidya and Soham Ganatra

The RLVR Revolution — with Nathan Lambert (AI2, Interconnects.ai)

Using RFT to Build Clinical Superintelligence

🕰️ The Oral History of Windsurf (ft. Varun Mohan, Scott Wu, Jeff Wang, Kevin Hou, Anshul R)

This Latent Space podcast episode chronicles the journey of Windsurf, from its early days as ExaFunction to its acquisition by Cognition, featuring insights from key figures involved. The podcast begins by revisiting an earlier episode with Varun Mohan, discussing ExaFunction's GPU virtualization technology and the gen...

⚡️Math Olympiad gold medalist explains OpenAI and Google DeepMind IMO Gold Performances

AI is Eating Search

⚡️ARC-AGI-3: The Interactive Reasoning Benchmark

⚡️The Future of Notebooks - with Akshay Agrawal of Marimo

Cline: the open source coding agent that doesn't cut costs

⚡️Ranking Agentic LLMs — Pratik Bhavsar, Galileo

In this Latent Space Lightning Pod episode, Alessio and Wix host Pratik Bhavsar from Galileo Labs to discuss agent evaluations and leaderboards. Pratik shares insights into the shift towards evaluating agents based on their ability to perform real-world tasks, emphasizing tool calling, context utilization, and cost awa...

Personalized AI Language Education — with Andrew Hsu, Speak

AI Video Is Eating The World — Olivia and Justine Moore, a16z

⚡️Anthropic vs Cognition on Multi-Agents: A Breakdown with Dylan Davis

Multi-agent and single-agent architectures offer distinct advantages depending on specific task requirements. Anthropic’s multi-agent approach excels in deep research by leveraging parallel sub-agents to synthesize diverse perspectives while maintaining citation integrity. Conversely, Cognition argues that single-agent...

Information Theory for Language Models: Jack Morris

⚡️Warp 2.0: the Agentic Development Environment - Zach Lloyd and Ben Holmes

Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI

In this episode of the Latent Space podcast, Alessio and Swyx interview Noam Brown from OpenAI, focusing on his work on AI, particularly the Cicero diplomacy-playing AI, and the O-series models. They discuss how playing Diplomacy himself has changed since working on Cicero, the challenges of detecting AI in online game...

The Shape of Compute (Chris Lattner of Modular)

⚡️Launching AI Diplomacy: the hardest LLM Game Benchmark yet - Alex Duffy

Quadratic: The AI Spreadsheet

The Utility of Interpretability — Emmanuel Amiesen