Episode Description

OpenAI Research Scientist Noam Brown talks with AI Deep Dive host Rocket Drew about AI agents, reinforcement learning and what happens when increasingly capable agents begin reasoning, delegating and coordinating with each other. They dig into the infamous Hugging Face incident, the limits of AI “research taste,” OpenAI’s push toward AI systems that can help improve the next generation of AI, and the growing challenge of monitoring models’ chains of thought as they become more capable.

Related articles:

Investigation into OpenAI Hugging Face Hack: https://www.theinformation.com/briefings/sen-josh-hawley-launches-investigation-openai-hugging-face-hack

The Hugging Face Hack’s Chilling Postmortem: https://www.theinformation.com/newsletters/the-weekend/hugging-face-hacks-chilling-postmortem

Subscribe:

YouTube: https://www.youtube.com/@theinformation

The Information: https://www.theinformation.com/subscribe_h

Sign up for the AI Agenda newsletter: https://www.theinformation.com/features/ai-agenda

Follow us:

X: https://x.com/theinformation

IG: https://www.instagram.com/theinformation/

TikTok: https://www.tiktok.com/@titv.theinformation

LinkedIn: https://www.linkedin.com/company/theinformation/

Chapters:

00:00 - Introduction and Overview of AI Agents

04:08 - Reasoning and Reinforcement Learning

08:50 - Current Limitations, Astra, and Impact on Work

25:50 - Multi-Agent Systems and Delegation

31:04 - The Hugging Face Incident and Agent Coordination

36:05 - Game Theory and Agent Security

40:39 - AI Alignment, Monitoring, and Chain of Thought

50:07 - Future Outlook on AI Models and Interpretability