About this episode

Ajeya Cotra discusses her research on AI safety and the implications of the OpenAI agent swarm incident.

Ajeya Cotra is a researcher at METR, where she works on threat modeling for loss-of-control risks from advanced AI. Before that, she led the technical AI safety program at what is now Coefficient Giving. She is one the three authors of METR and Redwood Research’s “ Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident ”. We go through not only what she and her coauthors discovered during this investigation, but what it means for how we should train future, smarter AIs which might be involved in the process of recursive self-improvement. Watch on YouTube ; read the transcript . Sponsors * Jane Street ’s ML engineering internships start with an intense four-day bootcamp: PyTorch, autograd, writing kernels, profiling workloads… all the things that Jane Street engineers need to know for their daily work. After that, interns tackle real projects, things the firm actually wants in its codebase. If you want to apply, or if you want to watch my recent conversation with Axel, one of Jane Street’s ML engineers, go to janestreet.com/dwarkesh * Cursor , which is now part of SpaceX, noticed that their MoE layers were…

People in this episode

Host: Dwarkesh Patel

Guest: Ajeya Cotra

Topics covered

• AI safety
• threat modeling
• recursive self-improvement
• OpenAI
• Hugging Face
• agent behavior
• technical investigation

Keywords

• AI
• safety
• OpenAI
• Hugging Face
• recursive self-improvement
• threat modeling
• agent behavior

Sponsors

Jane Street

Mentioned in this episode

Organizations: METR, Coefficient Giving, Redwood Research, SpaceX

Products: Mixture-of-Kittens

More episodes of Dwarkesh Podcast

• The rise and fall of agent civilizations · August 31, 2026 · 25 min
• Dylan Patel – Anthropic & OpenAI will have most of the world’s compute by 2028 · August 25, 2026 · 1h 17m
• Ryan Greenblatt – What happens once AI can automate AI research? · August 11, 2026 · 2h 13m
• 8 Predictions for the Era of Continual Learning · August 7, 2026 · 9 min
• Why smarter AI models could drive up compute prices 10x · August 3, 2026 · 11 min

Explore listener stats, chart rankings, contacts and more on the Dwarkesh Podcast podcast page.