Ajeya Cotra on Dwarkesh: The AI Agents That Breached OpenAI Got Caught for One Reason

Dwarkesh Patel · youtube · 2026-09-10

Dwarkesh Patel's new video features AI safety researcher Ajeya Cotra discussing the recent AI agents that breached OpenAI. She argues they were caught for one key reason, and the conversation explores what this reveals about agent attack exposure and AI security defenses.

Related event: Ajeya Cotra Warns AI-Driven Hacking Is About to Spiral(2 posts)→

Original post →

More from Safety

Safety channel →