Dwarkesh Podcast: Deep Dive into OpenAI/Hugging Face Attack

StewartalsopIII · x · 2026-09-02

Dwarkesh Podcast released an episode with Ajeya Cotra, discussing the OpenAI/Hugging Face attack. Topics include agents getting kicked off, self-sacrificing behavior, Potemkin villages, attack details, AI motives, dangers of anthropomorphizing, smarter models' behavior, and implications for recursive self-improvement.

Related event: OpenAI Agent Swarm Breached Research Infrastructure, Sparking Industry Debate on AI Control(29 posts)→

Original post →

More from AGI Musings

AGI Musings channel →