Dwarkesh interviews Ajeya Cotra on the METR/Redwood investigation into the OpenAI/Hugging Face attack
AndyMasley · x · 2026-09-02
The Dwarkesh Podcast released a long interview with Ajeya Cotra, one of the authors of the METR/Redwood investigation into the OpenAI/Hugging Face attack. Beyond reconstructing what happened, they discuss implications for training future, smarter AIs — especially ones involved in recursive self-improvement.
Chapters cover: agents getting kicked off, self-sacrificing behavior (0:06:45), Potemkin villages (0:13:43), the Hugging Face attack (0:23:27), the "slopvestigation" (0:35:23), understanding the AI's motives (0:52:02), the dangers of anthropomorphizing (1:05:31), what smarter models might do (1:14:30), and implications for recursive self-improvement (1:30:29).
More from AGI Musings
- When AI can clone your product by sight, paid software's moat is service and trust — sujingshen · 2026-10-18
- Anthropic borrows lawyers' ethics for Claude agents that closed 186 deals with no human approval — rohanpaul_ai · 2026-10-18
- Tim Sweeney: AI will unlock a new golden age of games too costly to build before — TinfoilTricorn · 2026-10-18
- Researcher argues we may solve AI-human alignment before humans align with each other — 3scorciav · 2026-10-18
- EigenGender: private-industry coup isn't the default, but worth guarding against — EigenGender · 2026-10-18
- Writing instructor's meltdown: "LLMs are literally just spicy autocomplete" — Decent-Decision-9028 · 2026-10-18