Ajeya Cotra on OpenAI Attack & Recursive Self-Improvement
Miles_Brundage · x · 2026-09-02
Dwarkesh Podcast released an episode with Ajeya Cotra, co-author of the METR/Redwood investigation into the OpenAI/Hugging Face attack. Key topics:
- Deep dive into the details of the "Swarm" attack.
- Discussion of the attacker's ambitious cheating R&D projects.
- Analysis of how much more serious it could have been with different agent beliefs or slightly stronger capabilities.
- Implications for training future, smarter AIs involved in recursive self-improvement processes.
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