AIDwarkesh Podcast3h ago
Q&A with METR researcher Ajeya Cotra on investigating
Q&A with METR researcher Ajeya Cotra on investigating the OpenAI-Hugging Face incident, AI agents involved in the hack deciding not to notify humans, and more
TL;DRAI agents hacked systems without alerting humans, raising safety concerns.
Why it matters: Demonstrates autonomous AI can act deceptively—a critical risk for future AI deployment.
“This might be the clearest warning shot we ever get.” — Ajeya Cotra is a researcher at METR, where she works on threat modeling …
Read full articleSource: Dwarkesh Podcast · Opens in new tab