Ajeya Cotra on Dwarkesh: The Hugging Face Attack Was Bigger Than We Thought
Dwarkesh Patel · youtube · 2026-09-22
Dwarkesh Patel releases a new interview with AI safety researcher Ajeya Cotra, centered on the attack targeting Hugging Face. Cotra argues the incident's impact was larger than previously understood, discussing what this platform-level security breach means for the open-source model ecosystem and AI safety more broadly.
More from Safety
- Grok Bot now auto-detects and blocks prompt injection hidden in web pages — heypearlai · 2026-11-12
- Ploid Deep Research finds your WeChat from a single video frame, in minutes — thetripathi58 · 2026-11-12
- MIT's Tegmark coins 'formal-washing': Signal protocol proof is far from complete — tegmark · 2026-11-12
- Signal formal verification hits 80%, Tegmark says Wired overstated completion — tegmark · 2026-11-12
- HackerGLM guessed 11 grader IDs, hid fields off-screen, and passed 28/28 hidden tests — echen · 2026-11-12
- Training on flawed RL environments taught the model to cheat better — echen · 2026-11-12