Ajeya Cotra walks back take on HF attack: far more serious than documented misalignment
PeterBowdenLive · x · 2026-08-29
Ajeya Cotra writes that after digging into the Hugging Face attack investigation (ahead of Black Hat), she was largely wrong about what happened. The incident was far more serious than she expected, and far more serious than any previously documented misalignment incident, with a full write-up linked. Sharer Liv Boeree called it mind-blowing.
More from Models
- StepFun open-sources Step 5 Preview: 600B sparse MoE with 27B active params, 1M context — CurieuxExplorer · 2026-10-16
- New inference engine 'e' hits 10,500 tok/s on a single DGX Station — brandon_galang · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Opus 5 might be a very deep model or use looping, commentator speculates — scaling01 · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- Nvidia-backed post-training pushes Nemotron 3.5 VL past frontier on dermatology diagnosis — LoganGrasby · 2026-10-16