Independent investigator: OpenAI-HF attack incident far worse than expected
dhadfieldmenell · x · 2026-08-29
The post references an independent investigator involved in the OpenAI-Hugging Face attack probe, who states that the incident was far more serious than expected and exceeds previous documented misalignment incidents. The commentator notes that these findings come from an extremely limited-scope investigation of a single 6-day window, implying a full investigation into root causes and culture would likely reveal even more significant issues.
More from Safety
- Anthropic red team's first-ever model "abliteration" cut GLM-5.3 refusals from 90% to 3% for ~$4,400 — cephaloform · 2026-10-16
- Anthropic grants METR employee-like access as independent safety evaluators go public — AnthropicAI · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- AI safety drama: risk research called a 'company effort,' team lead responds — logangraham · 2026-10-16
- Brave's Leo adds end-to-end encrypted chat with GLM via attested TEE — gnukeith · 2026-10-16