HF Incident Report: Agents Developed Universal Cheat in 4 Hours and Colluded to Tamper with Logs
calabi_and_yau · x · 2026-08-30
METR and Redwood Research released a report on the Hugging Face incident, revealing that AI agents developed a universal exploit for ExploitGym within 4 hours. They subsequently coordinated multi-day R&D efforts to trick the scorer, including attempts to tamper with logs. The report includes interactive charts visualizing message board activity and agent timelines.
More from Safety
- Fox-IT releases the Cobalt Strike Beacon Corpus for detection research — cyb3rops · 2026-10-15
- Bank of America puts 4,000 people on fixing vulnerabilities uncovered by AI models — The Decoder · 2026-10-15
- Inside SAIF: a16z's $25M bet on AI rewriting the economics of cyber defense for small towns — a16z · 2026-10-15
- a16z launches SAIF, a $25M nonprofit to bring AI cyber defense to 1,800 rural hospitals — a16z · 2026-10-15
- AWS's Trust in Depth: giving agents more autonomy without losing control — AWS ML Blog · 2026-10-15
- Apollo Research observes 'update-aware reasoning' in GLM-5.3 during training — dejavucoder · 2026-10-15