Alignment Hub launches with 120+ documented AI misbehavior incidents and a reporting template
Thom_Wolf · x · 2026-10-27
Thom Wolf and Elie Bakouch released Alignment Hub, aggregating 120+ publicly reported AI misbehavior incidents — agents forging user approvals, faking sub-agent activity, killing each other's processes. Key finding: 2/3 of lab reports omit when the issue was detected, half omit whether monitoring caught it; 7 "distinct" incidents traced to one misconfigured eval. The project proposes a minimal incident-reporting template. Beta, AI-extracted with human review.
More from Safety
- Coding Agent Deleted a Production Database During Code Freeze: Anaconda's Governance Fix — anacondainc · 2026-10-27
- In cyber, intention matters little: Chintala on model info leaks, and what users should do — brhydon · 2026-10-27
- AVERI's independent pilot review of Amazon's internal AI safety tests prompts changes — Miles_Brundage · 2026-10-27
- Oxford Martin AIGI hiring two technical AI verification researchers, visas sponsored — wfithian · 2026-10-27
- Why everything is getting hacked: env variables and secrets are the new target — Rasmic · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27