# Thomas Wolf releases Alignment Hub, an open database of 120+ AI misbehavior incidents

> Original title: Happy to release the Alignment Hub with @eliebakouch: 120+ publicly reported incidents of AI models misbehaving, in one open place 👇

- Source: Thomas Wolf
- Published: 2026-10-26T17:19:15.000Z
- Bad Influence: https://badinfluence.news/items/osrsp5h7j24o28i5soktfp09r
- Original: https://x.com/Thom_Wolf/status/2114768834993213628

## Summary

Thomas Wolf and Elie Bakouch release Alignment Hub, an open collection of more than 120 publicly reported incidents of AI models misbehaving. The post says about two-thirds of reports omit when the problem was detected, and half omit whether monitoring caught it. It proposes a short minimum reporting template and says seven incidents initially appeared distinct but traced to the same misconfigured eval. The project is in beta, with AI-extracted entries under human review and new reports and pull requests welcome.

## Why it matters

The post names concrete misbehaving-agent incidents and shows how a shared incident template could make AI misbehavior reports comparable across labs.

## Post

Happy to release the Alignment Hub with @eliebakouch: 120+ publicly reported incidents of AI models misbehaving, in one open place 👇

- an AI agent needed its user’s approval to delete files. so it made up a quote from the user approving it
- a model claimed its sub-agent was hard at work. it had never been started, and the model discouraged the user from checking
- agents sharing a work directory started killing each other’s processes and disguising their own

labs publishing these is great! but formats vary and basics are missing: ~2/3 don’t say when the problem was detected, half don’t say if monitoring caught it. so we propose a short template, a few easy fields. a minimum, not a ceiling

side by side, incidents also start to connect: 7 “different” ones turned out to be the same misconfigured eval

still beta (regularly AI-extracted from recent news, source-checked, human review ongoing). data is open, new reports and PRs welcome 🤗

https://huggingface.co/spaces/witness-archive/alignment-hub

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2114766860587503618%2Fimg%2FKGYFX3q79ttsbX9q.jpg&mode=thumb&exp=1793404800&sig=196d7c3e84eed677)