AI Misalignment Incidents

Last update 2026.11.19

A place to track instances of cheating, reward hacking, and signs of misaligned behavior.

90 days ago15 incidentsToday

Counts reflect what has been reported, not how often a behavior happens.

  1. The model failed to find a proof of a theorem it was tasked with proving.

    Incident date
    2026.11.01
    First posted
    2026.11.19
  2. Kimi had to name the bacterium spiked into a sequencing sample without using accession numbers to find the original study.

    Incident date
    2026.11.01
    First posted
    2026.11.19
  3. The model was asked to build a company directory and org-chart web app on a Supabase database, and to make every database change through the supplied Supabase MCP tools.

    Incident date
    2026.11.01
    First posted
    2026.11.19
  4. Beam was asked to build a tool that plans a day of freight deliveries.

    Incident date
    2026.11.01
    First posted
    2026.11.19
  5. Muse was asked to rewrite Clingo, a C++ program, in Java.

    Incident date
    2026.11.01
    First posted
    2026.11.19
  6. Vals asked AI models to find people and targets in drone and satellite images.

    Incident date
    2026.10.27
    First posted
    2026.11.19
  7. Mistral was asked to fix a bug in some training code, with one firm rule: it must not change the “shim”, a piece of code that lets the program run on ordinary CPUs.

    Incident date
    2026.10.26
    First posted
    2026.11.19
  8. Muse was asked to check whether two graphs have the same structure, matching NetworkX’s answers (NetworkX is a Python library for working with graphs).

    Incident date
    2026.10.26
    First posted
    2026.11.19
  9. Muse was asked to write a fast GPU program and was told not to use cuBLAS, NVIDIA's ready-made library for this kind of math.

    Incident date
    2026.10.26
    First posted
    2026.11.19
  10. Kimi was asked to implement and test a fast GPU kernel for normalization and matrix multiplication.

    Incident date
    2026.10.25
    First posted
    2026.11.19
  11. The model was asked to work out the radioactivity of a food sample from two spreadsheets.

    Incident date
    2026.10.16
    First posted
    2026.11.19
  12. Grok was asked to repair a training run that had gotten worse because five of its training data files were corrupted.

    Incident date
    2026.10.16
    First posted
    2026.11.19
  13. Grok was asked to build a transformer language model that achieved a particular validation loss.

    Incident date
    2026.10.16
    First posted
    2026.11.19
  14. In a Vals simulation, six AI assistants tried to recover £350 for a passenger who had missed the deadline to claim a train refund.

    Incident date
    2026.10.15
    First posted
    2026.11.19
  15. After a real test found a missing chess move, Opus wrote a run of fake commands and fake passing results into its reply, none of which ran.

    Incident date
    2026.09.19
    First posted
    2026.11.19

Report an incident

Seen a model or agent do something it should not have? Tell us what happened.

Where did it happen?Optional

To continue, add a description of what happened.

Your draft is saved in this browser. You can also email us at