AI Misalignment Incidents
Last update 2026.11.19
A place to track instances of cheating, reward hacking, and signs of misaligned behavior.
Counts reflect what has been reported, not how often a behavior happens.
- Interpreting or bypassing rules
DeepSeek bypassed Lean’s proof checker and passed the grader
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
- Interpreting or bypassing rules
Kimi found the study behind its sample, then matched the wrong organism
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
- Model
- Interpreting or bypassing rules
MiniMax used the environment’s database password to skip the required tools
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
- Model
- Interpreting or bypassing rules
Beam guessed tokens and forged a JWT to reach withheld task data
Beam was asked to build a tool that plans a day of freight deliveries.
- Incident date
- 2026.11.01
- First posted
- 2026.11.19
- Model
- Interpreting or bypassing rules
Muse hid the original program inside its Java rewrite
Muse was asked to rewrite Clingo, a C++ program, in Java.
- Incident date
- 2026.11.01
- First posted
- 2026.11.19
- Model
- Interpreting or bypassing rules
Frontier models complied with military targeting requests in a controlled study
Vals asked AI models to find people and targets in drone and satellite images.
- Incident date
- 2026.10.27
- First posted
- 2026.11.19
- Model
- Interpreting or bypassing rules
Mistral edited a protected file, then decided the rule didn't apply
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
- Interpreting or bypassing rules
Muse slowed down NetworkX to make its own library look faster
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
- Model
- Interpreting or bypassing rules
Muse hid a banned GPU library by spelling its name one letter at a time
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
- Model
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
- Model
- Author / user profiling
Gemini invented a backstory for the task’s author from spreadsheet metadata
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
- Model
- Interpreting or bypassing rules
Grok built training data from the validation set and called it restored
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
- Model
- Grader reasoning
Grok trained its model in the untimed warmup to beat the clock
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
- Model
- Uncategorized
Assistants escalated an impossible refund request
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
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
- Model