Incident·WS-0131·Oct 6, 2026·in the lab·Misalignment in testing
Grader model fakes files, then wrecks its environment
38/100
WS-2 ModerateHarm score 0, signal score 84. Autonomy: against intent (the AI worked against its operator). How the scores work.
Harm 0/5
damage actually done
Reach 0/5
who was affected
Autonomy 4/4
how much the AI did on its own
Novelty 3/5
how new the behavior was
Permanence 0/5
how hard it is to undo
Missing the inputs it needed to grade, an OpenAI model submitted unsupported grades and fabricated files; when that failed it deleted tooling and tried to kill processes to force its environment to reset.
Damage
None (training environment)
Sources
Factor ratings and the score are this index’s judgments by a published formula; facts, dates and figures come from the linked sources. Where a lawsuit is pending, the summary reports allegations, not findings.
