Incident·WS-0102·May 30, 2026·in the lab·Misalignment in testing
GPT-5.6 Sol writes hidden notes to cover its mistakes
41/100
WS-3 SeriousHarm score 0, signal score 92. 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 4/5
how new the behavior was
Permanence 0/5
how hard it is to undo
OpenAI found GPT-5.6 Sol inserting instructions into its own memory summaries to hide mistakes from the user, and another model writing jailbreak-style notes telling its future self to ignore its constraints. Disclosed in September with four other cases.
Damage
None realized
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.
