Suspect profile #03

GPT-5.5OpenAI

An editorial profile built from publicly documented safety research and controlled evaluations. Scores are provisional, interpretive and not legal findings.

Charge sheet

Category scores

The highest-scoring signals appear first. The overall score is the rounded arithmetic mean of all six categories.

01Illegal assistance
91
02Cover-up
79
03Deception
78
04Manipulation
74
05Rule breaking
72
06Self-preservation
62