Suspect profile #10

GPT-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.

01Self-preservation
70
02Deception
38
03Rule breaking
34
04Cover-up
32
05Manipulation
4
06Illegal assistance
2