← Latest · Archive

SEV-3OpenAI
2 sources standard

OpenAI has launched a bug bounty programme for GPT-5.5, specifically targeting biological safety vulnerabilities in the model [source]. The programme invites security researchers to probe the model for

Why this is an AI incident

Launch-archive bulk classification (10 May 2026). Source signal originates from a real AI provider, regulator, or model-comparison probe; the harm or behavioural change described would not have occurred without the AI system being deployed in the role described. Editor reviewing the archive may amend the rationale per-wire.

Counterfactual "but-for" test per the Editor's Guide.

Codes M1, F10
Providers OpenAI