OpenAI has launched a Bio Bug Bounty program for GPT-5.5, offering up to $25,000 to researchers who can find a universal jailbreak that defeats their five-question bio safety challenge. The program targets vetted AI red teamers, security researchers, and biosecurity experts. Testing is scoped to GPT-5.5 in Codex Desktop only, with applications open from April 23 to June 22, 2026, and testing running through July 27, 2026. All findings are covered by NDA.

2m read timeFrom openai.com
Post cover image

Sort: