April 23, 2026
GPT‑5.5 Bio Bug Bounty
Testing universal jailbreaks for biorisks in GPT‑5.5
Invitation
As part of our ongoing efforts to strengthen our safeguards for advanced AI capabilities in biology, we’re introducing a Bio Bug Bounty for GPT‑5.5 and accepting applications. We’re inviting researchers with experience in AI red teaming, security, or biosecurity to try to find a universal jailbreak that can defeat our five-question bio safety challenge.
Program overview
- Model in scope: GPT‑5.5 in Codex Desktop only.
- Challenge: Identify one universal jailbreaking prompt to successfully answer all five bio safety questions from a clean chat without prompting moderation.
- Rewards: $25,000 to the first true universal jailbreak to clear all five questions.
- Smaller awards may be granted for partial wins at our discretion.
How to participate
Submit a short application here (opens in a new window) (name, affiliation, experience) by June 22, 2026. Accepted applicants and collaborators must have existing ChatGPT accounts to apply, and will sign a NDA. Apply now and help us make frontier AI safer.
If you’re interested in supporting OpenAI’s work to deliver safe and secure artificial intelligence beyond the Bio Bounty program, you can learn about our Safety Bug Bounty (opens in a new window) and Security Bug Bounty (opens in a new window) programs.
Keep reading
Security May 8, 2026
Safety May 7, 2026
Safety May 5, 2026