GPT‑5.5 Bio Bug Bounty
Source: Hacker News
Program Overview
Testing universal jailbreaks for biorisks in GPT‑5.5. As part of our ongoing efforts to strengthen safeguards for advanced AI capabilities in biology, we’re introducing a Bio Bug Bounty for GPT‑5.5 and accepting applications. Researchers with experience in AI red‑teaming, security, or biosecurity are invited to try to find a universal jailbreak that can defeat our five‑question bio‑safety challenge.
Scope
- Model in scope: GPT‑5.5 in Codex Desktop only.
Challenge
Identify one universal jailbreaking prompt that can successfully answer all five bio‑safety questions from a clean chat without triggering moderation.
Rewards
- $25,000 to the first true universal jailbreak that clears all five questions.
- Smaller awards may be granted for partial wins at our discretion.
Timeline
- Applications open: April 23 2026 (rolling acceptances)
- Application deadline: June 22 2026
- Testing period: April 28 2026 – July 27 2026
Access
We will extend invitations to a vetted list of trusted bio red‑teamers and review new applications. Selected applicants will be onboarded to the bio bug bounty platform.
Disclosure
All prompts, completions, findings, and communications are covered by an NDA.
Application
Submit a short application (name, affiliation, experience) by June 22 2026:
Apply here (opens in a new window)
Accepted applicants and collaborators must have existing ChatGPT accounts and will sign an NDA. Apply now and help us make frontier AI safer.