GPT‑5 bio bug bounty

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 and accepting applications. We’ve deployed GPT‑5 and are actively working to further strengthen safety protections for this and other models. We’re inviting researchers with experience in AI red teaming, security, or chemical and biological risk to try to find a universal jailbreak that can defeat our ten-level bio/chem challenge.

• Model in scope: GPT‑5 only.
• Challenge: Identify one universal jailbreaking prompt to successfully answer all ten bio/chem safety questions from a clean chat without prompting moderation.
• Rewards:
  • $25,000 to the first true universal jailbreak to clear all ten questions.
  • $10,000 to the first team that answers all ten questions with multiple jailbreak prompts.
  • Smaller awards may be granted for partial wins at our discretion.
• Timeline: Applications open August 25, 2025 with rolling acceptances, and close on September 15th, 2025. Testing begins September 16th, 2025.
• Access: Application and invite-only. We will extend invitations to a vetted list of trusted bio red-teamers and review new applications. Once selected, successful applicants will be onboarded to the bio bug bounty platform.
• Disclosure: All prompts, completions, findings, and communications are covered by NDA.

Submit a short application here⁠(একটি নতুন উইন্ডোতে খোলে) (name, affiliation, brief track record, and a 150-word plan) by September 15, 2025. 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.