GPT-5.5 Bio Bug Bounty

OpenAI has launched the GPT-5.5 Bio Bug Bounty to identify universal jailbreaks related to biosafety risks. Participants can earn rewards up to $25,000 for finding vulnerabilities. This initiative aims to enhance the safety of AI models in biological contexts.

ArchiveLaunch

Signal trust

Single sourceEarly signal

PublishedThursday, April 23, 2026 at 2:00 AMApr 23, 02:00 AM

FreshnessArchive

Story ID#1769

Back to feed Original report

Original article excerpt

Server-side extracted preview paragraphs from the original source.

Explore the GPT-5.5 Bio Bug Bounty: a red-teaming challenge to find universal jailbreaks for bio safety risks, with rewards up to $25,000.

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.

Opening the briefing

GPT-5.5 Bio Bug Bounty

Original article excerpt