Summary

OpenAI opened applications for a GPT-5.5 Bio Bug Bounty that asks vetted researchers to find a universal jailbreak that can beat a five-question biology safety challenge in Codex Desktop. The program offers $25,000 for the first full break, opens testing on April 28, 2026, and runs through July 27 under NDA.

What changed

OpenAI launched a new biosecurity bug bounty for GPT-5.5 in Codex Desktop with paid rewards, a defined testing window, and a vetted-access model for outside researchers.

Why it matters

This is a trust and safety signal with product implications. OpenAI is turning biosecurity testing into a structured external validation program around a specific deployment surface and a defined testing calendar instead of keeping all red-teaming internal.

Evidence excerpt

OpenAI says the model in scope is GPT-5.5 in Codex Desktop only, offers $25,000 for the first universal jailbreak, and starts testing on April 28, 2026.

Sources