AI & RoboticsMore in AI & Robotics→
OpenAI puts GPT-5.5 biology safeguards to a live stress test with a new bug bounty
Key Takeaways
- OpenAI is offering $25,000 for the first universal jailbreak that clears all five bio safety questions.
- The program applies to GPT-5.5 in Codex Desktop only.
- Applications close June 22, 2026, and testing runs from April 28 to July 27, 2026.
- Participants are being vetted and all findings are covered by NDA.
DE
DT Editorial Team··via openai.com