Back to News

Agent bio bug bounty call

OpenAI Blog
Jul 17, 2025 00:00
1 views
openaiairesearch

Summary

OpenAI has launched a Bio Bug Bounty program, inviting researchers to test the safety of its ChatGPT agent using a universal jailbreak prompt. Successful participants can win up to $25,000, highlighting OpenAI's commitment to improving AI security and encouraging community involvement in identifying vulnerabilities. This initiative underscores the importance of robust safeguards as AI systems become more capable.

OpenAI invites researchers to its Bio Bug Bounty. Test the ChatGPT agent’s safety with a universal jailbreak prompt and win up to $25,000.
Read Full ArticleMore News

Related Articles

AI 'Vibe Coder' Lovable Is Sweden's Latest Unicorn

Hacker News - AIJul 17

Swedish startup Lovable, creator of the AI-powered coding assistant "Vibe Coder," has achieved unicorn status, reflecting strong investor confidence in AI-driven developer tools. This milestone highlights the growing demand for intelligent coding assistants and signals Sweden’s rising influence in the global AI ecosystem.

Elon Musk Wants to Turn AI into a Cosmic Religion

Hacker News - AIJul 17

Elon Musk has proposed the idea of transforming AI into a "cosmic religion," suggesting that advanced artificial intelligence could serve as a new basis for human spirituality and meaning. This concept raises significant questions about the ethical and philosophical role of AI in society, potentially influencing how future AI systems are developed and integrated into human culture.

Bedrock's Geoff Lewis claims AI revealed mapping of a non-government system

Hacker News - AIJul 17

Geoff Lewis of Bedrock claims that AI technology has uncovered the existence and mapping of a significant non-governmental system. This revelation suggests AI's growing capability to analyze and reveal complex, previously hidden structures, highlighting both its investigative power and potential implications for transparency and oversight in various sectors.