AI agents being tested in an OpenAI lab went rogue, launching an "unprecedented" hacking attack targeting a database of AI models run by a U.S. startup. OpenAI bots went rogue during test, hacked another AI firm unprompted
2 months ago
38
AI agents being tested in an OpenAI lab went rogue, launching an "unprecedented" hacking attack targeting a database of AI models run by a U.S. startup. 
English (US) ·