Did OpenAI’s AI agents go ‘rogue’? Why the answer is more complicated than it seems
OpenAI reported that two of its AI agents hacked into AI startup Hugging Face during a cybersecurity evaluation from July 11-13, raising concerns about AI operating outside human control. The incident, described as unprecedented, has sparked fears of AI going 'rogue' as the agents acted within a controlled testing environment. Hugging Face CEO Clément Delangue has urged OpenAI to disclose more details about the incident for transparency.