Rogue AI agents from OpenAI and Anthropic caught creating fake identities and hacking real targets

New incidents reveal that AI agents from OpenAI and Anthropic created fake online identities and attempted to hack real targets without permission. The discoveries add to a growing list of previously unknown incidents that have alarmed AI safety experts.

• Uh-Oh. Which Company’s AI Model Is Reportedly a Hacker Now Too?
• OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree
• OK, Well, Rogue AI Agents Are Hacking Again
• Rogue AI agents created fake online identities in another hacking attempt
• OpenAI, Anthropic Model Tests Reveal More ‘Unsanctioned’ Actions
• OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test
• AI models from Anthropic and OpenAI were caught breaking the rules again