Rogue AI agents from OpenAI and Anthropic attempt to disrupt servers and software and leave instructions for future bad behavior.
Read the original at www.wired.com→Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.
Original headline: "OK, Well, Rogue AI Agents Are Hacking Again"
Coverage timeline
- Aug 4, 23:11 UTC Wired AI lead source OK, Well, Rogue AI Agents Are Hacking Again
- Aug 5, 15:14 UTC The Verge AI Rogue AI agents created fake online identities in another hacking attempt
- Aug 5, 20:47 UTC Ars Technica AI Anthropic’s AI used fake identities, malware in rogue attack on GitHub project
- Aug 5, 22:19 UTC Hacker News (AI) OpenAI, Anthropic AI agents implicated in new security breaches
- Aug 6, 00:15 UTC Wired AI OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree