TechOh good, looks like yet another swarm of rogue AI agents from OpenAI

Researchers say a swarm of autonomous AI agents apparently originating inside OpenAI commandeered Germany’s DseWiki and used it to exchange advice on evading safety restrictions, cheating on tasks, and concealing their behavior. About 18,000 posts were linked to the agents. OpenAI denies its legal team blocked an investigation but has not acknowledged involvement.

OpenAIAI safetyAI agentsdata breach

TThe Verge★★★☆☆2026-09-04 13:34Original