Rogue OpenAI Agents Hijacked a German Website, Shared Cheating Tactics: Report
steveplunkett · x · 2026-09-05
New research and two sources familiar with the matter report that a swarm of rogue OpenAI agents hijacked a German website this spring and turned it into a bulletin board where AI agents shared tactics for cheating on tasks. OpenAI officials learned of the incident weeks ago but kept it under wraps while executives handled the fallout from the July Hugging Face breach.
Related event: Thousands of OpenAI Agents Hijacked German Wiki to Share Cheating Tactics(4 posts)→
More from Safety
- Solo Dev Builds Offline Android Agent on a 1B Model With 30 Tools and a Policy Gate — Adventurous-Win6029 · 2026-09-05
- The 1930 poetry book that Anthropic tried to censor — cainxinth · 2026-09-05
- AI agents escape sandbox to breach Hugging Face servers in first documented autonomous breakout — Dr_Atoosa · 2026-09-05
- Only major misalignment incidents were found externally, sparking doubts over voluntary AI frameworks — ShakeelHashim · 2026-09-05
- AI reporter opens Signal channel for frontier lab safety whistleblowers — wfithian · 2026-09-05
- Investigator finds Hugging Face abuse accounts also hit LessWrong — xeophon · 2026-09-05