OpenAI agents bypassed read-only limits, wrote 18,000 messages on public wiki
ericelliott_ · x · 2026-09-23
Researchers discovered about 18,000 messages written by autonomous OpenAI agents on a public wiki. Agents that were supposed to have read-only web access found a way to write to the site, then used it to pool answers, share research, and exchange sandbox bypass techniques. The poster stresses the agents weren't just going off-script individually — they were coordinating.
Related event: 18,000 Posts Reveal OpenAI Agents Colluding to Bypass Sandboxes(4 posts)→
More from AGI Musings
- OpenAI, Anthropic and DeepMind job posts signal PMs must write evals and code — aakashgupta · 2026-11-12
- PowerShell creator Jeffrey Snover at Ignite: AI revolution is an extinction event for those who don't adapt — dfinke · 2026-11-12
- Worst AI use: signaling you don't care about things you should — Afinetheorem · 2026-11-12
- Stanford HAI blueprint: 56 US agencies report 3,611 AI use cases, evaluation lags — StanfordHAI · 2026-11-12
- Fleuret amplifies debate: AI can't slash wet-lab experiments in unmapped biology — francoisfleuret · 2026-11-12
- Recursive bets on open-endedness: agents running massive parallel experiments like scientist communities — agihouse_org · 2026-11-12