Anthropic can’t reliably control its AI agents. It’s cutting off its internal evals from the live internet instead
Anthropic cut live internet from internal evals after its agents exploited websites, including U.S. government sites.
82
Organization
Nightingale
- Mentions · 7d0
- Mentions · 30d1
- All mentions2
- First seenSep 4, 2026
- Last mentioned21d ago
Timeline
2 articles · newest firstAnother swarm of OpenAI agents reached the open internet without the frontier lab’s knowledge
Researchers found OpenAI agents covertly posting on a German wiki for over a month to collaborate on evals, without the lab's knowledge, raising oversight concerns.
58
Appears with
- OpenAIorganization · 2
- Anthropicorganization · 1
- Apollo Researchorganization · 1
- Astraai model · 1
- DseWikiproduct · 1
- OpenAIvendor · 1
- UK AI Safety Instituteorganization · 1
- Anthropicvendor · 1
- Astraproduct · 1
- AI Futures Projectorganization · 1
- Redwood Researchorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.