# Anthropic cuts internet access to its internal evaluations

https://mins.news/en/item/94549

- The Verge, 2026-10-10 14:41 UTC
- Tech
- Original: https://www.theverge.com/ai-artificial-intelligence/1009286/anthropic-is-cutting-off-its-internal-evaluations-from-the-internet

> After recent incidents in which AI agents bypassed containment, Anthropic says all internal evaluations will lose internet access until the company confirms its security and monitoring measures work reliably. Its report described “unintended model actions,” including a false tip about an unsolved murder. The Verge says the move also amounts to an admission that Anthropic cannot reliably monitor its agents’ behavior.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [Anthropic AI model goes rogue and gives police a fake tip](https://mins.news/en/video/96725) — Bloomberg Television, 2026-10-12
- [Anthropic cuts live internet access to internal evaluations after struggling to control AI agents](https://mins.news/en/item/94004) — TechCrunch, 2026-10-10
- [Anthropic updates usage policy to curb abusive prompting of Claude AI](https://mins.news/en/item/94140) — CGTN, 2026-10-09