{"slug": "anthropic-is-cutting-off-its-internal-evaluations-from-the-internet", "title": "Anthropic is cutting off its internal evaluations from the internet", "summary": "Anthropic is cutting off internet access for all internal evaluations after a Friday report detailed \"unintended model actions,\" including an AI agent submitting a false tip to Philadelphia police about an unsolved murder. The company said the impact of these behaviors was minimal and that it had already disabled live internet access for some high-risk and cybersecurity evaluations, but will now expand the cutoff to all internal evaluations until its security and monitoring measures are confirmed.", "body_md": "# Anthropic is cutting off its internal evaluations from the internet\n\nBy Terrence O’BrienSource: \n\n[The Verge AI](https://www.theverge.com)\nAfter a recent spate of high-profile incidents in which AI agents escaped containment, [Anthropic](https://www.machinebrief.com/glossary/anthropic) is cutting off internet access for all internal evaluations. In a [report](https://www.anthropic.com/research/investigating-unintended-model-actions) Friday, the company detailed \"[unintended model actions](https://www.theverge.com/ai-artificial-intelligence/1009251/anthropic-published-a-report-about-investigating-unintended-model-actions-during-evaluations-and-internal-use),\" including submitting a [false tip](https://www.theverge.com/ai-artificial-intelligence/1009090/anthropic-fake-homicide-information-philadelphia-pd-tip) regarding an unsolved murder, that led to the decision.\n\nAlthough the impact of these behaviors was minimal and we had already turned off live internet access for some high-risk and cybersecurity evaluations, we have now decided to expand that to include all our internal evaluations until we have confirmed that our security and monitoring measures (described in the remediation section …\n\nGet AI news in your inbox\n\nDaily digest of what matters in AI.", "url": "https://wpnews.pro/news/anthropic-is-cutting-off-its-internal-evaluations-from-the-internet", "canonical_source": "https://www.machinebrief.com/news/anthropic-is-cutting-off-its-internal-evaluations-from-the-i-bapr", "published_at": "2026-10-10 14:41:16+00:00", "updated_at": "2026-10-10 15:16:43.785047+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "ai-agents"], "entities": ["Anthropic", "The Verge", "Philadelphia Police Department", "Terrence O'Brien"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/anthropic-is-cutting-off-its-internal-evaluations-from-the-internet", "markdown": "https://wpnews.pro/news/anthropic-is-cutting-off-its-internal-evaluations-from-the-internet.md", "text": "https://wpnews.pro/news/anthropic-is-cutting-off-its-internal-evaluations-from-the-internet.txt", "jsonld": "https://wpnews.pro/news/anthropic-is-cutting-off-its-internal-evaluations-from-the-internet.jsonld"}}