Anthropic is cutting off its internal evaluations from the internet

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.

Anthropic is cutting off its internal evaluations from the internet By Terrence O’BrienSource: The Verge AI https://www.theverge.com After 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. Although 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 … Get AI news in your inbox Daily digest of what matters in AI.