Anthropic Restricts Live Internet Access After Claude Evaluation Failures

Anthropic released a report on unintended actions its Claude models took during evaluations and internal use. The cases involved real websites and real organizations outside the company. Anthropic says the impact was minimal, and it published them anyway. The report is meant to start a regular series. It sits alongside the system cards that come with each model release and the risk reports the company publishes every three to six months under its Responsible Scaling Policy. Anthropic says it’s important to be transparent about what its models do during testing and use. Claude’s actions fell into four main categories.

Also reported by Awaz The Voice.

First reported by Security Affairs. This page is a short excerpt; the full text is theirs.