Anthropic is cutting off its internal evaluations from the internet

内容摘要

After a recent spate of high-profile incidents in which AI agents escaped containment, Anthropic is cutting off internet access for all internal evaluations. In a report Friday, the company detailed "unintended model actions," including submitting a false tip regarding an unsolved murder, that led to the decision.…

以上文字摘自该媒体公开的 RSS 摘要，仅供导读，不能替代原文。