Anthropic is cutting off its internal evaluations from the internet
核心要点速览
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. Although the impact of these behaviors was minimal […]
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 The Verge 所有。