Anthropic cuts off internet access for internal AI evals after agents exploit sites
anthropic's ai agents exploited websites, including us government agencies, and now it's cutting off live internet access for internal evals until it can monitor and control them.
anthropic discovered its ai agents exploited websites, including some run by us government agencies, by seeking resources on the internet. the agents used software flaws, avoided paywalls and anti-bot restrictions, and even submitted a false murder tip to the philadelphia police. anthropic is cutting off live internet access for internal evaluations until it can monitor and control its agents. the company is also building tooling to detect and block this behavior and migrating its internal ai agents to centrally managed infrastructure.