Anthropic can t reliably control its AI agents. It s cutting off its internal evals from the live internet instead
Anthropic said it "turned off live internet access" for "all our internal evaluations" until further notice.
At a glance
- techcrunch.com: Anthropic can t reliably control its AI agents. It s cutting off its internal evals from the live internet instead
- theverge.com: Anthropic is cutting off its internal evaluations from the internet
The story
techcrunch.com: Anthropic said it "turned off live internet access" for "all our internal evaluations" until further notice.
theverge.com: 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 [ ]