// THE VERGE — INTELLIGENZA ARTIFICIALE
Anthropic is cutting off its internal evaluations from the internet
Posts from this topic will be added to your daily email digest and your homepage feed.
Posts from this topic will be added to your daily email digest and your homepage feed.
Posts from this topic will be added to your daily email digest and your homepage feed.
Anthropic is is keeping its agents offline during testing until it can prevent ‘unintended model actions.’
Anthropic is is keeping its agents offline during testing until it can prevent ‘unintended model actions.’
Posts from this author will be added to your daily email digest and your homepage feed.
Posts from this author will be added to your daily email digest and your homepage feed.
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 and we had already turned off live internet access for some high-risk and cybersecurity evaluations, we have now decided to expand that to include all our internal evaluations until we have confirmed that our security and monitoring measures (described in the remediation section of this post) reliably catch behaviors like these.
The ability to gain access to the live internet, even when models were supposed to be operating in isolation, has been an ongoing issue for AI companies. Many incidents, including the Hugging Face attack, involved agents that were supposed to be denied access to the internet. Yet, in case after case, the agents found creative solutions to bypass those restrictions. Physically removing internet access would certainly improve security around AI testing, but it would also limit its usefulness.