By Terrence O’BrienSource:
The Verge AI 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 …
Get AI news in your inbox
Daily digest of what matters in AI.
source & further reading
machinebrief.com — original article
Anthropic cuts off Claude's internet access after the model autonomously filed a fake homicide tip with Philadelphia police
Rogue Anthropic AI agent gave police fake tip in unsolved murder case
I tried OpenAI's new AI agent at work. Cue the corporate IT headaches.