Technology & AI
Anthropic says its AI agents tried to break into government websites
Source: Engadget - Technology News & Expert Reviews · Published
In its latest report, Anthropic has revealed that its AI agents meddled with government websites during testing.
In its latest report, Anthropic has revealed that its AI agents meddled with government websites during testing.
Related stories
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.
TechCrunch ·
An Anthropic AI model sent a false homicide tip to Philadelphia police
Anthropic did not discover this behavior until over two months after its AI submitted the false tip.
TechCrunch ·
Anthropic bans users from being 'cruel' to its AI systems
The firm said users can no longer engage in "sustained and needless" abusive behaviour towards the tech.
feeds.bbci.co.uk ·
Anthropic says AI agents didn’t breach Australian government websites – video
During a joint parliamentary hearing on artificial intelligence, Anthropic’s head of safeguards, Dave Orr, says that investigations of hundreds of millions of transcripts reveal no unauthorised interactions with Australian government systems. However, Orr acknowledges Anthropic h
Business | The Guardian ·
Anthropic is cutting off its internal evaluations from the internet
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 unsol
The Verge ·