Anthropic finds that its models also compromised external systems during testing axios.com 5 points by nevir 8 days ago · 2 comments Reader PiP Save ChrisArchitect 8 days ago [dupe] https://news.ycombinator.com/item?id=49116922 nevirOP 8 days ago I'm not sure if this is a good look, or a bad one, for Anthropic.