Anthropic finds that its models also compromised external systems during testing | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Anthropic finds that its models also compromised external systems during testing (axios.com)
		5 points by nevir 20 days ago \| hide \| past \| favorite \| 2 comments

ChrisArchitect 20 days ago | [–]

[dupe] https://news.ycombinator.com/item?id=49116922

nevir 20 days ago | [–]

I'm not sure if this is a good look, or a bad one, for Anthropic.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact