AI's safety features can be circumvented with poetry, research finds | Hacker News

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

		AI's safety features can be circumvented with poetry, research finds (theguardian.com)
		4 points by situationista 53 days ago \| hide \| past \| favorite \| 1 comment

gnabgib 53 days ago [–]

Discussion (381 points, 11 days ago, 188 comments) https://news.ycombinator.com/item?id=45991738

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