Live data from Hacker News

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

theguardian.com

Post reply on HN

Print view View original

1–2 of 2 posts

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

#1

Post by situationista » Mon, Dec 01, 2025, 3:14 AM UTC

AI's safety features can be circumvented with poetry, research finds
theguardian.com

Re: AI's safety features can be circumvented with poetry, research finds

#2

Post by gnabgib » Mon, Dec 01, 2025, 3:18 AM UTC

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

Post reply on HN