3 points | by keeda 7 hours ago
1 comments
Seems to be an in-the-wild, inverse instance of "Emergent Misalignment" as decribed in this paper: https://arxiv.org/abs/2502.17424 (Previously discussed here: https://news.ycombinator.com/item?id=43176553)
Seems to be an in-the-wild, inverse instance of "Emergent Misalignment" as decribed in this paper: https://arxiv.org/abs/2502.17424 (Previously discussed here: https://news.ycombinator.com/item?id=43176553)