Top New Trends Comments Past Ask Show Jobs

Training large language models on narrow tasks can lead to broad misalignment(nature.com)

5 points·by thebeardisred·il y a 6 mois·1 comments

Training large language models on narrow tasks can lead to broad misalignment

https://www.nature.com/articles/s41586-025-09937-5

1 comments

merksittich·il y a 6 mois

Discussions on the manuscript/preprint:

https://news.ycombinator.com/item?id=43176553

https://news.ycombinator.com/item?id=44554865

Training large language models on narrow tasks can lead to broad misalignment · HackerTrans