• Top
  • New

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

by thebeardisredon 1/16/2026, 6:17 AMwith 1 comments

by merksittichon 1/16/2026, 8:14 AM

Discussions on the manuscript/preprint:

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

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