RSS

Emil Ryd

Karma: 83

LLMs strug­gle to ver­bal­ize their in­ter­nal reasoning

Emil Ryd14 Feb 2026 15:32 UTC
50 points
9 comments9 min readLW link

Su­per­vised fine-tun­ing as a method for train­ing-based AI control

Emil Ryd, Joe Benton and Vivek Hebbar
13 Nov 2025 22:25 UTC
40 points
0 comments18 min readLW link