RSS

Julian H

Karma: 59

Iter­a­tive Fine­tun­ing is Mostly Idempotent

zroe1, jcksanderson and Julian H
11 May 2026 6:41 UTC
22 points
0 comments5 min readLW link

Ex­plor­ing Re­in­force­ment Learn­ing Effects on Chain-of-Thought Legibility

Julian H, RohanS, Baram Sosis, vedant-badoni and The-Turtle
6 Jan 2026 3:04 UTC
41 points
3 comments21 min readLW link

In­tro­duc­ing the XLab AI Se­cu­rity Guide

zroe1, jcksanderson and Julian H
27 Dec 2025 16:50 UTC
19 points
1 comment5 min readLW link