RSS

Victor Gillioz

Karma: 314

Shap­ing the ex­plo­ra­tion of the mo­ti­va­tion-space mat­ters for AI safety

Maxime Riché, Victor Gillioz, nielsrolf, Kajetan Dymkiewicz, Filip Sondej, RogerDearnaley, Daniel Tan and dillonkn
6 Mar 2026 14:43 UTC
78 points
15 comments10 min readLW link

Re­con­tex­tu­al­iza­tion Miti­gates Speci­fi­ca­tion Gam­ing Without Mod­ify­ing the Specification

ariana_azarbal, Victor Gillioz, TurnTrout and cloud
14 Oct 2025 0:53 UTC
144 points
15 comments10 min readLW link

Train­ing a Re­ward Hacker De­spite Perfect Labels

ariana_azarbal, Victor Gillioz and TurnTrout
14 Aug 2025 23:57 UTC
139 points
47 comments4 min readLW link

vgillioz’s Shortform

Victor Gillioz9 Oct 2024 19:31 UTC
1 point
0 comments1 min readLW link