RSS

darshanav

Karma: 15

SWE and AI safety researcher | CS UChicago

Free will as a model parameter

darshanav8 Jul 2026 21:11 UTC
10 points
1 comment6 min readLW link

Cal­ibrat­ing al­ign­ment evals

darshanav7 Jul 2026 18:24 UTC
9 points
0 comments6 min readLW link