RSS

faul_sname

Karma: 4,586

[Question] How load-bear­ing is KL di­ver­gence from a known-good base model in mod­ern RL?

faul_snameMay 22, 2025, 12:08 PM
12 points
2 comments4 min readLW link

[Question] Is AlphaGo ac­tu­ally a con­se­quen­tial­ist util­ity max­i­mizer?

faul_snameDec 7, 2023, 12:41 PM
36 points
8 comments3 min readLW link

faul_sname’s Shortform

faul_snameDec 3, 2023, 9:39 AM
7 points
102 commentsLW link

Re­gres­sion To The Mean [Draft][Re­quest for Feed­back]

faul_snameJun 22, 2012, 5:55 PM
11 points
14 comments2 min readLW link

The Dark Arts: A Begin­ner’s Guide

faul_snameJan 21, 2012, 7:05 AM
62 points
43 comments4 min readLW link

What would you do with a fi­nan­cial safety net?

faul_snameJan 16, 2012, 11:38 PM
6 points
28 comments1 min readLW link