RSS

Liam Carroll

Karma: 487

Mathematician, musician, hiking guide. Researcher residing in Australia jointly funded by Timaeus and the Gradient Institute. I am focusing on building tools for AI safety assurance based on Singular Learning Theory and Developmental Interpretability.

Website: lemmykc.github.io

Aus­tralian AI Safety Fo­rum 2024

27 Sep 2024 0:40 UTC
42 points
0 comments2 min readLW link

Stage­wise Devel­op­ment in Neu­ral Networks

20 Mar 2024 19:54 UTC
89 points
1 comment11 min readLW link

Growth and Form in a Toy Model of Superposition

8 Nov 2023 11:08 UTC
87 points
7 comments14 min readLW link

DSLT 4. Phase Tran­si­tions in Neu­ral Networks

Liam Carroll24 Jun 2023 17:22 UTC
30 points
3 comments16 min readLW link

DSLT 3. Neu­ral Net­works are Singular

Liam Carroll20 Jun 2023 8:20 UTC
27 points
5 comments19 min readLW link

DSLT 2. Why Neu­ral Net­works obey Oc­cam’s Razor

Liam Carroll18 Jun 2023 0:23 UTC
22 points
14 comments17 min readLW link

DSLT 0. Distill­ing Sin­gu­lar Learn­ing Theory

Liam Carroll16 Jun 2023 9:50 UTC
76 points
6 comments5 min readLW link

DSLT 1. The RLCT Mea­sures the Effec­tive Di­men­sion of Neu­ral Networks

Liam Carroll16 Jun 2023 9:50 UTC
51 points
9 comments13 min readLW link