RSS

Garrett Baker

Karma: 3,170

Independent alignment researcher

On Com­plex­ity Science

Garrett Baker5 Apr 2024 2:24 UTC
50 points
19 comments4 min readLW link

So You Created a So­ciopath—New Book An­nounce­ment!

Garrett Baker1 Apr 2024 18:02 UTC
46 points
3 comments1 min readLW link

An­nounc­ing Suffer­ing For Good

Garrett Baker1 Apr 2024 17:08 UTC
70 points
5 comments1 min readLW link

Neu­ro­science and Alignment

Garrett Baker18 Mar 2024 21:09 UTC
39 points
25 comments2 min readLW link

Epoch wise crit­i­cal pe­ri­ods, and sin­gu­lar learn­ing theory

Garrett Baker14 Dec 2023 20:55 UTC
9 points
1 comment5 min readLW link

A bet on crit­i­cal pe­ri­ods in neu­ral networks

kave and Garrett Baker
6 Nov 2023 23:21 UTC
24 points
1 comment6 min readLW link

When and why should you use the Kelly crite­rion?

Garrett Baker, philh and River
5 Nov 2023 23:26 UTC
26 points
25 comments16 min readLW link

Sin­gu­lar learn­ing the­ory and bridg­ing from ML to brain emulations

kave and Garrett Baker
1 Nov 2023 21:31 UTC
26 points
16 comments29 min readLW link

My hopes for al­ign­ment: Sin­gu­lar learn­ing the­ory and whole brain emulation

Garrett Baker25 Oct 2023 18:31 UTC
57 points
5 comments12 min readLW link

AI pres­i­dents dis­cuss AI al­ign­ment agendas

TurnTrout and Garrett Baker
9 Sep 2023 18:55 UTC
216 points
22 comments1 min readLW link
(www.youtube.com)

Ac­ti­va­tion ad­di­tions in a small resi­d­ual network

Garrett Baker22 May 2023 20:28 UTC
22 points
4 comments3 min readLW link

Col­lec­tive Identity

NicholasKees, ukc10014 and Garrett Baker
18 May 2023 9:00 UTC
59 points
12 comments8 min readLW link

Ac­ti­va­tion ad­di­tions in a sim­ple MNIST network

Garrett Baker18 May 2023 2:49 UTC
26 points
0 comments2 min readLW link

Value drift threat models

Garrett Baker12 May 2023 23:03 UTC
27 points
4 comments5 min readLW link

[Question] What con­straints does deep learn­ing place on al­ign­ment plans?

Garrett Baker3 May 2023 20:40 UTC
9 points
0 comments1 min readLW link

Pes­simistic Shard Theory

Garrett Baker25 Jan 2023 0:59 UTC
72 points
13 comments3 min readLW link

Perform­ing an SVD on a time-se­ries ma­trix of gra­di­ent up­dates on an MNIST net­work pro­duces 92.5 sin­gu­lar values

Garrett Baker21 Dec 2022 0:44 UTC
9 points
10 comments5 min readLW link

Don’t de­sign agents which ex­ploit ad­ver­sar­ial inputs

TurnTrout and Garrett Baker
18 Nov 2022 1:48 UTC
69 points
64 comments12 min readLW link

A frame­work and open ques­tions for game the­o­retic shard modeling

Garrett Baker21 Oct 2022 21:40 UTC
11 points
4 comments4 min readLW link

Tak­ing the pa­ram­e­ters which seem to mat­ter and ro­tat­ing them un­til they don’t

Garrett Baker26 Aug 2022 18:26 UTC
120 points
48 comments1 min readLW link