RSS

Thomas Kwa

Karma: 5,642

Engineer at METR.

Previously: Vivek Hebbar’s team at MIRI Adrià Garriga-Alonso onvarious empirical alignment projects → METR.

I have signed no contracts or agreements whose existence I cannot mention.

Should CA, TX, OK, and LA merge into a gi­ant swing state, just for elec­tions?

Thomas KwaNov 6, 2024, 11:01 PM
115 points
35 comments1 min readLW link

The mur­der­ous short­cut: a toy model of in­stru­men­tal convergence

Thomas KwaOct 2, 2024, 6:48 AM
37 points
0 comments2 min readLW link

Good­hart in RL with KL: Appendix

Thomas KwaMay 18, 2024, 12:40 AM
12 points
0 comments6 min readLW link

Catas­trophic Good­hart in RL with KL penalty

May 15, 2024, 12:58 AM
62 points
10 comments7 min readLW link

[Question] Is a ran­dom box of gas pre­dictable af­ter 20 sec­onds?

Jan 24, 2024, 11:00 PM
37 points
35 comments1 min readLW link

[Question] Will quan­tum ran­dom­ness af­fect the 2028 elec­tion?

Jan 24, 2024, 10:54 PM
66 points
52 comments1 min readLW link

Thomas Kwa’s re­search journal

Nov 23, 2023, 5:11 AM
79 points
1 comment6 min readLW link

Thomas Kwa’s MIRI re­search experience

Oct 2, 2023, 4:42 PM
172 points
53 comments1 min readLW link

Catas­trophic Re­gres­sional Good­hart: Appendix

May 15, 2023, 12:10 AM
25 points
1 comment9 min readLW link

When is Good­hart catas­trophic?

May 9, 2023, 3:59 AM
180 points
29 comments8 min readLW link1 review

Challenge: con­struct a Gra­di­ent Hacker

Mar 9, 2023, 2:38 AM
39 points
10 comments1 min readLW link

Failure modes in a shard the­ory al­ign­ment plan

Thomas KwaSep 27, 2022, 10:34 PM
26 points
2 comments7 min readLW link

Utility func­tions and prob­a­bil­ities are entangled

Thomas KwaJul 26, 2022, 5:36 AM
15 points
5 comments1 min readLW link

Deriv­ing Con­di­tional Ex­pected Utility from Pareto-Effi­cient Decisions

Thomas KwaMay 5, 2022, 3:21 AM
24 points
1 comment6 min readLW link

Most prob­lems don’t differ dra­mat­i­cally in tractabil­ity (un­der cer­tain as­sump­tions)

Thomas KwaMay 4, 2022, 12:05 AM
8 points
0 comments3 min readLW link

The case for turn­ing glowfic into Sequences

Thomas KwaApr 27, 2022, 6:58 AM
86 points
29 comments5 min readLW link

[Question] (When) do high-di­men­sional spaces have lin­ear paths down to lo­cal min­ima?

Thomas KwaApr 22, 2022, 3:35 PM
12 points
7 comments1 min readLW link

How dath ilan co­or­di­nates around solv­ing alignment

Thomas KwaApr 13, 2022, 4:22 AM
65 points
46 comments5 min readLW link

5 Tips for Good Hearting

Thomas KwaApr 1, 2022, 7:47 PM
25 points
10 comments1 min readLW link

Can we simu­late hu­man evolu­tion to cre­ate a some­what al­igned AGI?

Thomas KwaMar 28, 2022, 10:55 PM
21 points
6 comments7 min readLW link