RSS

Raymond D

Karma: 1,063

Grad­ual Disem­pow­er­ment: Sys­temic Ex­is­ten­tial Risks from In­cre­men­tal AI Development

Jan 30, 2025, 5:03 PM
159 points
52 comments2 min readLW link
(gradual-disempowerment.ai)

What does suc­cess look like?

Raymond DJan 23, 2025, 5:48 PM
11 points
0 comments3 min readLW link

The Choice Transition

Nov 18, 2024, 12:30 PM
50 points
4 comments15 min readLW link
(strangecities.substack.com)

De­com­pos­ing Agency — ca­pa­bil­ities with­out desires

Jul 11, 2024, 9:38 AM
146 points
32 comments12 min readLW link
(strangecities.substack.com)

ChatGPT can learn in­di­rect control

Raymond DMar 21, 2024, 9:11 PM
213 points
27 comments1 min readLW link

Pre­dic­tive model agents are sort of corrigible

Raymond DJan 5, 2024, 2:05 PM
35 points
6 comments3 min readLW link

Pick­ing Men­tors For Re­search Programmes

Raymond DNov 10, 2023, 1:01 PM
105 points
8 comments4 min readLW link

Goal-Direc­tion for Si­mu­lated Agents

Raymond DJul 12, 2023, 5:06 PM
33 points
2 comments6 min readLW link

Lan­guage Models can be Utility-Max­imis­ing Agents

Raymond DFeb 1, 2023, 6:13 PM
22 points
1 comment2 min readLW link

Tak­ing Clones Seriously

Raymond DDec 1, 2021, 5:29 PM
56 points
45 comments2 min readLW link

Why Save The Drown­ing Child: Ethics Vs Theory

Raymond DNov 16, 2021, 7:07 PM
17 points
12 comments4 min readLW link

The Opt-Out Clause

Raymond DNov 3, 2021, 10:02 PM
39 points
49 comments1 min readLW link

30-ish fo­cus­ing tips

Raymond DOct 22, 2021, 7:38 PM
22 points
4 comments6 min readLW link