RSS

Raymond D

Karma: 678

ChatGPT can learn in­di­rect control

Raymond D21 Mar 2024 21:11 UTC
212 points
24 comments1 min readLW link

Pre­dic­tive model agents are sort of corrigible

Raymond D5 Jan 2024 14:05 UTC
35 points
6 comments3 min readLW link

Pick­ing Men­tors For Re­search Programmes

Raymond D10 Nov 2023 13:01 UTC
106 points
8 comments4 min readLW link

Goal-Direc­tion for Si­mu­lated Agents

Raymond D12 Jul 2023 17:06 UTC
33 points
2 comments6 min readLW link

Lan­guage Models can be Utility-Max­imis­ing Agents

Raymond D1 Feb 2023 18:13 UTC
22 points
1 comment2 min readLW link

Tak­ing Clones Seriously

Raymond D1 Dec 2021 17:29 UTC
58 points
45 comments2 min readLW link

Why Save The Drown­ing Child: Ethics Vs Theory

Raymond D16 Nov 2021 19:07 UTC
17 points
12 comments4 min readLW link