RSS

CBiddulph

Karma: 632

CBid­dulph’s Shortform

CBiddulphJan 30, 2025, 9:35 PM
4 points
18 comments1 min readLW link

[Question] Why not train rea­son­ing mod­els with RLHF?

CBiddulphJan 30, 2025, 7:58 AM
4 points
4 comments1 min readLW link

Wor­ries about la­tent rea­son­ing in LLMs

CBiddulphJan 20, 2025, 9:09 AM
42 points
3 comments7 min readLW link

5 ways to im­prove CoT faithfulness

CBiddulphOct 5, 2024, 8:17 PM
42 points
40 comments6 min readLW link

OpenAI’s Sora is an agent

CBiddulphFeb 16, 2024, 7:35 AM
96 points
25 comments4 min readLW link

Is Me­taethics Un­nec­es­sary Given In­tent-Aligned AI?

CBiddulphSep 2, 2023, 9:48 AM
10 points
0 comments7 min readLW link

Prepar­ing for AI-as­sisted al­ign­ment re­search: we need data!

CBiddulphJan 17, 2023, 3:28 AM
31 points
3 comments1 min readLW link

The Ra­tional Utili­tar­ian Love Move­ment (A His­tor­i­cal Ret­ro­spec­tive)

CBiddulphNov 3, 2022, 7:11 AM
3 points
0 comments1 min readLW link