RSS

Caleb Biddulph

Karma: 1,396

MATS 8.1 scholar, mentored by Micah Carroll. Former SWE at Google Gemini. Founding president of Cornell Effective Altruism.

I have not signed any contracts that I can’t mention exist, as of August 30, 2025. I’ll try to update this statement at least once a year, so long as it’s true. I added this statement thanks to the one in the gears to ascension’s bio.

LLMs as am­plifiers, not assistants

Caleb Biddulph19 Jun 2025 17:21 UTC
27 points
8 comments7 min readLW link

[Question] What was so great about Move 37?

Caleb Biddulph29 May 2025 7:00 UTC
24 points
4 comments3 min readLW link

Pro­ce­du­ral vs. Causal Understanding

Caleb Biddulph29 May 2025 7:00 UTC
7 points
2 comments2 min readLW link

Ves­ti­gial rea­son­ing in RL

Caleb Biddulph13 Apr 2025 15:40 UTC
54 points
8 comments9 min readLW link

Caleb Bid­dulph’s Shortform

Caleb Biddulph30 Jan 2025 21:35 UTC
4 points
47 comments1 min readLW link

[Question] Why not train rea­son­ing mod­els with RLHF?

Caleb Biddulph30 Jan 2025 7:58 UTC
4 points
4 comments1 min readLW link

Wor­ries about la­tent rea­son­ing in LLMs

Caleb Biddulph20 Jan 2025 9:09 UTC
45 points
6 comments7 min readLW link

5 ways to im­prove CoT faithfulness

Caleb Biddulph5 Oct 2024 20:17 UTC
46 points
40 comments6 min readLW link

OpenAI’s Sora is an agent

Caleb Biddulph16 Feb 2024 7:35 UTC
98 points
25 comments4 min readLW link

Is Me­taethics Un­nec­es­sary Given In­tent-Aligned AI?

Caleb Biddulph2 Sep 2023 9:48 UTC
12 points
0 comments7 min readLW link

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

Caleb Biddulph17 Jan 2023 3:28 UTC
31 points
3 comments11 min readLW link

The Ra­tional Utili­tar­ian Love Move­ment (A His­tor­i­cal Ret­ro­spec­tive)

Caleb Biddulph3 Nov 2022 7:11 UTC
3 points
0 comments1 min readLW link
(ratutilove.substack.com)