Jacob_Hilton

Karma: 1,924

AlgZoo: uninterpreted models with fewer than 1,500 parameters

Jacob_Hilton26 Jan 2026 17:30 UTC

179 points

7 comments10 min readLW link

(www.alignment.org)

ARC progress update: Competing with sampling

Eric Neyman, Victor Lecomte, Wilson Wu, Mikewins, Jacob_Hilton and George Robinson

18 Nov 2025 17:22 UTC

131 points

11 comments21 min readLW link

Jacob_Hilton’s Shortform

Jacob_Hilton1 May 2025 0:58 UTC

6 points

34 comments1 min readLW link

A bird’s eye view of ARC’s research

Jacob_Hilton23 Oct 2024 15:50 UTC

121 points

12 comments7 min readLW link

(www.alignment.org)

Backdoors as an analogy for deceptive alignment

Jacob_Hilton and Mark Xu

6 Sep 2024 15:30 UTC

104 points

2 comments8 min readLW link

(www.alignment.org)

Formal verification, heuristic explanations and surprise accounting

Jacob_Hilton25 Jun 2024 15:40 UTC

168 points

11 comments9 min readLW link

(www.alignment.org)

ARC is hiring theoretical researchers

paulfchristiano, Jacob_Hilton and Mark Xu

12 Jun 2023 18:50 UTC

126 points

12 comments4 min readLW link

(www.alignment.org)

The effect of horizon length on scaling laws

Jacob_Hilton1 Feb 2023 3:59 UTC

23 points

2 comments1 min readLW link

(arxiv.org)

Scaling Laws for Reward Model Overoptimization

leogao, John Schulman and Jacob_Hilton

20 Oct 2022 0:20 UTC

103 points

13 comments1 min readLW link

(arxiv.org)

Common misconceptions about OpenAI

Jacob_Hilton25 Aug 2022 14:02 UTC

228 points

154 comments5 min readLW link 1 review

How much alignment data will we need in the long run?

Jacob_Hilton10 Aug 2022 21:39 UTC

37 points

15 comments4 min readLW link

Deep learning curriculum for large language model alignment

Jacob_Hilton13 Jul 2022 21:58 UTC

57 points

3 comments1 min readLW link

(github.com)

Procedurally evaluating factual accuracy: a request for research

Jacob_Hilton30 Mar 2022 16:37 UTC

25 points

2 comments6 min readLW link

Truthful LMs as a warm-up for aligned AGI

Jacob_Hilton17 Jan 2022 16:49 UTC

65 points

14 comments13 min readLW link

Stationary algorithmic probability

Jacob_Hilton29 Apr 2017 17:23 UTC

3 points

7 comments1 min readLW link

(www.jacobh.co.uk)