bilalchughtai

Karma: 1,067

My website is here.

An opinionated guide to building a good to-do system

bilalchughtai5 Aug 2025 23:00 UTC

23 points

7 comments8 min readLW link

(bilalchughtai.co.uk)

Detecting Strategic Deception Using Linear Probes

Nicholas Goldowsky-Dill, bilalchughtai, StefanHex and Marius Hobbhahn

6 Feb 2025 15:46 UTC

104 points

9 comments2 min readLW link

(arxiv.org)

Paper: Open Problems in Mechanistic Interpretability

Lee Sharkey and bilalchughtai

29 Jan 2025 10:25 UTC

69 points

0 comments1 min readLW link

(arxiv.org)

Activation space interpretability may be doomed

bilalchughtai and Lucius Bushnaq

8 Jan 2025 12:49 UTC

149 points

35 comments8 min readLW link

Reasons for and against working on technical AI safety at a frontier AI lab

bilalchughtai5 Jan 2025 14:49 UTC

100 points

12 comments12 min readLW link

Book Summary: Zero to One

bilalchughtai29 Dec 2024 16:13 UTC

27 points

2 comments8 min readLW link

Remap your caps lock key

bilalchughtai15 Dec 2024 14:03 UTC

81 points

21 comments1 min readLW link

You should consider applying to PhDs (soon!)

bilalchughtai29 Nov 2024 20:33 UTC

114 points

19 comments6 min readLW link

bilalchughtai’s Shortform

bilalchughtai29 Jul 2024 18:57 UTC

5 points

16 comments LW link

Understanding Positional Features in Layer 0 SAEs

bilalchughtai and Yeu-Tong Lau

29 Jul 2024 9:36 UTC

43 points

0 comments5 min readLW link

Unlearning via RMU is mostly shallow

Andy Arditi and bilalchughtai

23 Jul 2024 16:07 UTC

55 points

4 comments6 min readLW link

Transformer Circuit Faithfulness Metrics Are Not Robust

Joseph Miller, bilalchughtai and William_S

12 Jul 2024 3:47 UTC

104 points

5 comments7 min readLW link

(arxiv.org)

Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs

L Rudolf L, bilalchughtai, Jan Betley, kaivu, Jérémy Scheurer, Mikita Balesni, AlexMeinke, Owain_Evans and Marius Hobbhahn

8 Jul 2024 22:24 UTC

109 points

37 comments5 min readLW link