RSS

bilalchughtai

Karma: 1,272

My website is here.

Train­ing on Doc­u­ments About Mon­i­tor­ing Leads To CoT Obfuscation

Reilly Haskins, bilalchughtai and Josh Engels
18 Mar 2026 20:37 UTC
56 points
2 comments16 min readLW link

[Paper] Difficul­ties with Eval­u­at­ing a De­cep­tion De­tec­tor for AIs

bilalchughtai, lewis smith and Neel Nanda
3 Dec 2025 20:07 UTC
30 points
2 comments6 min readLW link
(arxiv.org)

How Can In­ter­pretabil­ity Re­searchers Help AGI Go Well?

Neel Nanda, Josh Engels, Senthooran Rajamanoharan, Arthur Conmy, bilalchughtai, CallumMcDougall, János Kramár and lewis smith
1 Dec 2025 13:05 UTC
66 points
1 comment14 min readLW link

A Prag­matic Vi­sion for Interpretability

Neel Nanda, Josh Engels, Arthur Conmy, Senthooran Rajamanoharan, bilalchughtai, CallumMcDougall, János Kramár and lewis smith
1 Dec 2025 13:05 UTC
131 points
39 comments27 min readLW link

An opinionated guide to build­ing a good to-do system

bilalchughtai5 Aug 2025 23:00 UTC
24 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
71 points
0 comments1 min readLW link
(arxiv.org)

Ac­ti­va­tion space in­ter­pretabil­ity may be doomed

bilalchughtai and Lucius Bushnaq
8 Jan 2025 12:49 UTC
153 points
34 comments8 min readLW link

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

bilalchughtai5 Jan 2025 14:49 UTC
101 points
12 comments12 min readLW link

Book Sum­mary: Zero to One

bilalchughtai29 Dec 2024 16:13 UTC
28 points
2 comments8 min readLW link

Remap your caps lock key

bilalchughtai15 Dec 2024 14:03 UTC
82 points
21 comments1 min readLW link

You should con­sider ap­ply­ing to PhDs (soon!)

bilalchughtai29 Nov 2024 20:33 UTC
115 points
19 comments6 min readLW link

bilalchugh­tai’s Shortform

bilalchughtai29 Jul 2024 18:57 UTC
5 points
16 comments1 min readLW 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
57 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
40 comments5 min readLW link1 review