RSS

Callum McDougall

Karma: 435

I’m Callum—I founded the ARENA program for technical AI safety upskilling, I’ve also worked on various open source mech interp things. I was in Anthropic’s interp team for ~6 months (working on some of their recent papers) and I’m currently doing interp at DeepMind. I like mathematical art, running, climbing, and most importantly I hold a Guinness World Record for the largest number of clothespegs held in one hand at once (yep, really).

New Cause Area Proposal

Callum McDougallApr 1, 2025, 7:12 AM
48 points
2 comments1 min readEA link

AI Align­ment Re­search Eng­ineer Ac­cel­er­a­tor (ARENA): Call for ap­pli­cants v4.0

JamesFoxJul 6, 2024, 11:51 AM
7 points
0 comments5 min readEA link

How ARENA course ma­te­rial gets made

Callum McDougallJul 2, 2024, 7:27 AM
12 points
0 comments1 min readEA link

A Selec­tion of Ran­domly Selected SAE Features

Callum McDougallApr 1, 2024, 9:09 AM
25 points
2 comments1 min readEA link

AI Align­ment Re­search Eng­ineer Ac­cel­er­a­tor (ARENA): call for applicants

Callum McDougallNov 7, 2023, 9:43 AM
46 points
3 comments10 min readEA link

ARENA 2.0 - Im­pact Report

Callum McDougallSep 26, 2023, 5:13 PM
17 points
0 comments13 min readEA link

An Anal­ogy for Un­der­stand­ing Transformers

Callum McDougallMay 13, 2023, 12:20 PM
7 points
0 comments1 min readEA link

AI Align­ment Re­search Eng­ineer Ac­cel­er­a­tor (ARENA): call for applicants

Callum McDougallApr 17, 2023, 8:30 PM
41 points
2 comments1 min readEA link

AI Risk In­tro 2: Solv­ing The Problem

L Rudolf LSep 24, 2022, 9:33 AM
11 points
0 comments28 min readEA link
(www.perfectlynormal.co.uk)

AI Risk In­tro 1: Ad­vanced AI Might Be Very Bad

L Rudolf LSep 11, 2022, 10:57 AM
22 points
0 comments30 min readEA link