RSS

Paul Bricman

Karma: 190

Sealed Com­pu­ta­tion: Towards Low-Fric­tion Proof of Locality

Paul Bricman29 Apr 2025 15:26 UTC
4 points
0 comments10 min readLW link
(noemaresearch.com)

Re­v­erse en­g­ineer­ing the mem­ory lay­out of GPU inference

Paul Bricman9 Apr 2025 15:40 UTC
5 points
0 comments6 min readLW link
(noemaresearch.com)

Join the $10K Au­toHack 2024 Tournament

Paul Bricman25 Sep 2024 11:54 UTC
5 points
0 comments1 min readLW link
(noemaresearch.com)

Towards AI Safety In­fras­truc­ture: Talk & Outline

Paul Bricman7 Jan 2024 9:31 UTC
11 points
0 comments2 min readLW link
(www.youtube.com)

Hash­marks: Pri­vacy-Pre­serv­ing Bench­marks for High-Stakes AI Evaluation

Paul Bricman4 Dec 2023 7:31 UTC
12 points
6 comments16 min readLW link
(arxiv.org)

Ele­ments of Com­pu­ta­tional Philos­o­phy, Vol. I: Truth

Paul Bricman and Tom Feeney
1 Jul 2023 11:44 UTC
12 points
6 comments1 min readLW link
(compphil.github.io)

Cat­a­logu­ing Pri­ors in The­ory and Practice

Paul Bricman13 Oct 2022 12:36 UTC
13 points
8 comments7 min readLW link

(Struc­tural) Sta­bil­ity of Cou­pled Optimizers

Paul Bricman30 Sep 2022 11:28 UTC
25 points
0 comments10 min readLW link

In­ter­lude: But Who Op­ti­mizes The Op­ti­mizer?

Paul Bricman23 Sep 2022 15:30 UTC
15 points
0 comments10 min readLW link

Rep­re­sen­ta­tional Tethers: Ty­ing AI La­tents To Hu­man Ones

Paul Bricman16 Sep 2022 14:45 UTC
30 points
0 comments16 min readLW link

Ide­olog­i­cal In­fer­ence Eng­ines: Mak­ing Deon­tol­ogy Differ­en­tiable*

Paul Bricman12 Sep 2022 12:00 UTC
6 points
0 comments14 min readLW link

Over­sight Leagues: The Train­ing Game as a Feature

Paul Bricman9 Sep 2022 10:08 UTC
20 points
6 comments10 min readLW link

Bench­mark­ing Pro­pos­als on Risk Scenarios

Paul Bricman20 Aug 2022 10:01 UTC
25 points
2 comments14 min readLW link

Steelmin­ing via Analogy

Paul Bricman13 Aug 2022 9:59 UTC
24 points
0 comments2 min readLW link
(paulbricman.com)

[Linkpost] diffu­sion mag­ne­tizes man­i­folds (DALL-E 2 in­tu­ition build­ing)

Paul Bricman7 May 2022 11:01 UTC
1 point
0 comments1 min readLW link
(paulbricman.com)

[Linkpost] Value ex­trac­tion via lan­guage model abduction

Paul Bricman1 May 2022 19:11 UTC
5 points
3 comments1 min readLW link
(paulbricman.com)