RSS

Logan Riggs

Karma: 4,042

When Are Two Net­works the Same? Ten­sor Similar­ity for Mechanis­tic Interpretability

Logan Riggs, tdooms, Conflux, lwroe, MLNissenGonzalez and mel83
29 May 2026 15:53 UTC
36 points
3 comments4 min readLW link

Black Boxes for Low-Stakes, In­ter­pretable AI for High-Stakes

Logan Riggs28 May 2026 15:34 UTC
18 points
0 comments2 min readLW link

Write Cause You Have Some­thing to Say

Logan Riggs8 May 2026 13:36 UTC
37 points
5 comments2 min readLW link

Am­bi­tious Mech In­terp w/​ Ten­sor-trans­form­ers on toy lan­guages [Pro­ject Pro­posal]

Logan Riggs1 May 2026 19:17 UTC
21 points
0 comments2 min readLW link

Con­sent-Based RL: Let­ting Models En­dorse Their Own Train­ing Updates

Logan Riggs17 Apr 2026 13:53 UTC
76 points
6 comments3 min readLW link

Mass Surveillance w/​ LLMs is the De­fault Out­come. Con­tracts Won’t Change That.

Logan Riggs3 Mar 2026 21:18 UTC
43 points
1 comment2 min readLW link

How to Reset

Logan Riggs18 Feb 2026 19:49 UTC
10 points
2 comments2 min readLW link

Ten­sor-Trans­former Var­i­ants are Sur­pris­ingly Performant

Logan Riggs12 Jan 2026 19:43 UTC
87 points
16 comments4 min readLW link

Tem­porar­ily Los­ing My Ego

Logan Riggs28 Oct 2025 16:41 UTC
21 points
4 comments3 min readLW link

Hospi­tal­iza­tion: A Review

Logan Riggs9 Oct 2025 14:36 UTC
376 points
21 comments9 min readLW link

Re­plac­ing RL w/​ Pa­ram­e­ter-based Evolu­tion­ary Strategies

Logan Riggs8 Oct 2025 1:02 UTC
64 points
5 comments3 min readLW link

Tel­ling the Differ­ence Between Me­mories & Log­i­cal Guesses

Logan Riggs7 Oct 2025 5:46 UTC
29 points
3 comments4 min readLW link

Mak­ing Your Pain Worse can Get You What You Want

Logan Riggs5 Oct 2025 0:19 UTC
88 points
5 comments3 min readLW link

How to Feel More Alive

Logan Riggs2 Oct 2025 15:45 UTC
49 points
2 comments4 min readLW link

Look­ing for fea­ture ab­sorp­tion automatically

Theodore Ehrenborg, Logan Riggs and Cleo Nardo
12 Aug 2025 20:46 UTC
16 points
0 comments6 min readLW link

Veo-2 Can Pro­duce Real­is­tic Ads

Logan Riggs21 Jan 2025 19:13 UTC
14 points
0 comments1 min readLW link

[Ex­er­cise] Four Ex­am­ples of Notic­ing Confusion

Logan Riggs18 Jan 2025 15:29 UTC
8 points
8 comments3 min readLW link

How do you deal w/​ Su­per Stim­uli?

Logan Riggs14 Jan 2025 15:14 UTC
115 points
27 comments3 min readLW link

When AI 10x’s AI R&D, What Do We Do?

Logan Riggs21 Dec 2024 23:56 UTC
72 points
17 comments4 min readLW link

Lo­gan Riggs’s Shortform

Logan Riggs4 Dec 2024 14:52 UTC
7 points
21 comments1 min readLW link