Dmitry Vaintrob

Karma: 2,643

Generalization and infinite width

Dmitry Vaintrob1 Aug 2026 8:41 UTC

30 points

0 comments16 min readLW link

PIRAMID: Progress and Plans

Lauren Greenspan, Ari Brill, TomCarlson, Andrew Mack, Nischal Mainali, Jennifer Lin, Lucas Teixeira and Dmitry Vaintrob

27 Jul 2026 13:08 UTC

48 points

2 comments14 min readLW link

Introducing PIRAMID: Physics-Informed Research for Ambitious Mechanistic Interpretability

Lauren Greenspan, Ari Brill, Andrew Mack, Nischal Mainali, Jennifer Lin, Lucas Teixeira and Dmitry Vaintrob

25 Jul 2026 15:54 UTC

91 points

1 comment6 min readLW link

Learning zero, and what SLT gets wrong about it

Dmitry Vaintrob29 Apr 2026 6:41 UTC

37 points

6 comments13 min readLW link

Mean field sequence: an introduction

Dmitry Vaintrob and Lauren Greenspan

4 Apr 2026 7:30 UTC

74 points

4 comments12 min readLW link

Brown math department postdoctoral position

Dmitry Vaintrob and Eric Larson

16 Mar 2026 1:09 UTC

21 points

0 comments1 min readLW link

A tale of three theories: sparsity, frustration, and statistical field theory

Dmitry Vaintrob25 Jan 2026 18:09 UTC

63 points

0 comments18 min readLW link

Steelmanning heuristic arguments

Dmitry Vaintrob13 Apr 2025 1:09 UTC

77 points

1 comment17 min readLW link

Memorization-generalization in practice

Dmitry Vaintrob30 Jan 2025 14:10 UTC

7 points

1 comment4 min readLW link

Efficiency spectra and “bucket of circuits” cartoons

Dmitry Vaintrob29 Jan 2025 15:06 UTC

20 points

0 comments7 min readLW link

The memorization-generalization spectrum and learning coefficients

Dmitry Vaintrob28 Jan 2025 16:53 UTC

17 points

0 comments10 min readLW link

My supervillain origin story

Dmitry Vaintrob27 Jan 2025 12:20 UTC

123 points

5 comments5 min readLW link

The generalization phase diagram

Dmitry Vaintrob26 Jan 2025 20:30 UTC

28 points

2 comments16 min readLW link

On polytopes

Dmitry Vaintrob25 Jan 2025 13:56 UTC

56 points

5 comments12 min readLW link

QFT and neural nets: the basic idea

Dmitry Vaintrob24 Jan 2025 13:54 UTC

28 points

0 comments8 min readLW link

Writing experiments and the banana escape valve

Dmitry Vaintrob23 Jan 2025 13:11 UTC

34 points

1 comment2 min readLW link

Against blanket arguments against interpretability

Dmitry Vaintrob22 Jan 2025 9:46 UTC

54 points

4 comments7 min readLW link

Logits, log-odds, and loss for parallel circuits

Dmitry Vaintrob20 Jan 2025 9:56 UTC

57 points

4 comments11 min readLW link

Is theory good or bad for AI safety?

Dmitry Vaintrob19 Jan 2025 10:32 UTC

29 points

1 comment5 min readLW link

Renormalization Redux: QFT Techniques for AI Interpretability

Lauren Greenspan and Dmitry Vaintrob

18 Jan 2025 3:54 UTC

47 points

12 comments7 min readLW link