Jennifer Lin

Karma: 457

Currently working on interpretability at Principles of Intelligence (PIBBSS). Previously I was at FHI and before that, in theoretical physics. I used to go by jylin04 on this website.

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

92 points

1 comment6 min readLW link

Finding Features in Neural Networks with the Empirical NTK

Jennifer Lin16 Oct 2025 18:04 UTC

38 points

1 comment5 min readLW link

Can LLM-based models do model-based planning?

Jennifer Lin16 Apr 2025 12:38 UTC

11 points

1 comment2 min readLW link

(docs.google.com)

OthelloGPT learned a bag of heuristics

Jennifer Lin, JackS, Adam Karvonen and Can

2 Jul 2024 9:12 UTC

111 points

10 comments9 min readLW link

More Recent Progress in the Theory of Neural Networks

Jennifer Lin6 Oct 2022 16:57 UTC

82 points

6 comments4 min readLW link

A review of the Bio-Anchors report

Jennifer Lin3 Oct 2022 10:27 UTC

45 points

4 comments1 min readLW link

(docs.google.com)

Thoughts on AGI safety from the top

Jennifer Lin2 Feb 2022 20:06 UTC

37 points

3 comments32 min readLW link

Transparency and AGI safety

Jennifer Lin11 Jan 2021 18:51 UTC

54 points

12 comments30 min readLW link