LawrenceC

Karma: 7,189

I do AI Alignment research. Currently at METR, but previously at: Redwood Research, UC Berkeley, Good Judgment Project.

I’m also a part-time fund manager for the LTFF.

Obligatory research billboard website: https://chanlawrence.me/

Maybe I was too harsh on deep learning theory (three days ago)

LawrenceC30 Apr 2026 6:57 UTC

37 points

0 comments4 min readLW link

Not a Paper: “Frontier Lab CEOs are Capable of In-Context Scheming”

LawrenceC29 Apr 2026 3:00 UTC

164 points

4 comments7 min readLW link

a letter of babble

LawrenceC28 Apr 2026 6:22 UTC

32 points

0 comments5 min readLW link

The other paper that killed deep learning theory

LawrenceC27 Apr 2026 6:57 UTC

77 points

1 comment8 min readLW link

The paper that killed deep learning theory

LawrenceC26 Apr 2026 6:55 UTC

176 points

8 comments6 min readLW link

Quick Paper Review: “There Will Be a Scientific Theory of Deep Learning”

LawrenceC25 Apr 2026 6:55 UTC

101 points

3 comments6 min readLW link

Communicating with people who disagree on “obvious” things

LawrenceC24 Apr 2026 6:56 UTC

13 points

3 comments3 min readLW link

An Angry Review of Greg Egan’s “Didicosm”

LawrenceC23 Apr 2026 6:57 UTC

41 points

13 comments5 min readLW link

A “Lay” Introduction to “On the Complexity of Neural Computation in Superposition”

LawrenceC22 Apr 2026 2:26 UTC

33 points

0 comments5 min readLW link

Informal Leadership Structures and AI Safety

LawrenceC21 Apr 2026 6:59 UTC

31 points

3 comments4 min readLW link

Quality Matters Most When Stakes are Highest

LawrenceC20 Apr 2026 6:53 UTC

247 points

21 comments3 min readLW link

Summarizing and Reviewing my earliest ML research paper, 7 years later

LawrenceC19 Apr 2026 6:55 UTC

11 points

0 comments6 min readLW link

Post-mortem’ing my earliest ML research paper, 7 years later

LawrenceC18 Apr 2026 6:41 UTC

39 points

0 comments7 min readLW link

Why I’m Less of a Shill for Related Work Sections

LawrenceC17 Apr 2026 6:49 UTC

22 points

0 comments3 min readLW link

Two Examples of Joy in the Seemingly Mundane

LawrenceC16 Apr 2026 6:48 UTC

17 points

1 comment3 min readLW link

For with what judgment we shall be judged

LawrenceC15 Apr 2026 6:52 UTC

27 points

1 comment4 min readLW link

A Retrospective of Richard Ngo’s 2022 List of Conceptual Alignment Projects

LawrenceC14 Apr 2026 6:58 UTC

39 points

0 comments9 min readLW link

5 Hypotheses for Why Models Fail on Long Tasks

LawrenceC13 Apr 2026 6:54 UTC

18 points

3 comments4 min readLW link

On not being scared of math

LawrenceC12 Apr 2026 5:37 UTC

23 points

0 comments4 min readLW link

Have we already lost? Part 3: Reasons for Optimism

LawrenceC11 Apr 2026 6:58 UTC

25 points

5 comments3 min readLW link