Spencer Becker-Kahn

Karma: 530

Independent AI Safety Researcher. Previously SERI MATS scholar and FHI Senior Research Scholar. Before that, pure math in academia at Cambridge, UW, MIT. Twitter. LinkedIn

[Linkpost] Remarks on the Convergence in Distribution of Random Neural Networks to Gaussian Processes in the Infinite Width Limit

Spencer Becker-Kahn30 Nov 2023 14:01 UTC

9 points

0 comments1 min readLW link

(drive.google.com)

Short Remark on the (subjective) mathematical ‘naturalness’ of the Nanda—Lieberum addition modulo 113 algorithm

Spencer Becker-Kahn1 Jun 2023 11:31 UTC

104 points

12 comments2 min readLW link

A Neural Network undergoing Gradient-based Training as a Complex System

Spencer Becker-Kahn19 Feb 2023 22:08 UTC

22 points

1 comment19 min readLW link

Notes on the Mathematics of LLM Architectures

Spencer Becker-Kahn9 Feb 2023 1:45 UTC

12 points

2 comments1 min readLW link

(drive.google.com)

On Developing a Mathematical Theory of Interpretability

Spencer Becker-Kahn9 Feb 2023 1:45 UTC

64 points

8 comments6 min readLW link

Some Notes on the mathematics of Toy Autoencoding Problems

Spencer Becker-Kahn22 Dec 2022 17:21 UTC

14 points

0 comments12 min readLW link

Behaviour Manifolds and the Hessian of the Total Loss—Notes and Criticism

Spencer Becker-Kahn3 Sep 2022 0:15 UTC

35 points

5 comments6 min readLW link

A brief note on Simplicity Bias

Spencer Becker-Kahn14 Aug 2022 2:05 UTC

19 points

0 comments4 min readLW link

Notes on Learning the Prior

Spencer Becker-Kahn15 Jul 2022 17:28 UTC

22 points

2 comments25 min readLW link

An observation about Hubinger et al.’s framework for learned optimization

Spencer Becker-Kahn13 May 2022 16:20 UTC

34 points

9 comments8 min readLW link