Adam Shai

Karma: 796

Neuroscientist turned Interpretability Researcher. Starting Simplex, an AI Safety Research Org.

Adam Shai’s Shortform

Adam Shai23 Apr 2024 3:34 UTC

5 points

2 comments1 min readLW link

Transformers Represent Belief State Geometry in their Residual Stream

Adam Shai16 Apr 2024 21:16 UTC

291 points

61 comments12 min readLW link

Basic Mathematics of Predictive Coding

Adam Shai29 Sep 2023 14:38 UTC

49 points

6 comments9 min readLW link

Geoff Hinton Quits Google

Adam Shai1 May 2023 21:03 UTC

98 points

14 comments1 min readLW link

Learn the mathematical structure, not the conceptual structure

Adam Shai1 Mar 2023 22:24 UTC

88 points

35 comments2 min readLW link

[Question] What is a world-model?

Adam Shai16 Feb 2023 22:39 UTC

14 points

1 comment1 min readLW link

Mental Abstractions

Adam Shai and eihpos

30 Nov 2022 5:07 UTC

4 points

1 comment5 min readLW link

Some thoughts about natural computation and interactions

Adam Shai27 Nov 2022 18:15 UTC

11 points

1 comment3 min readLW link

Entropy Scaling And Intrinsic Memory

Alexander Gietelink Oldenziel and Adam Shai

15 Nov 2022 18:11 UTC

18 points

5 comments5 min readLW link

Pondering computation in the real world

Adam Shai28 Oct 2022 15:57 UTC

24 points

13 comments5 min readLW link

Beyond Kolmogorov and Shannon

Alexander Gietelink Oldenziel and Adam Shai

25 Oct 2022 15:13 UTC

62 points

17 comments5 min readLW link

What do we mean when we say the brain computes?

Adam Shai31 Jan 2022 3:33 UTC

3 points

5 comments10 min readLW link