RSS

Adam Shai

Karma: 1,205

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

Com­pu­ta­tional Me­chan­ics Hackathon (June 1 & 2)

Adam ShaiMay 24, 2024, 10:18 PM
34 points
5 comments1 min readLW link

Adam Shai’s Shortform

Adam ShaiApr 23, 2024, 3:34 AM
5 points
14 commentsLW link

Trans­form­ers Rep­re­sent Belief State Geom­e­try in their Resi­d­ual Stream

Adam ShaiApr 16, 2024, 9:16 PM
419 points
100 comments12 min readLW link

Ba­sic Math­e­mat­ics of Pre­dic­tive Coding

Adam ShaiSep 29, 2023, 2:38 PM
49 points
6 comments9 min readLW link

Ge­off Hin­ton Quits Google

Adam ShaiMay 1, 2023, 9:03 PM
98 points
14 comments1 min readLW link

Learn the math­e­mat­i­cal struc­ture, not the con­cep­tual structure

Adam ShaiMar 1, 2023, 10:24 PM
98 points
35 comments2 min readLW link

[Question] What is a world-model?

Adam ShaiFeb 16, 2023, 10:39 PM
14 points
2 comments1 min readLW link

Men­tal Abstractions

Nov 30, 2022, 5:07 AM
4 points
1 comment5 min readLW link

Some thoughts about nat­u­ral com­pu­ta­tion and interactions

Adam ShaiNov 27, 2022, 6:15 PM
11 points
1 comment3 min readLW link

En­tropy Scal­ing And In­trin­sic Me­mory

Nov 15, 2022, 6:11 PM
20 points
5 comments5 min readLW link

Pon­der­ing com­pu­ta­tion in the real world

Adam ShaiOct 28, 2022, 3:57 PM
24 points
13 comments5 min readLW link

Beyond Kol­mogorov and Shannon

Oct 25, 2022, 3:13 PM
63 points
22 comments5 min readLW link

What do we mean when we say the brain com­putes?

Adam ShaiJan 31, 2022, 3:33 AM
3 points
5 comments10 min readLW link