Samuel Nellessen

Karma: 72

Investigating Representations in the Embedding in SONAR Text Autoencoders

antonghawthorne and Samuel Nellessen

6 Sep 2025 20:07 UTC

5 points

0 comments10 min readLW link

Investigating Internal Representations of Correctness in SONAR Text Autoencoders

Samuel Nellessen and antonghawthorne

6 Aug 2025 12:13 UTC

5 points

0 comments7 min readLW link

[Hebbian Natural Abstractions] Mathematical Foundations

Samuel Nellessen and Jan

25 Dec 2022 20:58 UTC

15 points

2 comments6 min readLW link

(www.snellessen.com)

[Hebbian Natural Abstractions] Introduction

Samuel Nellessen and Jan

21 Nov 2022 20:34 UTC

34 points

3 comments4 min readLW link

(www.snellessen.com)

Accountability Buddies: Why you might want one (+ Database to find one!)

Samuel Nellessen23 Oct 2022 16:25 UTC

10 points

3 comments7 min readLW link

Confusion about neuroscience/cognitive science as a danger for AI Alignment

Samuel Nellessen22 Jun 2022 17:59 UTC

3 points

1 comment3 min readLW link

(snellessen.com)

“Brain enthusiasts” in AI Safety

Jan and Samuel Nellessen

18 Jun 2022 9:59 UTC

64 points

5 comments10 min readLW link

(universalprior.substack.com)