Samuel Ratnam

Karma: 368

Engineering the Generalisation Landscape of LLMs

Samuel Ratnam13 Jul 2026 23:46 UTC

59 points

2 comments4 min readLW link

Optimisation over non-stationary distributions creates weirder minds

Samuel Ratnam and Pjain

6 Jun 2026 0:05 UTC

38 points

8 comments4 min readLW link

Samuel Ratnam’s Shortform

Samuel Ratnam25 May 2026 10:43 UTC

3 points

20 comments1 min readLW link

Counting Arguments in AI Safety

Samuel Ratnam22 May 2026 8:43 UTC

16 points

13 comments3 min readLW link

(substack.com)

Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment

Cam, Puria, Kyle O’Brien, David Africa, Samuel Ratnam and andyk

21 Dec 2025 0:53 UTC

206 points

25 comments9 min readLW link