Arch223

Karma: 11

A Rational Proposal

Arch22326 Jan 2026 20:22 UTC

−6 points

0 comments14 min readLW link

Alignment may be localized: a short (and albeitly limited) experiment

Arch22324 Nov 2025 17:48 UTC

18 points

0 comments5 min readLW link

Interpretability is the best path to alignment

Arch2235 Sep 2025 4:37 UTC

2 points

6 comments5 min readLW link

Steering Vectors Can Help LLM Judges Detect Subtle Dishonesty

Leon Eshuijs, mcbeth, Etha and Arch223

3 Jun 2025 20:33 UTC

12 points

1 comment5 min readLW link

Arch223′s Shortform

Arch22318 Nov 2024 1:54 UTC

1 point

1 comment1 min readLW link