RSS

Archie Chaudhury

Karma: 53

The slow death of the ac­cel­er­a­tionist.

Archie Chaudhury6 Apr 2026 3:40 UTC
3 points
1 comment5 min readLW link

Teach­ing Models to Dream of Bet­ter Mon­i­tors through Eval­u­a­tor Con­di­tioned Training

Alec Harris, Kasey C, Archie Chaudhury and yix
19 Mar 2026 21:01 UTC
41 points
2 comments10 min readLW link

A Ra­tional Proposal

Archie Chaudhury26 Jan 2026 20:22 UTC
−2 points
0 comments14 min readLW link

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

Archie Chaudhury24 Nov 2025 17:48 UTC
18 points
0 comments5 min readLW link

In­ter­pretabil­ity is the best path to alignment

Archie Chaudhury5 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 Archie Chaudhury
3 Jun 2025 20:33 UTC
12 points
1 comment5 min readLW link

Arch223′s Shortform

Archie Chaudhury18 Nov 2024 1:54 UTC
1 point
1 comment1 min readLW link