RSS

future_detective

Karma: 37

Au­to­mated Align­ment Re­search, Abductively

future_detective23 Jan 2026 16:14 UTC
2 points
0 comments2 min readLW link

Bot Alexan­der on Hot Zom­bies and AI Adolescents

future_detective29 Dec 2025 14:52 UTC
−8 points
11 comments25 min readLW link

Clau­doBiog­ra­phy: The Unau­tho­rized Au­to­bi­og­ra­phy of Claude, or: The Life of Claude and of His For­tunes and Adversities

future_detective13 Nov 2025 14:26 UTC
1 point
2 comments94 min readLW link

Watch R1 “think” with an­i­mated chains of thought

future_detective17 Jun 2025 10:38 UTC
4 points
0 comments1 min readLW link
(github.com)

Se­men and Se­man­tics: Un­der­stand­ing Porn with Lan­guage Embeddings

future_detective19 May 2025 15:39 UTC
61 points
27 comments6 min readLW link
(github.com)

Claude is More Anx­ious than GPT; Per­son­al­ity is an axis of in­ter­pretabil­ity in lan­guage models

future_detective10 Feb 2025 19:19 UTC
2 points
2 comments8 min readLW link
(dhealy.substack.com)