RSS

michaelwaves

Karma: 120

Data-Cen­tric In­ter­pretabil­ity for LLM-based Multi-Agent Re­in­force­ment Learning

michaelwaves, Yanjo and Yuqi Sun
6 Feb 2026 19:27 UTC
10 points
0 comments4 min readLW link

AI Mood Ring: A Win­dow Into LLM Emotions

michaelwaves6 Dec 2025 2:56 UTC
7 points
0 comments2 min readLW link

How To De­ploy a (Tiny) AI

michaelwaves1 Dec 2025 6:22 UTC
1 point
0 comments2 min readLW link

I gave LLMs emo­tional damage

michaelwaves29 Nov 2025 8:24 UTC
9 points
1 comment11 min readLW link

AI Teddy Bears: A Brief Investigation

michaelwaves27 Nov 2025 8:24 UTC
35 points
2 comments3 min readLW link

The Eco­nomics of Re­plac­ing Call Cen­ter Work­ers With AIs

michaelwaves25 Nov 2025 21:07 UTC
40 points
9 comments5 min readLW link

Les­sons from build­ing a model or­ganism testbed

joshc, sarun0, Annie Sorkin and michaelwaves
17 Nov 2025 17:58 UTC
20 points
1 comment14 min readLW link

A Work­flow for Sys­tem Prompted Model Organisms

michaelwaves3 Oct 2025 21:39 UTC
1 point
0 comments3 min readLW link

Break­ing GPT-OSS: A brief investigation

michaelwaves12 Sep 2025 7:54 UTC
7 points
0 comments3 min readLW link

michaelwaves’s Shortform

michaelwaves3 Sep 2025 22:12 UTC
1 point
0 comments1 min readLW link