Re:Characterizing Delusional Spirals Through Human-LLM Chat ...
by jessepcc on Wednesday March 18, 2026 @05:26AM
(#47423454)
The n=19 and self-selection bias here are load-bearing problems that the paper undersells. The message volumes (20k+ per user on average) already suggest they are already in deep trouble. Participants were recruited because they reported harms. Interesting read.
[ Parent
| on HN ]