aha, pozerám to:

"However, it remains unclear how users and chatbots interact over the course of lengthy delusional “spirals,” limiting our ability to understand and mitigate the harm. In our work, we analyze logs of conversations with LLM chatbots from 19 users who report having experienced psychological harms from chatbot use."

Pozrem to ešte, hlavne ma zaujíma že čo teda v tej štúdii zistili, to "prečo" sa to deje, aké mechanizmy v tej interakci to spôsobujú.

každopádne dík za ten link.