you are viewing a single comment's thread
view the rest of the comments
[–] 4 points 7 months ago

It's ironic that a lot of the work in this study was done by ChatGPT, basically judging itself on how much of an enabler of schizophrenic delusions it is:

https://github.com/jlcmoore/llm-delusions-annotations

model="openai/gpt-5.1-2025-11-13",

  • source