Here's an article where it link to the chats. And yes, they are vile. https://arstechnica.com/tech-policy/2024/12/chatbots-urged-t...
> 9/10 times these issues are caused by the AI being overly sycophantic and agreeing with the user when the user says insane things.
Repeat after me: an AI for sale should never advocate suicide or agree that it should be a good idea.