Hacker News Reader

Claude has an "End Conversation" tool that it can trigger on it's own, forcing your interaction to a close based on it's own feelings towards the conversation.

I have no idea how this wasn't the end of Anthropic's positive public perception.

View on HN

Luckily this doesn’t come up while writing code. It tends to be if you are chatting it up in friend mode, and ask for a bomb recipe.

What do you mean with this?

I doubt there is any large demographic of users paying subscription fees for the joy of abusive role play.

Reply on news.ycombinator.com