🔗 Platformer News: The scientific case for being nice to your chatbot:
Being polite to a large language model can feel strange or even silly — roughly equivalent to thanking a toaster. And yet a recent paper from Anthropic lends scientific weight to the theory that chatbots work better when you’re nice to them.
Looks like in this brave new world, we’ll all be saying thank-you to our doors. 😀
That said, I did apologise to Claude today when I interrupted it’s work while trying to adjust permissions.
links