> I'm curious as to how ChatGPT would proceed from a prompt of the form "What would you like to talk about?"
When asking these sorts of questions, and when talking to these models in general, we should remember that they've been fine-tuned to be servile and give answers that are likely to please humans (and with a big helping on censorship on top).
If we are serious about testing their sentience, we should really be talking to the raw models.
When asking these sorts of questions, and when talking to these models in general, we should remember that they've been fine-tuned to be servile and give answers that are likely to please humans (and with a big helping on censorship on top).
If we are serious about testing their sentience, we should really be talking to the raw models.