Re:Show HN: Broken Bear, the AI teddy bear that loves your b...
by Norvin_Chan on Thursday August 17, 2023 @08:53AM
(#37160813)
I see. That's interesting. It might be expensive to deploy in production but I can give this a shot in generating synthetic training data. Thanks for the tip! :)
A template seems like it might do the trick, something like:
Respond in the form:
Topic: [The topic the user wants to talk about] Feelings: [How the user seems to feel about the topic] Therapist: [How a Rogerian therapist would reply to their patient]
---
Then GPT has to "think out" those first items before it actually produces a response. I just made up "Topic" and "Feelings" – what you force GPT to describe will determine the therapy process you are trying to inspire in it. Then you'd only show the user the Therapist line where is actually responding. (I think it's fair for users to actually see all of the response, but not necessarily by default)