News for hackers. Stuff that matters.
Re:GPT-JSON: Structured and typehinted GPT responses in Python by icyfox on Friday May 05, 2023 @12:10AM (#35825127)
Thanks for the thoughts! I've deployed a few meta models that act like you're describing for second stage predictions, but for fuzzy task definitions have actually seen similar luck with having GPT explicitly explain its rational and then force it to choose a true/false rating. My payloads often end up looking like:

  class Payload:
    reasoning: str = Field(description="Why this value might be true or false),
    answer: bool
Since it's autoregressive I imagine the schema helps to define the universe of what it's supposed to do, then the decoder attention when it's filling the `answer` can look back on the reasoning and weigh the sentiment internally. I imagine the accuracy specifics depend a lot on the end deployment here.

There are no comments on this comment yet.