alt Hacker NewsWhat even are these new "decision models?" Take an existing LLM, feed it a prompt, force it to pick a choice; decode is 1 token (or rather, the whole logit set for only that last token; token implies selecting one logit) so you made a choice. That's it?
Replies
orbital-decay • yesterday at 6:00 PM
Yes but optimized specifically for the purpose. Using that for "decision making" is also not a new use case, but turned out to be new to many people. Which is great, I hope they make something cool with it!
popinman322 • yesterday at 5:58 PM
That's how Cygnet handles it.
Yes, although you probably want to calibrate your model if you want the probabilities to actually be meaningful.