logoalt Hacker News

jvanderbottoday at 12:47 AM1 replyview on HN

Oh, that's somewhat philosophical. The prediction here is a mechanical thing, just random sampling along a pre-calibrated mapping of options given the tokens and their importance weights. That sampling can be called prediction if you use it that way, or it can be called thinking if you are into the psychosis too deeply. Or it can be called a CLI tool command if you're in an agentic framework


Replies

danielmarkbrucetoday at 1:42 AM

No, it's not philsophical. Because if you optimize to predict, you are doing something different to optimizing for a reward. It's a different process - different objective function, different optimization, different set up.