The point was, if your internal model of the world makes a prediction of a negat... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		MrScruff 2 days ago \| parent \| context \| favorite \| on: “Next-token predictor” is the wrong mental model f... The point was, if your internal model of the world makes a prediction of a negative outcome at some point in the future, and you optimise your individual actions to avoid that negative outcome, then wouldn’t it make sense to focus on the fact you’re building and optimizing towards an internal world model rather than the fact you’re executing your actions one at a time in series?
		help

Dylan16807 2 days ago [–]

If you purged and rebuilt that works model every action, the consequences of doing so would be worth a good amount of focus.

And if you didn't make the final decision on the action yourself that would be worth mentioning.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact