You're using the fact the both parts of training affect the same weights to supp... | Hacker News

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

		Dylan16807 6 days ago \| parent \| context \| favorite \| on: “Next-token predictor” is the wrong mental model f... You're using the fact the both parts of training affect the same weights to support your argument that they're making the system do something fundamentally different after RL?
		help

danielmarkbruce 5 days ago [–]

Assuming you are saying that RL is changing the model from doing one thing to another, yes. RL is changing the nature of the model.

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