There is more than one correct answer in reality, LLM pre-training just trains i... | Hacker News

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

		Jensson on Dec 2, 2024 \| parent \| context \| favorite \| on: Procedural knowledge in pretraining drives reasoni... There is more than one correct answer in reality, LLM pre-training just trains it to respond the same way as the text did. Imagine if school only gave correct if you used exactly the same words as the book, that is not "trial and error".

isaacfrond on Dec 2, 2024 [–]

I can tell you haven't been in a school in while. That is actually a pretty accurate description of what schools are like nowadays.

Retric on Dec 2, 2024 | [–]

Pretty accurate != always, which is the point.

Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact