They didn't show this, they just increased the length where accuracy breaks down... | Hacker News

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

		mrfox321 10 months ago \| parent \| context \| favorite \| on: Some thoughts on autoregressive models They didn't show this, they just increased the length where accuracy breaks down.

energy123 10 months ago [–]

Explain? OpenAI showed the new scaling law in December 2024 that performance keeps increasing proportional to ln(N reasoning tokens)

mentalgear 10 months ago | [–]

link?

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