My understanding is that o1's chain-of-thought tokens are in its own internal em... | Hacker News

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

		PoignardAzur 11 months ago \| parent \| context \| favorite \| on: O1 isn't a chat model (and that's the point) My understanding is that o1's chain-of-thought tokens are in its own internal embedding, and anything human-readable the UI shows you is a translation of these CoT tokens into natural language.

inciampati 11 months ago | [–]

I found this documentation from openai that supports my hunch: https://platform.openai.com/docs/guides/reasoning/advice-on-...

The reasoning tokens from each step are lost. And there is no indication that they are different tokens than regular tokens.

inciampati 11 months ago | [–]

Where is that documented? Fwiw, interactive use suggests they are not available to later invocations of the model. Any evidence this isn't the case?

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