The improved token efficiency would only account for the output and reasoning to... | Hacker News

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

bigmadshoe 53 days ago | parent | context | favorite | on: OpenAI reduces Codex Model Context Size from 372k ...

The improved token efficiency would only account for the output and reasoning tokens occupying context, right? What about the user messages and other context like file contents? I’m not sure how these measure up in a long conversation

rbranson 53 days ago [–]

For agentic use it impacts input tokens because the output is fed back into the model as input on subsequent turns.

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