Anthropic got rid of controlling the thinking budget by parsing your prompt - no... | Hacker News

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

bavell 5 months ago | parent | context | favorite | on: How I use Claude Code: Separation of planning and ...

Anthropic got rid of controlling the thinking budget by parsing your prompt - now it's a setting in /config.

energy123 5 months ago [–]

They never parsed your prompt. The magic word reduces the probability that the token corresponding to the end of chain-of-thought will be emitted, which increases test-time compute.

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