How did you chose the 8192 token thinking budget? I've often seen Deepseek R1 us... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

guelo 82 days ago | parent | context | favorite | on: Claude 3.7 Sonnet and Claude Code

How did you chose the 8192 token thinking budget? I've often seen Deepseek R1 use way more than that.

freediver 81 days ago [–]

Arbitrary, and even with this budget it is already more verbose (and slower) overall than all the other thinking models - check tokens and latency in the table.

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