Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
SwellJoe
75 days ago
|
parent
|
context
|
favorite
| on:
Claude Code sends 33k tokens before reading the pr...
Why turn thinking off? I mean, yes, it uses less tokens, but you're using the best model OpenAI offers, but then making it as dumb as cheaper models.
drtournier
75 days ago
[–]
Interesting question - what I learned doing that is that sol ends up injecting its thinking traces as code and shell terminal comments. YMMV, but in my case what I saw was sufficient to use with my routine work in my projects
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: