Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
datadrivenangel
82 days ago
|
parent
|
context
|
favorite
| on:
Adaptive LLM routing under budget constraints
the GPT 5 models use ~10x more tokens depending on the reasoning settings.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
