Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jupi2142
4 months ago
|
parent
|
context
|
favorite
| on:
Learning to Reason with LLMs
Using codeforces as a benchmark feels like a cheat, since OpenAI use to pay us chump change to solve codeforces questions and track our thought process on jupyter notebook.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
