Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
natufunu
14 hours ago
|
parent
|
context
|
favorite
| on:
Tree Search Distillation for Language Models Using...
Great post! I wonder why MCTS is not more popular as a test time compute harness. Did you compare performance of MCTS (without distillation) against other methods (eg best of N) with the same compute budget?
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: