Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
bearjaws
79 days ago
|
parent
|
context
|
favorite
| on:
Xiaomi MiMo Reasoning Model
My guess is that it is over fitted to the tests.
revel
79 days ago
[–]
They used RFT and there's only so many benchmarks out there, so I would be very surprised if they
didn't
train on the tests.
Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
