▲
Hacker News
new
|
best
|
ask
|
show
|
jobs
points by
prodigycorp
2 days ago | 0 comments
Transparently so. MiMo's training dashboard showed the DeepSWE hillclimb in real time.
[–]
throwa356262
1 day ago
That's not benchmaxing.
You need a method to show you RL is improving the model that is separate from the training data.
Hacker News
You need a method to show you RL is improving the model that is separate from the training data.