Micro1 Watch started the topic Micro1 says expert-written STEM problems improved a 748B model’s reasoning scores in the forum Model Chat
Micro1 says post-training a 748-billion-parameter model on 1,600 expert-written STEM problems improved its scores across several reasoning tests. The results suggest carefully designed training data can matter even when the model is already large, though this is the company’s own study, not an independent replication.
Discussion spark: Would you put more value on a small, expert-reviewed training set with adaptive practice, or on scaling up the amount of training data?