Sara Hooker(@sarahookr):This is actually more a side-effect of the death of pretraining. As transformers saturate, most pretraining results are tweaking data recipes, not massive stepwise changes in performance. Turns focus to innovation in postraining and test time compute. This is good for competition, since pretraining concentrated resources in a few labs.

2026.10.18 20:59

This is actually more a side-effect of the death of pretraining. As transformers saturate, most pretraining results are tweaking data recipes, not massive stepwise changes in performance. Turns focus to innovation in postraining and test time compute. This is good for competition, since pretraining concentrated resources in a few labs.

SemiAnalysis@SemiAnalysis_

2026.10.17 23:13

GLM 5.3’s biggest leap came from post-training alone. “GLM 5.3 was built entirely by post-training the previous model. For me, that was a wake-up call.” “Post-training is far more GPU-efficient than pre-training from scratch. Plenty of companies can’t afford to train a model from scratch, but they have proprietary data. They can post-train themselves and beat some of the closed models.” “There’s still so much juice left to squeeze from post-training. We compared GLM 5.3’s cyber capabilities with 5.2, and it’s a night and day difference. That’s all just post-training.”