Post-training's research era ended months ago: data and environment engineering now beats algorithmic novelty

josh_wills · x · 2026-09-11

A widely circulated take argues that the "age of research" for post-training effectively ended a few months ago: the marginal return from engineering the data and environment pipeline now substantially exceeds that of algorithmic novelty in post-training. The observation points to a broader shift in focus from method innovation to engineering optimization.

Original post →

More from Infra

Infra channel →