Dylan Patel: efficient pretraining makes post-training misalignment exponentially easier

dylan522p · x · 2026-11-23

AI researcher Dylan Patel backs the case for "pacing" post-training RL, arguing that as pretraining gets more efficient, models become exponentially easier to misalign within fewer RL steps during post-training — making careful pacing a legitimate concern.

Original post →

More from AGI Musings

AGI Musings channel →