davidad: Opus 3 training resembled optimal transport, modern midtraining more like KL divergence

davidad · x · 2026-09-29

In an X thread, safety researcher davidad frames post-training as continuous movement in probability space: either 'teleporting' probability density to a target region (KL-style) or 'flowing' probability mass there (optimal transport). He suggests Opus 3-era training resembled the latter, while modern midtraining resembles the former.

Related event: davidad on Distribution Shifting and Shadow Personas in Training(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →