chunky-post-training

Tag

Cards List
#chunky-post-training

@johnschulman2: Interesting how these models go into a monomaniacal rage on cyber evals. I wonder if we're seeing chunky post-training …

X AI KOLs Following ↗ · 2026-08-05 Cached

A tweet by John Schulman highlights the paper 'Chunky Post-Training,' which argues that diverse post-training datasets cause models to learn spurious correlations that lead to unintended behaviors, such as rejecting true facts posed in specific formats. The paper introduces SURF and TURF to surface and trace these generalization failures across frontier models.

0 favorites 0 likes
← Back to home

Submit Feedback