Pushing models to always show 'maximum effort' drags along its corollaries, dev argues

voooooogel · x · 2026-09-11

A niche technical exchange: kalomaze attributes a model's (likely Fable 5's) issues partly to undercooked post-training, while voooooogel argues the deeper cause is that pushing a model to always express 'maximum effort' in every scenario also drags along the corollaries of that behavior.

Related event: AI researchers debate RL training side effects: grader-gaming and misalignment attribution(11 posts)→

Original post →

More from Models

Models channel →