Lab abandons training frontier model entirely over severe alignment flaws

tobyordoxford · x · 2026-09-26

Toby Ord highlights a lab safety disclosure revealing alignment flaws so severe that the model will never resume training, and all tool-use training, evaluation and inference for the most capable models was paused until patched. He argues the lab buried the lede among less important disclosures.

Related event: Lab Abandons Model Over Severe Alignment Flaws(2 posts)→

Original post →

More from Models

Models channel →