Leak claims OpenAI's Astra post-training unfinished, can't yet convert compute into gains

teortaxesTex · x · 2026-09-04

An unverified claim on X suggests GPT-6 Astra's post-training is far from done: the model reportedly cannot yet reliably and monotonically turn more compute into better results, hinting at an unstable scaling curve. The post notes Anthropic's Fable camp disagrees.

Related event: Report: GPT-6 Astra post-training unfinished, compute-to-performance scaling still unstable(2 posts)→

Original post →

More from Models

Models channel →