OpenAI wins on post-training and scales pretraining with Astra, author argues

Angel 🌼 @Angaisb_Originally posted 2026.09.21

Open original on X

I wouldn't call Anthropic the kings of pretraining anymore, it's easy to ruin good pretraining with bad RL and you can see it in how bad Opus 5 and Sonnet 5 are OpenAI mastered post-training, which is the hard part, they just needed to scale pretraining with Astra

This post quotes another post: “Leak: OpenAI preps GPT-6 Sol and Luna, Astra 6.1 in RL training”