GPT 6 Astra lets you change reasoning effort mid-conversation without breaking the cache

intellectronica · x · 2026-09-05

Per this tweet, GPT 6 Astra has a notably practical capability: you can change reasoning effort mid-conversation without invalidating the context cache.

Note: this comes from an individual post and is an unconfirmed report on model behavior.

Original post →

More from Models

Models channel →