Eleanor Berger Describes GPT 6 Astra Reasoning Adjustment

Eleanor Berger shared a tweet about a development in GPT 6 Astra. She states that reasoning effort can be changed mid conversation without invalidating the cache. The post suggests beginning with Astra light, which she equates to Sol medium, then raising the thinking effort if the task benefits from more depth. This method avoids the need to rewrite the complete context. The tweet presents the capability as a useful efficiency gain during ongoing exchanges.