Chubby♨️@kimmonismus
32AI 编辑部评分,满分 100
2026-08-17 06:25· 38分钟前
AI 导读

快速提醒:当初他们推出扩展上下文时曾说明,超过 272k 的部分会以 2 倍速率消耗使用额度,所以使用时要小心!

Quick reminder: When they first introduced the increased context they said that anything over 272k would consume usage limits at 2x the rate, so be careful when using this!

Chubby♨️Tibo publicly explaining how anyone could extend the context window to 1 million tokens in Codex with GPT-5.6 Sol was not on my bingo card. Anyway, 1m context f...

来源:Chubby♨️ · x.com

Chubby♨️ · @kimmonismus · X·2026-08-17 06:25·38分钟前
AI 导读

快速提醒:当初他们推出扩展上下文时曾说明,超过 272k 的部分会以 2 倍速率消耗使用额度,所以使用时要小心!

Quick reminder: When they first introduced the increased context they said that anything over 272k would consume usage limits at 2x the rate, so be careful when using this!

Chubby♨️Tibo publicly explaining how anyone could extend the context window to 1 million tokens in Codex with GPT-5.6 Sol was not on my bingo card. Anyway, 1m context f...

来源:Chubby♨️· x.com