註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Eleanor Berger
@intellectronica
加入 January 2011
1.5K 正在關注    5.5K 粉絲
one very cool development with gpt 6 astra is that you can change reasoning effort mid-convo without invalidating the cache. start with astra light (roughly equivalent to sol medium), then jack the thinking effort up if you see the task can benefit from more, all without worrying about having to rewrite the complete context cache.
顯示更多
0
30
349
20
轉發到社區