註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Aethir
@AethirCloud
Powering the Future of AI. Building Decentralised Cloud Compute Infrastructure.
加入 May 2022
202 正在關注    673K 粉絲
A measurement study published in March put a number on something practitioners have felt for a while. Chain-of-thought prompting lifted accuracy sharply on hard tasks, and raised energy per answer by 120 to 150 times. Majority voting added 72% to 177% for much smaller gains. Same deployment, same question, two orders of magnitude apart in compute consumed. Any capacity plan that assumes a fixed cost per query is now wrong by default, sometimes by a hundredfold. The variance is in how the model thinks.
顯示更多
0
45
174
18
轉發到社區