返回探索

Jev 与 Claude 在长链条估算上表现相当

Mike Taylor 分享:在没有公开答案的长链条问题上,Claude 通过思考痕迹默默计算,而 Jev 也能与之 1:1 匹配估算结果。

Even on long chain questions where there is no published answer i.e. "how many round trips to the Moon do all US vehicles drive in a day?" claude still does well because it silently works it out in its thinking traces, but jev can match its estimations 1:1.

Jev 与 Claude 在长链条估算上表现相当 1
· 0 次赞在 X 打开