Back to explore

Jev が長い連鎖推論の見積もりで Claude に匹敵

Mike Taylor 氏は、公開された答えがない長い連鎖の質問で、Claude が思考トレースで計算し、Jev もその推定に 1:1 で一致できると述べています。

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 が長い連鎖推論の見積もりで Claude に匹敵 1
· 0 likesOpen on X