Back to explore

Jevの分類精度を検証:AIHOTの事前スクリーニングで安定

著者がJevの分類精度を検証。AIHOTでAI関連コンテンツかどうかを判定する事前スクリーニングに使用し、安定した性能を確認。GLM 5.3 Flashは全問正解だが最も遅い。

Finally got some time to test Jev. Its classification accuracy is indeed pretty good. On AIHOT, for a small pre-screening task—judging whether incoming content is AI-related—it's solid. GLM 5.3 Flash is the only one that got everything 100% right, but it's also the slowest and

Jevの分類精度を検証:AIHOTの事前スクリーニングで安定 1
· 196 likesOpen on X