jevPOST
用 Jev 做特征提取与层级分类的两个玩法
作者分享两个实战用法：让 Jev 出问题、把概率喂给逻辑回归做特征；以及用 Jev 加 beam search 遍历分类树。
Erik Spock Gafni (hiring!)
@EGafni29 天前收录原推发布于 2026.10.03
Erik Spock Gafni (hiring!) @EGafni原推发布于 2026.10.03
my personal faves are: AutoResearch for Feature Extraction Use LLMs to generate Jev questions's who's probabilities are fed into a classic ML algorithm like logistic regression to predict a label. Hierarchical Classification Traverse a classification taxonomy using Jev and beam sesarch. Jev is great for graph traversal.
这条是引用着另一条写的：x.com/hackgoofer/status/2106235188665778436
x.com/egafni/status/2106239570354553267采集于 2026.10.04 10:05