用 Jev 分类器做 agent 失败模式挖掘

Applied Compute @appliedcompute原推发布于 2026.09.24

在 X 上打开原推

Gap analysis is how our Applied Researchers, like @_brylee10, surface agent failures across billions of tokens of RL traces for our customers. Using our platform, AC2, and low-cost classifiers like Jev, we can catch 85% of failure modes at a fraction of the cost of LLM judges and turn them into training data.

这条是引用着另一条写的：「用 Jev 自动聚类 RL 训练中的失败模式」