GoogleCloudPlatform/kubectl-ai

evals: we should ensure resources in eval tasks must not contain hints to help with the eval tasks

オープン

#298 opened on 2025/06/02

 (0 件のコメント) (0 件のリアクション) (0 人の担当者)Go (708 件のフォーク)auto 404
enhancementhelp wanted

Repository metrics

Stars
 (7,532 個のスター)
PR merge metrics
 (PR metrics pending)

説明

We want to ensure the eval tasks represent realistic scenario and we have observed that name/namespaces of the k8s resources used in the task contains hint to make AI Models aware that these are part of evals or some sort of test. I think this affects the model's performance on the task, so we need to fix it for all the existing tasks.

コントリビューターガイド