GitHub adopts cheaper AI model to catch secrets developers leave in code

GitHub trained a credential classifier for its secret scanning pipeline that cut median post-push scan execution time by 86% and model serving costs by more than 98% compared with its previous large language model pipeline, the company said. The classifier is designed to improve generic secret detection and reduce false alerts across GitHub's two scanning stages: push protection, which checks changes before a push is accepted, and post-push scanning, which examines repository content and creates alerts for potential credential leaks.