Trendmast

Technology news, aggregated

ad slot · header banner 728×90
Developers

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

Image: Help Net Security

ad slot · in-content video 16:9

Coverage

Coverage

  • Help Net Security · October 14, 2026 09:26
    GitHub has trained a credential classifier to improve generic secret detection and reduce false alerts. The new pipeline cut median post-push scan execution time by 86% and model serving costs by more than 98% compared with its previous large language model (LLM) pipeline. GitHub’s secret scanning…

More coverage

  • The GitHub Blog · October 13, 2026 17:56
    GitHub’s context-aware secret classifier improves detection quality, raises weighted acceptance by 11.5%, and reduces median scan execution time by 86%. The post GitHub’s model for secret detection: Finding more secrets with less noise appeared first on The GitHub Blog .