AI failed to properly patch software flaws 74% of the time, 1Password's study warns

资讯摘要

Follow ZDNET: Add us as a preferred source on Google.ZDNET's key takeawaysA new study shows the effectiveness of AI-generated patches.  Only 26% of the patches generated were actually usable.AI isn't ready to patch the planet, but it can be used in cyberdefense. New research has revealed that artificial intelligence and large language models (LLMs) are not ready to take on the task of creating fixes and patching security vulnerabilities.

来源与参考

1. 原始链接
2. AI failed to properly patch software flaws 74% of the time, 1Password's study warns