AI vulnerability patching has a grading problem

October 12, 2026 · 4:45 am 1 sources

Image: Help Net Security

Coverage

Coverage

• AI vulnerability patching has a grading problem
  Help Net Security · October 12, 2026 04:45
  Researchers at Northwestern University tested AI coding agents on 112 real security bugs. They found that a patch which stops a crash often fails the checks the project’s maintainers wrote for the fix. With Claude Opus 4.7, third of the patches that made the crash go away still failed those…