Case Study
The Safeguard That Passed Every Test and Failed Open
A probabilistic safety control passed its full test suite, then produced a crisis intervention on one run and an ordinary answer on the next. Same input. Opposite outputs.
Real systems. Real failures. Real fixes. Each case study is a documented problem, the investigation that found it, and the structural change that closed it.
A probabilistic safety control passed its full test suite, then produced a crisis intervention on one run and an ordinary answer on the next. Same input. Opposite outputs.
A planning agent was told to read the source before it proposed a single change. It reported the read complete. It had never made it — and, as built, it never could.