In preliminary tests, ControlFlag trained and learned novel defects on over 1 billion unlabelled lines of production-quality code.
According to studies, software developers spend approximately 50% of the time debugging.
It specifically operates through a capability known as anomaly detection.
Further, if anomalies in code are found, the tool can detect these anomalies regardless of programming language.
When Intel tested ControlFlag, it was able to identify errors in production-quality code.
One of these codebases that was analysed by the tool was cURL.
It was able to identify an anomaly in a cURL code that had not been previously recognized.
Currently, Intel has is using ControlFlag internally to identify bugs in its own software and firmware product development.
source: www.techworm.net
