Program that repairs programs: how to achieve 78.3 percent precision in automated program repair

In February 2017, Microsoft and Cambridge University announced a DeepCoder algorithm that produces programs from problem inputs/outputs. DeepCoder, which operates on a novel yet greatly simplified programming language, cannot handle complex problems—general programming languages are still too hard for DeepCoder to master. So, currently, programmers don’t have to worry about being replaced by machines. But programmers have plenty of other worries, including programming bugs. Could machines assist programmers by taking over the task of bug fixes?”


Related Content