A company based in Zurich by the name of DeepCode is a dream come true for the programmers. The company claims that their system has an essential tool for analyzing and improving the code, the system is like Grammarly for programmers. It uses a corpus of 250,000 rules, reads your public and private GitHub repositories and tells you how to fix problems in your code. It remains compatible and generally improves your code.
The code is fixed through a lot of changes such as, from name: String: to name: {type: String} with suggestions for code that might be actually missing in the function calls. It’s an interesting tool, especially if the programmer needs help in finding hidden bugs in the code.
The advising tool of this system gives surprisingly precise suggestions. The system can build its own recommendations based on the large amounts of code it finds and things humans might miss.
The founder of DeepCode Veselin Raychev says,
“We built a platform that understands the intent of the code, we autonomously understand millions of repositories and note the changes developers are making. Then we train our AI engine with those changes and can provide unique suggestions to every single line of code analyzed by our platform. Today we have more than 250K rules and growing daily. Our competition has to manually create rules and the biggest competitor has 3-4,000 rules and they’ve been working for years.”
DeepCode is more than a simple debugger, the system reads and tries to compare code to other implementations, giving you the best-of-class performance from every line. Now the team just has to get the programmers to use it. DeepCode’s team has extensive experience in machine learning and AI research.
Raychev further said,
“We have a unique platform that understands software code the same way Grammarly understands written language, this unique proposition is positioned us save billions of dollars within the software development community with our first service and then to be on the front end of transforming the industry towards fully autonomous code synthesis.”
Will you use DeepCode to improve your code? Let us know in the comments below.
