Hacker News Reader

This sounds like what the company Mechanical Orchard offers: https://www.mechanical-orchard.com/

Their pitch is like, "we take your COBOL code, and all the real-world data you can give us. Then we model your COBOL program as a graph, where each node has inputs and outputs. Then we use AI to port each node, making sure that it has the same (input => output) mapping for all the test data you gave us."

View on HN

> for all the test data you gave us

This is the secret sauce. You'll be responsible for any defects if you didn't prepare your test data to act like a massive unit test. Wonder how hard is to prepare the ideal test data vs writing the unit tests themselves in COBOL and verifying their translation. I guess if you throw enough data at it, the effort is minimal while the coverage becomes good enough to fix any bugs manually.

Reply on news.ycombinator.com