Chris PittsRE: https://mastodon.social/@art3starr/116321156586901899
Loving the thinking behind this. Having worked on (and helped unravel) several big balls of mud projects over the years this seems spot on.
The trouble with BBOM projects is they often have That One Guy who has either written it, or worked with it for years, giving advice like “Just read the code” (yeah, right. It reads like War and Peace) or “Put that change into this line here” (pointing to a totally random spot in an equally random file) yet are totally unable to provide any kind of high level view or model of how the thing hangs together.
And yet the new person becomes the villain because they can’t make changes 🙄
The only solution is careful, methodical refactoring to reveal the system’s secrets. Software archaeology.
Which can be kinda fun. But is awfully time consuming.
One final thing. Using AI to analyse legacy code bases - don’t. I know people who have tried and it gets it wrong. So wrong you may as well do it yourself.
Also it means learning doesn’t happen. It’s cognitive surrender, which is dangerous.