recently I gave AI a task to configure a software and the software didn’t have any docs of how it works only the source code. the agent went through all the files and generated a summary of how it works and why it’s not working for my particular scenario and suggested edits to my docker-compose.yml file. I couldn’t believe it since the bug was very hard to find and it used headless firefox to find why it wasn’t working.
made me realize do we still need documentation of how a software work when a AI can easily explain it?
How often will an AI explain, with near 90% accuracy, an entire distributed system. Better yet, make it generate documentation for prime95 and see how quickly it melts.
for a complex and large projects, it might be less accurate. but most project I use daily aren’t that complex (besides browser and linux kernel ).
there were an even I went to and the speaker asked, “what things AI couldn’t make”. my answer was “entire cloud platform like AWS” he was speechless xD