Documentation explains how an app works currently. But part of the context that the LLM lacks is how I imagine the app to work. This is difficult to integrate into version control.
Literate Development: AI-Enhanced Software Engineering
21–24 of 24 posts
Re: Literate Development: AI-Enhanced Software Engineering
#22Regardless, are there any good examples of projects generated by LLMs? There was a game like Angry Birds. But that was long time ago. I did some simple 'games'. If it's easy there should be a lot of open source projects, right?
Here is one: https://blog.sshh.io/p/building-v0-in-a-weekend
Re: Literate Development: AI-Enhanced Software Engineering
#23A rule of thumb I’ve started using is: “if your function name and arguments aren’t good enough to have Copilot tab completion make a cogent attempt at implementing the full behavior, you need more comments/docstrings and/or you need to create utility methods that break down the complexity.” Alternatively: “if you tab complete a docstring and it doesn’t match what you expect, your code can be clearer and you should ad…
This is only true for the most generic code. Copilot isn't going to autocomplete my recursive JSON2Neo4j import function.
Re: Literate Development: AI-Enhanced Software Engineering
#24I recommend that the author actually tries this approach on a reasonably sized project before recommending it to others.