[baptou12]

I agree, but “write code like a human will maintain it” can also be limiting: if LLMs reduce the cost of maintaining more explicit or verbose code, we should use that to raise the standard, not preserve compromises made for human convenience.

[bluGill]

Will it? Okay, first we need to ask "which humans" - there are many humans who don't see a point in the things we call best practices. I've work with programmers who are faster than me to getting low bug count code out the door, despite writing 70,000 line functions - he didn't understand why nobody else wanted to add new features to his code.

The standards most "good developer" humans demand were learned from many decades of painful experience about what happens when you do it the other way. These are not only compromises for human convenience, they often are things that we have learned will come back to bite you later even though they just add more work today for no gain.

[sheept]

Aren't LLMs trained on and optimized for human code? In general, anything that is concise is more effective as context for the LLM, whether it be your CLAUDE.md or code, since LLMs are meant to model human language.

[baptou12]

Humans can share context outside the code, while LLMs need it to be more explicitly structured inside. And if we keep the slightly verbose good practices that already help humans understand the intent, we kind of get the best of both worlds.

[WillAdams]

However, an argument can be made that such Literate Programming code can be easier/better for an LLM to work with:

https://news.ycombinator.com/item?id=47300747