> AI will never know the why behind the architecture…

That's true only if you don't provide that context. The answer is: Do provide that context. My experience is that LLM output will be influenced and improved by the why's you provide.

▲

asdev 2 days ago | parent | next [-]

if you know that context, you don't need a codemap

	▲	CharlesW 2 days ago \| parent \| next [-]
		As you just said, codemaps don't include the "why" behind the architecture. That's context you need to add.
	▲	baq 2 days ago \| parent \| prev [-]
		this is possible if you have a couple two-pizza teams. beyond that, good luck.

▲

dingnuts 2 days ago | parent | prev [-]

it takes longer to explain the context to the model than it does to just write the code based on the context I already understand, especially since code is more terse than natural language

▲

fizx 2 days ago | parent | next [-]

Definitely, iff you have to provide the context with every task. If agent memory worked better and across your whole team, then providing context might be much easier

▲

Jaxan 2 days ago | parent | prev [-]

But wouldn’t the context also be useful, in written form, to colleagues?

	▲	CharlesW 2 days ago \| parent [-]
		It absolutely is, yes.