[Spartan-S63]

I'm extremely skeptical of this take. LLMs today aren't good at keeping significant context (even with large context windows) in such a way that doesn't lead to a spaghetti mess of code.

We're in a precarious spot where code is cheap to generate thanks to LLMs, but it's hard to build Good Software™ with only generated code. It's a pit of despair, of sorts.

If we can get LLMs to a place where that's no longer true, then writing code going away may be the new base case, but there's no guarantee we can extend LLMs that far.

[spense]

we're in agreement. context rot is real.

i'm suggesting the solution is abstraction + composition. 1/ use ai to solve a subset of the problem 2/ abstract away its complexity to just its interface 3/ build with known interfaces.

this is how we solve problems. it should work the same for ai.