It's not enough to enforce the invariants because they may need to change. You need to follow the invariants when they're right, and go back and reconsider them when they prove unhelpful. Knowing which is the case requires judgment that today's models are simply incapable of (not consistently, at least).
Re:I'm going back to writing code by hand
by stingraycharles on Monday May 11, 2026 @11:16PM
(#48103786)
Yeah that's what I mean with "more human involvement", so the approach is to put the human in the loop in these moments, and the LLM knowing when it should do this.
Yeah I’m currently working for several months already on a harness that wraps Claude Code and Codex etc to ensure that these types of invariants are captured and enforced (after the first few harness attempts failed), and - while it’s possible - slows down the workflow significantly and burns a lot more tokens. In addition to requiring more human involvement, of course.
I suspect this is the right direction, though, as the alternatives inevitably lead any software project to delve into a spaghetti mess maintenance nightmare.