I’ve recently been thinking about this too, here is my idea: https://clintonboys.com/projects/lit/

ferroman 13 hours ago | parent | next [-]

Using prompt as source of truth is not reliable, because outputs for the same prompt may vary

	▲	mtsolitary 12 hours ago \| parent [-]
		Of course. But if this is the direction we’re going in, we need to try and do something no? Did you read the post I linked?

▲

fragmede 13 hours ago | parent | prev | next [-]

Fascinating! https://github.com/clintonboys/lit-demo-crud isn't deep enough to really get a feel for how well this would work in practice.

▲

gethly 13 hours ago | parent | prev [-]

> Like everyone else with a keyboard, a brain and a vested interest in their future as a programmer, I’ve been using AI agents to write a lot of code recently.

alrighty then..