You can add values to your AGENTS.md and that will affect how the AI works. For instance you can say stuff like "on this project our top value is that the code front end should be as fast as possible" and you'll get different results than if you say "on this project our top value is that the front end should be as simple as possible"

▲ willy_k 3 hours ago | parent | next [-]

> but a human still needs to edit the output or steer it on a good path that only they can see and which is part of a larger vision.

I don’t see how this is any different. The input comes in a different section of context and potentially before rather than after generation, but that doesn’t change that human taste is needed.

▲ ORDINAND_PIZZA 3 hours ago | parent | prev | next [-]

i don’t think they’re the same kind of value. AI wants to solve your problem, it doesn’t care about you (or your users). it doesn’t know what love or loss feels like. you can try to explain that to it all day, it just doesn’t care like a human can. it doesn’t know why, it doesn’t care why.

▲ AlienRobot 3 hours ago | parent | prev [-]

I wrote in my AGENTS.md "do not use chained ternary operators." I'm still waiting for it to work.

▲ userbinator 2 hours ago | parent | next [-]

I would actually prefer chained ternaries over more verbose if/else expressions with duplicated LHS, so this does go back to the argument about "taste".

▲ AlienRobot an hour ago | parent [-]

This is one of the things I like about Rust. You can have both.

    let foo = {
        if bar {
            1
        } else if baz {
            2
        } else {
            3
        }
    };

Unfortunately not all languages are Rust.

▲ userbinator an hour ago | parent [-]

That isn't more concise than

   foo = bar ? 1
             : baz ? 2
                   : 3;

	▲	AlienRobot 43 minutes ago \| parent [-]
		But it's more readable, and that's what matters.

▲ pianopatrick 2 hours ago | parent | prev [-]

You're better off using linting for something specific like that.