[tombert]

We’re talking about different things.

Let’s look at regular intelligence. Stuff in human brains.

If I ask a human a question like “how many sides does a square have?” and that human says “three”, that’s an objectively wrong answer, and I would say that that person is “wrong”.

The human brain also does not have a narrowly defined specialized purpose and can do a lot of things and yet we are perfectly ok still saying “true” or “false” to the truth values being asserted.

A truth proposition can have a “correct” or “incorrect” value. If a human gives me the wrong bank balance because they misremembered it, it’s still wrong regardless of the actual intelligence associated with it.

So again, I don’t think this kind of pedantry is actually useful because you’re not actually saying anything; you’re saying “these models aren’t trained on being correct, they’re on word patterns”, which was never disputed, but that is orthogonal to the truth value.