you could think of "knowing what a giraffe is" in this instance as a slice of an intelligent thought, but it's not a whole thought, let alone a train of thoughts, or a plan involving many trains of thought over time for internally motivated reasons.

If we could get it to tell us a story about a particular giraffe, and then ask it next week about that same giraffe, and then the giraffe could be referenced by it while it tells a joke on a talk show in a decade -- that's maybe too high a bar, but that's real intelligence.

Why is long term memory a requirement? Are amnesiacs not intelligent?

> that's maybe too high a bar, but that's real intelligence.

It's not necessarily a requirement, but I couldn't witness someone do it and then deny their intelligence.

But it's not sufficient either, right? Just having memory alone also wouldn't prove intelligence, so it's not necessary or sufficient

I agree that memory alone is not sufficient to "prove intelligence".

Above, I wrote a paragraph sketching an example of complex behaviours, entailing creativity, humour, longevity, planning, memory, storytelling, object recognition, social skills, etc., as a "clear display of intelligence", not a minima, to use as a counterpoint to merely "recognizing a giraffe".

So I think you've missed my point, or, I've severely missed yours. If I have, sorry! As a general feeling toward internet nitpicks, we're unlikely to work in good faith to help each other out from here, so I'm out.

Well, the point I was getting towards is that if you remove the memory-based requirements from the scenario you set out, then it doesn't sound so far off from what something like GPT-3 can already do today. I am trying to reduce your scenario down to the minimal requirements so we can get a better understanding of whether those requirements are achievable by computers or not. If we just rely on "knowing it when we see it" then we might fool ourselves until the point where it's too late to go back.