[foobarbecue]

My point exactly. This article could have been written: "AI is biased against drawing just one banana" and I would have preferred it. And I said "almost" because I skimmed two of the paragraphs in the middle that seemed unlikely to contain information.

[lproven]

But that isn't the point.

The point is, LLMs look smart but they are not, and an easily-verifiable data point is that they can't count.

[foobarbecue]

Ah, right, and that's not obvious to some people... I guess I'm just not the target audience.