Hacker News Reader

I've interacted with that account before and they were always snarky, as if their test they made is the arbiter of intelligence and that we shouldn't be so impressed by AI that to me is actually impressive.

You don't test on the training set.

Everybody in ML (e.g., me) knows that.

But that's what we're seeing.

I'm saying: "Here's a test outside the training set."

I had to go back and reread GPs comment because I didn’t sense any snark the first time. Still not sure if I do.

That's right. There was no snark intended.

He's just spamming his website in every thread related to ML. The snark gets more attention.