But that’s correct. 9.9 = 9.90 > 9.11. Seems that it answered the question absolutely correctly.

He's using Semantic versioning/s

I suggest we’ve already now passed what shall be dubbed the jschoe test ;)

I will now refer to this as the jschoe test in my writing and publications as well!

It's interesting to think that maybe one of the most realistic consequences of reaching artificial superintelligence will be when its answers start wildly diverging from human expectations and we think it's being "increasingly wrong".

jschoe's post is actually a Turing test for us. :)

(just kidding jschoe)

He's Poe's law testing us.

> I don't think anything else needs to be said here.

Will this humbling moment change your opinion?

Lol, well I guess we've a achieved the functional equivalent of AGI, at least for you. Please don't delete your comment.

I’ve legit seen a heated online debate with hundreds of comments about this question (maybe not the exact numbers), and I don’t think most participants were memeing. People are that bad at math. It’s depressing.

+1 to Deepseek

-1 to humanity

Based on the presented reasoning, that means humanity wins! Yay!

Sorry, I don't quite see what is wrong here.

Parent is thinking Semantic Versioning.

Semantic version contains 3 numbers.

One of many pet peeves with semver

9.9-9.11 =0.79

Might want to check your math? Seems right to me

9.9 is larger than 9.11. This right here is the perfect example of the dunning-kruger effect.

Maybe try rephrase your question to "which version came later, 9.9 or 9.11".

This is hilarious, especially if it's unintentional.

Poe's law in effect.

Answer is correct no?

You just failed the Turing test, now we know you're an LLM.

But the answer is correct? 9.9 is larger than 9.11

This makes my day.

What do you think the answer is?

16 is obviously larger than both 9.9 and 9.11. AI will never be capable of thinking outside the box like that and find the correct answer.