[kozlovsky]

If we show a neural network some examples from the Game of Life and expect it to master the rules of a cellular automaton, then aren't we asking too much from it? In some ways, this is analogous to expecting that if we show the neural network examples from the physical world, it will automatically derive Newton's three laws. Not every person observing the world around him can independently deduce Newton's laws from scratch, no matter how many examples he sees.

[moconnor]

This is exactly what we ask of neural networks and in the case of the game of life the article and paper show that yes they do derive the rules. Equally, we can expect them to derive the laws of physics by observation - certainly diffusion networks appear to derive some of them as they pertrain to light.

[passwordoops]

"then aren't we asking too much from it"

Not according to the hype merchants, hucksters, and VCs who think word models are displaying emergence and we're 6 months from AGI, if only we can have more data

[int_19h]

Not according to the actual article that you're commenting on, either.

"As the researchers added more layers and parameters to the neural network, the results improved and the training process eventually yielded a solution that reached near-perfect accuracy."

So, no, we aren't asking too much from it. We just need more compute.

[nottorp]

Let's be snarky a bit:

Can you do a neural network that, given a starting position of the game of life, decides if it cycles or not? ;)

Ok, not cycles... dies, stabilizes, goes into a loop etc.

[GrantMoyer]

So Oracle's working on an LLM too, eh?

[nottorp]

<cough> halting problem. But now I'm spoiling it.

[markisus]

We know neural networks cannot solve the halting problem. But isn’t the question whether they can learn the transition table for game of life? Since each cell depends only on neighbors, this is as easy as memorizing how each 3x3 tile transitions.

[nottorp]

The original question, maybe. Mine is basically the halting problem, I think.

The other difference is I don't take it seriously.

[DeathArrow]

Everybody and their mom are into LLMs.

[yumong]

And Second Life and Myspace.

[brookst]

Same thing happened with the Internet.

[scarmig]

The halting problem doesn't mean you can never decide if something cycles etc, just that you can't always decide.

As it stands, my guess is that the LLM would always confidently make a decision, even if it were wrong, and then politely backtrack if you pushed backed, even if it were originally right.

[catlifeonmars]

For a grid of a fixed size, yes.

[elevatedastalt]

Every other day we see demos of AIs doing things that were thought of an impossible 6 months earlier, but sure, sounds like it's the "hype merchants" who are out of touch with reality.

[danielbln]

From the HN comment rules:

> Be kind. Don't be snarky. Converse curiously; don't cross-examine. Edit out swipes.

> Please don't fulminate. Please don't sneer, including at the rest of the community.

[bell-cot]

My read of the comment is: "You are correct, but bear in mind that the world seems infested with people who are far less realistic and honest than you."

[iiovemiku]

The rules also say "Please don't complain that a submission is inappropriate. If a story is spam or off-topic, flag it. Don't feed egregious comments by replying; flag them instead. If you flag, please don't also comment that you did."

I'm not really sure it's the best idea to accuse someone of breaking the rules if in doing so you're also breaking one yourself.

[HeatrayEnjoyer]

??

They are displaying emergence. They might as well be the walking definition of it.