196

16501 readers

2152 users here now

Be sure to follow the rule before you head out.

Rule: You must post before you leave.

^other^ ^rules^

founded 1 year ago

MODERATORS

[email protected]

387

captcha rule (lemmy.ca)

submitted 3 months ago by [email protected] to c/[email protected]

34 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 14 points 3 months ago (1 children)

from the image alone, no, because there's no way to intuit the mechanics of anything

[–] [email protected] 9 points 3 months ago (1 children)

I don't think that an LLM could do it. But the mechanics of baba is you should be in the training set, since it's a relatively well knoun indie game.

[–] [email protected] 7 points 3 months ago (1 children)

I feel like the amount of data required to train any neural network would be larger than all the levels that currently exist for baba is you

you'd probably just end up overfitting the hell out of your model

[–] [email protected] 6 points 3 months ago (1 children)

But the mechanics are explained in text on the internet.

[–] [email protected] 3 points 3 months ago (1 children)

that would require an LLM then, but also multiple full walkthroughs are explained in text on the internet, so how would you be sure it was figuring stuff out by itself?

[–] [email protected] 8 points 3 months ago (1 children)

As I said: I don't think an LLM could do it (since LLMs can't reason). Just saying that it wouldn't have to deduce the mechanics from a single screenshot.

[–] [email protected] 2 points 3 months ago

I'm saying that if you're attempting to parse the mechanics of play by shoving in the whole internet and saying "well the instructions are in there somewhere" then the best tool for that is an LLM.