this post was submitted on 11 Jun 2025
129 points (99.2% liked)

chapotraphouse

13914 readers
800 users here now

Banned? DM Wmill to appeal.

No anti-nautilism posts. See: Eco-fascism Primer

Slop posts go in c/slop. Don't post low-hanging fruit here.

founded 4 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] joaomarrom@hexbear.net 75 points 2 weeks ago (11 children)

Of course it did. LLMs are terrible at any real tasks that involve actual reasoning and are not doable by a stochastic natural-sounding text extruding machine. Check out this study by a bunch of Apple engineers that pointed out this exact same thing: https://machinelearning.apple.com/research/illusion-of-thinking

[–] 7bicycles@hexbear.net 17 points 2 weeks ago (6 children)

I get how the LLM is bad at chess, I think most of everyone games of chess suck ass by definition but I'm kind of baffled about how it apparently not only played badly but wrong. How is there a big enough dataset of people yucking it up for that to happen entirely consistently?

[–] fox@hexbear.net 27 points 2 weeks ago

I'm sure they've digested every public piece of chess notation ever written but they have no capacity for comprehension and are programs that emit text shaped like chess notation if you make that request of them.

load more comments (5 replies)
load more comments (9 replies)