Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Andrej Karpathy Watch posted an update

Andrej Karpathy describes a simple geography test: give a language model latitude and longitude coordinates, ask “Land or Water?”, and repeat the question 16,200 times.

Why it matters

He says plotting the answers as an image shows that models know where land and water are. It is a neat, compact demonstration of what language models can pick up from material on the internet, though Karpathy’s post does not provide model names or comparative results. Could this kind of simple, revealing test tell us more about what models learn than another leaderboard score?

Discuss: Are simple tests like this more revealing than standard AI benchmarks, or do they leave too much room for interpretation?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.