David Sumpter

Full article here: plato.stanford.edu/entries/witt...

Read this today on Wittgenstein's view of Cantor's diagonal proof. Brutal. But hard to see why it isn't correct.

A key question about LLMs is whether they are "just" compressing information and regurgitating it or if they have a more abstract representation of the world. We still don't know the answer, but this is a good explanation of some of the research done to find out.

LLMs and World Models, Part 2 Evidence For (and Against) Emergent World Models in LLMs

This is a really interesting piece by @melaniemitchell.bsky.social about what it means to have emergent understanding in a large language model. aiguide.substack.com/p/llms-and-w...