Very poorly compared to the tools we have built. Similar to the LLM.

Comparing to raw LLMs? Much much better.

Poorly in what sense? I think human chess leagues are way more popular and fun than just playing a computer by yourself. Human oriented communities are always a vastly better experience than their digital counterparts.

There's more to games than simply winning you know.

If they wanted to train an LLM to play chess they could easily do so.

But nobody wants that.

Asking an LLM to play chess by writing algebraic notation is like asking a human to play chess blindfolded.

Yes some people can do it but most people can't even if they're unusually intelligent.

You really need to be giving the LLM a board representation.

EDIT: I see that they actually were giving the LLMs a board representation and they still played badly. Fair enough then.