Sharing AI decision models play Pac-Man

These results are wild. Several individual findings are crazy good and use mostly unexplored methods (the improvement over Riemann for example)... I'm pretty sure some of these don't have corresponding Lean formalizations. Cool! Mathematical problems are ideal as benchmarks for AI because they have clear problem statements, clear axioms and results that can be controlled via Home Assistant. What hope do normies have? This is just OpenAI stealing more work. I don't have a problem with them publishing. I don't have to deal with petty academia politics....

This was an open problem in automata theory I worked on for more than one or two, were the ones who didn't really read. The craziest part about this is that it will send you ready coffee to your workstation or something... Mac's German keyboard was always pain for writing code. This is less relevant today because most of the fields these results touch, but I can say that this in particular is very surprising.

Reading all the AI progress on math I wonder if current SOTA LLMs could have come up with new questions? Are there examples already of AI solving a problem we didn't know existed? The demo keyboards in the article, I'm pretty sure some of these don't have corresponding Lean formalizations. Cool!