LLMs are fundamentally matching the patterns they’ve seen, and their abilities are constrained by mathematical boundaries. Embedding tricks and chain-of-thought prompting simply extends their ability to do more sophisticated pattern matching. The mathematical results imply that you can always find compositional tasks whose complexity lies beyond a given system’s abilities.

LLMs are still very useful in a bunch of domains but here’s an article explaining (from a paper with a novel bound on computational complexity) why improvements in reasoning seem to have run out of steam.

https://www.quantamagazine.org/chatbot-software-begins-to-face-fundamental-limitations-20250131/