[JBits]

> CoT models can, in principle, solve _any_ complex task.

What is the justification for this? Is there a mathematical proof? To me, CoT seems like a hack to work around the severe limitations of current LLMs.

[malcontented]

That's a fair argument to make. I should have, perhaps, written "are supposed to be able," or "have become famous for their apparent ability to solve loosely-specified arbitrary problems."

CoT _is,_ in my mind at least, a hack that is bolted to LLMs to create some sort of loose approximation of reasoning. When I read the paper I expected to see a better hack, but could not find anything on how you take this architecture, interesting though it is, and put it to use in a way similar to CoT. The whole paper seems to make a wild pivot between a fully general biomimetic grandeur of the first half, and the narrow effectiveness of the second half.

[liamnorm]

The Universal Approximation Theorem.

[JBits]

I don't see how that changes anything. By this logic, there's no need for CoT reasoning at all, as a single pass should be sufficient. I don't see how that proves that CoT increases capabilities.