What's the implication of this? That the model already decided on a solution, upon first seeing the problem, and the reasoning is post hoc rationalization?

But reasoning does improve performance on many tasks, and even weirder, the performance improves if reasoning tokens are replaced with placeholder tokens like "..."

I don't understand how LLMs actually work, I guess there's some internal state getting nudged with each cycle?

So the internal state converges on the right solution, even if the output tokens are meaningless placeholders?