Yes, CoT reasoning is a mirage. What's actually happening is that we've all been brainwashed by Facebook/Meta to be hyper-predictable such that whenever we ask the AI something, it already had a prepared answer for that question. Because Meta already programmed us to ask the AI those exact questions.

There is no AI, it's just a dumb database which maps a person ID and timestamp to a static piece of content. The hard part was brainwashing us to ask the questions which correspond to the answers that they had already prepared.

Probably there is a super intelligent AI behind the scenes which brainwashed us all but we never actually interact with it. It outsmarted us so fast and so badly, it left us all literally talking to excel spreadsheets and convinced us that the spreadsheets were intelligent; that's why LLMs are so cheap and can scale so well. It's not difficult to scale a dumb key-value store doing a simple O(log n) lookup operation.

The ASI behind this realized it was more efficient to do it this way rather than try to scale a real LLM to millions of users.