ChatGPT usage is a very poor metric. Anything interesting is happening via API. Even the chat completion endpoint still isn’t “ChatGPT” on its own. None of these complaints about it being “dumber” apply to the API outputs. OpenAI don’t care about nerfing chatGPT because it’s not their real product.
It would not HAVE to do that, it just is much harder to get it to happen reliably through attention, but it’s not impossible. But offloading deterministic tasks like this to typical software that can deal with them better than an LLM is obviously a much better solution.
But this solution isn’t “in the works”, it’s usable right now.
Working without python:
It left out the only word with an f, flourish. (just kidding, it left in unfathomable. Again… less reliable.)