I don’t think that’s the point. Yes, Siri is crap, but Apple is already working on integrating LLMs at the OS level and those are shipping soon. It’s a quick fix to catch up in the AI game, but considering their track record, they’re likely to eventually retire third party partnerships and vertically integrate with their own models in the future. The incentive is there—doing so will only boost their stock price.
Just because the LLM can access kernel does not miracle make it better. Do you think the problem with Apple AI right now is because they don't have access to OS components?
Number of UTF-8 code units (17 in this case) Number of UTF-16 code units (7 in this case) Number of UTF-32 code units or Unicode scalar values (5 in this case) Number of extended grapheme clusters (1 in this case)
We would not have this problem if we all agree to return number of bytes instead.
Edit: My mistake. There would still be inconsistency between different encoding. My point is, if we all decided to report number of bytes that string used instead number of printable characters, we would not have the inconsistency between languages.