You can do unit conversions with powertoys on windows, spotlight on mac and whatever they call the nifty search bar on various Linux desktop environments without even hitting the internet with exactly the same convenience as an llm. Doing discrete things like that with an llm inference is the most inefficient and stupid way to do them.
They weren’t though. You put stuff in the search bar and it detected you were asking about unit conversion and have you an answer, without ever involving an llm. Are you being dense on purpose?
You can do unit conversions with powertoys on windows, spotlight on mac and whatever they call the nifty search bar on various Linux desktop environments without even hitting the internet with exactly the same convenience as an llm. Doing discrete things like that with an llm inference is the most inefficient and stupid way to do them.
All things were doable before. The point is that they were manual extra steps.
They weren’t though. You put stuff in the search bar and it detected you were asking about unit conversion and have you an answer, without ever involving an llm. Are you being dense on purpose?