Improved automatic language detection would be even nicer. I.e. BlueSky _may_ recognize it's some language X I write in and consequently may propose to switch. But usually I just fail to see it. Besides, it's cumbersome when I think it could be automatic.
1Samuel
@samuel.fm
hard to do accurately with an on-device model unfortunately
1 2Veikko EevaI have no doubt also you wouldn't have looked into it.
I've been also looking if some the newer models could be very little and purpose built for that. Maybe e.g. something done with github.com/microsoft/Bi.... Or have dictionaries of "most used words" in usual languages and "guess accurately".
GitHub - microsoft/BitNet: Official inference framework for 1-bit LLMs
Official inference framework for 1-bit LLMs. Contribute to microsoft/BitNet development by creating an account on GitHub.
github.com
Samuelwe use www.npmjs.com/package/lande, but it's got a horrendous false positive rate so we only show the prompt if the confidence is high
2 2Veikko EevaIf people tag well enough, you could perhaps train a better one. Maybe combine with some other tricks too. :)