And if you want to get your hands dirty with Unicode glyphs, check out [Roman Czyborra]’s tools here, which are simple command line tools that let you easily experiment using ASCII art.

I suspected this because, due to some technical quirks of how rare unicode characters are tokenized by GPT-4, the corresponding ASCII is very evident to the model.

If you hold a modern device that supports the latest emojis (based on Unicode 16.0), ... However, ASCII was limited to the English alphabet, punctuation, and numbers.

Unicode could be seen as a universal version of ASCII. ASCII is, after all, the American Code for Information Interchange, and its first iteration included the English-language alphabet and ...

ASCII continues to exist but has been largely replaced by Unicode, which can be used to encode any language. Understanding the American Code for Information Interchange (ASCII) ...