I've also had Fable successfully build a text editor (quill integration) into a Vaadin project that randomly loses its content after you type a few characters (this is on the 3rd iteration).
I’ve had Opus randomly insert (correct) Russian words into responses. It’s like their training data includes some bilingual forums where idiomatic Russian speakers congregate.
I've only had that happen with Chinese models until now. Interesting that Fable is doing it too.
I've also had Fable successfully build a text editor (quill integration) into a Vaadin project that randomly loses its content after you type a few characters (this is on the 3rd iteration).
I’ve had Opus randomly insert (correct) Russian words into responses. It’s like their training data includes some bilingual forums where idiomatic Russian speakers congregate.
Could it be that Anthropic is using the Chinese characters trick to consume less tokens behind the scenes?
Aren’t Unicode characters generally treated as 2 tokens to avoid a huge vocabulary?
It used a chinese character instead of the word "true"
Same here