Hacker News new | ask | show | jobs
by born1989 454 days ago
Thanks! Isn’t “an Astronomer” a single word for the purpose of answering that question?

Following your comment, I asked “Give me pairs of synonyms where the last letter in the first is the first letter of the second”

Claude 3.7 failed miserably. Chat GPT 4o was much better but not good

3 comments

Don't know about Claude, but at least with ChatGPT's tokenizer, it's 3 "words" (An| astronom|er).
That is a sub-token task, something I'd expect current models to struggle with given how they view the world in word / word fragment tokens rather than single characters.
"An astronomer" is two tokens, which is the relevant concern when people worry about this.