News for hackers. Stuff that matters.

A comment on Ask HN: Did you encounter any leap year bugs today?. Parent comment

Re:Ask HN: Did you encounter any leap year bugs today? by ToValueFunfetti on Friday March 01, 2024 @12:23AM (#39558813)
The number of tokens depends on context; if you just entered 'egregious' it will have broken it into three tokens, but with the whole query it's one.
[ Parent | on HN ]
Re:Ask HN: Did you encounter any leap year bugs today? by fuzztester on Friday March 01, 2024 @02:29AM (#39559467)
Why three tokens, not one?
[ Parent | on HN ]
Re:Ask HN: Did you encounter any leap year bugs today? by 317070 on Friday March 01, 2024 @03:07AM (#39559666)
without the leading space, it is not common enough as a word to have become a token in its own right. Like the vast majority of lowercase words, in OpenAIs tokenizer you need to start " egregious" with a space character for the single token.
[ Parent | on HN ]