Y
Hacker News
new
|
ask
|
show
|
jobs
by
isaacfung
749 days ago
The current gen llms tokenize numbers digit by digit unlike earlier llms.
2 comments
Last5Digits
749 days ago
They don't. Which you can easily check with any of the dozen web apps currently implementing the GPT-4o tokenizer.
link
mike_hearn
749 days ago
No, it doesn't help. Bloomberg tried this and it didn't seem to make much difference.
link
singularity2001
748 days ago
If someone else is interested in the Bloomberg tokenizer:
https://medium.com/generative-ai-insights-for-business-leade...
link