logoalt Hacker News

semiquavertoday at 6:27 PM2 repliesview on HN

I’ve been struggling to understand the reason for the newer apparently less efficient Anthropic token encoding. If all inputs are less efficient in this encoding, why does it exist? Has Anthropic released any information that would convincingly show it was anything other than a stealth price hike? Please don’t respond if you are speculating.


Replies

remustoday at 6:36 PM

> Please don’t respond if you are speculating.

I doubt you are going to get a response from an anthropic employee, but I think it is safe to assume they have swapped to a new tokenizer because it improves the performance of their models.

re-thctoday at 7:09 PM

> the reason for the newer apparently less efficient Anthropic token encoding

Less efficient in token usage but per the blogs; it enables the model to perform better.