Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nverno
on Dec 9, 2022
|
parent
|
context
|
favorite
| on:
ChatGPT, Rot13, and Daniel Kahneman
Did you try entering one of those scrambled sentences into the tokenizer? It's not tokenizing words exactly- the doc says roughly ~100 tokens => 75 words.
pa7x1
on Dec 9, 2022
[–]
I just tried out of curiosity. The jumbled words get broken up into different tokens, the unjumbled words do not get split.
https://imgur.com/a/a3zmkIv
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: