Preferences

That's probably because the model works on tokens and not letters. Depending on what "it" means, the model can use various tokenization methods that you can run on your computer really easily so you can see what it sees.

Sure, but the tokenization should cause problems for the encoding and cipher tasks as well? In addition to that: The odd/even starting letter task should be solvable by only considering tokens since the first letter should fall on the beginning of the token.

This item has no comments currently.

Keyboard Shortcuts

Story Lists

j
Next story
k
Previous story
Shift+j
Last story
Shift+k
First story
o Enter
Go to story URL
c
Go to comments
u
Go to author

Navigation

Shift+t
Go to top stories
Shift+n
Go to new stories
Shift+b
Go to best stories
Shift+a
Go to Ask HN
Shift+s
Go to Show HN

Miscellaneous

?
Show this modal