(no title)
ocimbote | 3 years ago
Let me tell you: the training data did not contain that many X to begin with :D
The Xs at best look like Ts, at worst like malformed Os.
Always funny to find the blind spots of some piece of tech.
ocimbote | 3 years ago
Let me tell you: the training data did not contain that many X to begin with :D
The Xs at best look like Ts, at worst like malformed Os.
Always funny to find the blind spots of some piece of tech.
throwaway4837|3 years ago
tjohns|3 years ago
gjm11|3 years ago
[EDITED to add:] Ah, oops, I see. You were talking specifically about _capital_ X. You are right and I was wrong: the model produces disastrous capital Xs even at high legibility settings.
jade-cat|3 years ago
dendrite9|3 years ago
The same settings but with min speed got caught at the z, creating what looked like repeating waves then a few letters that I couldn't place from the phrase.
Also amusing are the loops that get the tops cropped even though other letters extend higher.
pmarreck|3 years ago
as usual, the errors are at least as interesting as the successes on new tech!
noduerme|3 years ago
ocimbote|3 years ago
folkrav|3 years ago
PUSH_AX|3 years ago
dspillett|3 years ago
neogodless|3 years ago
> My first name is: XXX ZZZ JJJ
(max speed, max legibility, default stroke)
_ache_|3 years ago
alt227|3 years ago
joshspankit|3 years ago
https://imgur.com/a/PRl42rb
To be fair, I kind of remember handwriting X (and x) as totally counter-intuitive in school.
dubya|3 years ago
lovehashbrowns|3 years ago
kottapar|3 years ago
notoverthere|3 years ago
mushbino|3 years ago
shaky-carrousel|3 years ago
nashashmi|3 years ago
zmk_|3 years ago