wdpatti

It already does that for about 10 of the 26 letters in the alphabet that have Cyrillic clones

Looks like someone finally got it!

Thanks for all the compliments!

In all reality I spent like 30 minutes on this one Sunday afternoon when every model failed nearly 100% of the time - now it's more like 95% but about half figure out that there is something wrong and prompt the user to fix it. This isn't meant to be a permanent fix at all - just a cool idea that will be patched just like DANs were back in 2023.

Stuff other than AI starts to break if you try to copy/paste that much text in one go - I put a soft limit at 500 so people wouldn't go paste in their PhD dissertation and watch Word crash on them.

See the bottom of the website for some examples - most small models can't process the text at all.

I actually made this back in August but never posted it until now.

I agree with your point; many of the comments say that simple regex filtering can solve it, but they seem to ignore that it would break many languages that rely on these characters for things like accent marks.

When you click the “Gibbberify” button it copies it to your clipboard automatically.

Many of these characters actually have genuine uses in non-English languages, so it would be hard to just blindly remove all of the characters from every prompt without breaking other things.