well it’s not just a font. doing this does degrade performance, since rather than the words being common, individual tokens, each fancy cursed letter is processed as a really uncommon unique one. it will still answer correctly most of the time since in embeddings they are similar sentences, but it will probably answer worse (unless in thinking it rewrites your prompt correctly).

im actually confused which quadrant are you talking about? I don’t see any overestimating themselves

the universal Compass authorities who transcend the mere opinions of man

yeah what’s stupid about the reasoning about “it’ll poison ai models” is that it doesn’t even work