It's not unusual for text classifiers and other tools to know about alternate ways to write things with alternate unicode characters. Commercial LLMs see through them just fine, other systems explicitly squash " " to "unicode italics".<p>I cut and pasted the output of that thing into Copilot and Copilot had no problem understanding what was being talked about.<p>One summer I was working on an attempted foundation model based on character-CNNs and one topic for discussion was if we should build feature vectors for characters that have a lot of knowledge built in [1] or whether we should expect the model to learn all that at the byte level.<p>Anyhow, AI sees right through it today and you're not hiding anything by making everything you write look like a ransom letter.<p>[1] that italic i would have the i bit set and the italic bit set, the Chinese character 狐 has the Chinese bit and the simplified bit and the the h bit and the u bit and the rising tone bit set with something to disambiguate it from the other characters that sound the same
This automatic word censorship reminds me eerily of the short story "The City of Silence" by Ma Boyong.<p>part 1 <a href="https://web.archive.org/web/20120118104342/http://worldsf.wordpress.com/2011/11/29/tuesday-fiction-the-city-of-silence-by-ma-boyong/#expand" rel="nofollow">https://web.archive.org/web/20120118104342/http://worldsf.wo...</a><p>part 2 <a href="https://web.archive.org/web/20120201032550/http://worldsf.wordpress.com/2011/12/06/tuesday-fiction-the-city-of-silence-by-ma-boyong-part-two/" rel="nofollow">https://web.archive.org/web/20120201032550/http://worldsf.wo...</a>