well, you didn't really do anything, did you? Claude Code rendered these things and wrote the blog post haha

> "This is not theoretical. It is a measured property of the font files shipping on every Mac."

some patterns of speech are so recognizably LLM, i am convinced that the AI detection startups have a very strong chance to succeed on text.

▲

deaux 4 hours ago | parent | next [-]

Going off on a bit of a tangent here..

> some patterns of speech are so recognizably LLM, i am convinced that the AI detection startups have a very strong chance to succeed on text.

The problem for them is the market. Those who actually want to buy AI detection tools usually want the impossible - detecting any kind of AI-written text, or even AI-written-human-edited text.

You're right in that many HN articles (not going to comment on this one specifically) are very easy to detect. But that's just because these article writers are too lazy to even use any of the plethora of tools that remove the smells automatically, or tools that write without them in the first place (I've made such a tool myself), or even just adjusting the prompt to write in a different style that avoids them.

Most people who would be interested in paying for AI detection tools want them to detect all of the above cases too, which is of course impossible.

▲

aronhegedus 4 hours ago | parent | prev | next [-]

However it was written, it’s a useful and well structured article. I thought it was a good read

	▲	alterom 2 hours ago \| parent [-]
		I mean, no shit Sherlock, Cyrillic letters being indistinguishable from English ones is what Russian speakers have been using to get around braindead keyword сеnsоrshір¹ forever, same way kids type "de@th" on TikTok to avoid automoderation. Most of the added value in this article can be summed up by saying that the Cyrillic glyphs are identical to the similar English ones in the fonts that author looked at (which isn't true for all fonts), and author didn't find many other such examples. _______ ¹ Try matching that word with "censorship" for fun

▲

tstrimple 4 hours ago | parent | prev | next [-]

[flagged]

▲

tuwtuwtuwtuw 4 hours ago | parent [-]

Maybe not. I checked OPs blog and he seem to be putting up 2-3 longer posts per day. Since it is LLM content, I have no idea whether it's mainly hallucinations or based on facts. So what did I learn from reading the article? Maybe nothing, maybe it's just made up.

	▲	pmontra 3 hours ago \| parent [-]
		If you have a Mac you can follow the steps at the end of the post and reproduce the results https://paultendo.github.io/posts/confusable-vision-visual-s... I don't have a Mac.

▲

jcynix 2 hours ago | parent | prev [-]

Yes, some patterns of speech are recognizable … The "That's LLM generated" pattern is one of those. And while I can understand the motivation behind this, I find it more irritating now than LLM texts, if these contain useful information, which make me curious.

This text made me curious, I liked the approach the author has taken. And it made me think how I would do it. My first idea would be to use ImageMagick to render text and then use ImageMagick's https://imagemagick.org/script/compare.php to somehow calculate the risk of confounding glyphs.

So: Don't be snarky? Maybe we need another rule here, to limit comments on "LLM style" https://news.ycombinator.com/newsguidelines.html