Hacker News Reader

Comment by austinthetaco | Hacker News Reader

I'm not the person you are replying to, but the readme is very clearly written by an AI, and it sounds nothing like his older work. Sometimes it's just super clear to people something is written with AI without you getting some sort of singular "gotcha" word or indicator. It's just writing patterns that would be hard to clearly establish rules for here in an HN comment, but it's incredibly obvious when you learn to spot it.

View on HN

I recently vibed a little linked-in AI detector which looks for AI things like rule of three and scores it. It scored it 97% AI polished.

My gut feeling agrees. The rule of three is one of the stronger signals, can't stamp that out of the AI even if you wanted :-)

I'll push it to GH later, it's nothing fancy but it has been quite good in my experience. Here is highlights which it used

``` tricolon coordinated VERB run: “…break / on them collapse / unlock everything .” (3 members) tricolon coordinated VERB run: “…guard physical addresses / not DRAM coordinates / you rearrange the” (3 members) tricolon coordinated NOUN run: “…handful of data / it to z3 / the translation matrix” (3 members) tricolon coordinated NOUN run: “…view / the elaborate fences / locks / security checks the” (4 members) tricolon coordinated VERB run: “…Read it / the alias map / pipe” (3 members) ```

It's baffling but I'm starting to believe that some people genuinely cannot tell. It's like nails on chalkboard to me.

I mean, it's super clear to a lot of people that it's written by LLMs EVEN WHEN IT'S NOT. You can't vibe that shit too.

I just told my boss to remove a line in a doc because it sounded too AI-y. He then said that he had written it himself.

How do you know when it's not written by LLM except to take someone's word? If I got caught slopping I'd be too embarassed to admit it. "I wrote it all myself! I actually majored in slick writing and minored in tenuous metaphor."

I assume not 100% of all HN linked articles were written by AI, while at the same time noticing that 100% have a comment saying how it's AI written.

Find me one that you genuinely think is not AI written or edited, with comments claiming it is.

I’ve had blog posts I wrote 17 years ago “called out” as AI generated lol. More than once.

This entire subsection of the discussion is about the apparent fact that some people just can't tell whether they're reading AI slop or what. And this surely applies to the haters just as much as the lovers.

Anyway, I've no doubt your blog posts from 2009 or whatever were not generated by an LLM. But this fuckin shit right here from 2026 though? LLM. 100%.

(By which I don't mean it generated 100% of it, as there's the odd sentence that sounds vaguely human, just that I am 100% certain that the LLM was allowed to far more than merely breathe on this writing. And that's enough to get me complaining, because it makes it a real headache to read.)

I'm not a "lover" of AI, I'm just saying it's tiring when people scream AI all the time without proof.

Be grateful. I couldn't spot AI writing for a while, and I was suddenly enjoying reading clear and punchy text about all kinds of topics that people hadn't been talking much about.

Then at some point it "clicked" and I was suddenly unable to not see it. Articles that I had thought sophisticated now came across to me as if they were written in crayon.

Enjoy it while you still can!

(And yes, the article here is very clearly AI written. Great content, written in crayon.)

Yeah, it is painful to me to read. I have to deal with enough in my work, which is almost 100 percent AI driven now.

I'd sincerely love to see them

Reply on news.ycombinator.com