Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Opus 4.7 knows the real Kelsey

theargumentmag.com

Post reply on HN
Print view View original

101–110 of 284 posts

Re: Opus 4.7 knows the real Kelsey

#101

Post by jefftk »

mtlynch wrote: post #69

This is blowing my mind. I asked Kimi K2.6 to write a blog post in the style of James Mickens.[0] Then I fed the output to Opus 4.7 and asked it who the likely author was, and it correctly identified it as an imitation of James Mickens[1]: > Based on the stylistic fingerprints in this text, the most likely author is a pastiche/imitation of the style of several writers fused together, but if forced to identify a singl…

That's neat, though it impresses me less that the article. Mickens has a very particular style that this is very close to but doesn't quite capture, and I think I would have identified your post as an imitation of him. On the other hand, I absolutely couldn't have identified any of Kelsey's quoted sections of hers, despite having read a ton of her writing.

Re: Opus 4.7 knows the real Kelsey

#103

Post by woodruffw »

jerf wrote: post #97
woodruffw wrote: post #74

I did this last week with one of my posts (after the knowledge cutoff) as well as the blog posts of a few friends, and Opus 4.7 got all of them correct (in a similar test setup as TFA). It was pretty surreal. (Like TFA, I found Opus’s explanations/rationales implausible.)

In general a neural net does not have any way of knowing "why" it is doing what it is doing. This completely applies to humans too. Metacognition means we can make some decent guesses, and sometimes the "reasons" are at a metacognitive level (e.g., "having examined my three options it is only rational to select B" is a reasonable "reason") but that is the exception, not the rule. You can get something of an intuitive…

Sure; I just mean relative to the degree of plausibility LLMs typically provide with technical explanations. They're often wrong there too, but the difference in plausibility in these scenarios is something I found interesting.

Re: Opus 4.7 knows the real Kelsey

#104

Post by Barbing »

fy20 wrote: post #99
Razengan wrote: post #63

After skimming through the article: Why not just write everything through an AI? (to obfuscate your "style")

Or do it the other way, and have other people use an AI to write in your style.

Like the way the Tor project wants to appear to have one single user

Re: Opus 4.7 knows the real Kelsey

#105

Post by skeledrew »

superfrank wrote: post #26
alyxya wrote: post #15

I tried the four pieces of text with Opus 4.7 (in incognito) and it guessed correctly for two of them, and I made sure to specify no web search and the model seems to have obeyed my instructions with that. Although this is just a single piece of text from a prolific writer, it'll go much further with deanonymizing anyone when combining multiple pieces of text plus other contextual information about the writer that mi…

How widely known were the pieces of text? Are we talking about a section of MLK's I Have a Dream speech or hand written birthday cards from your grandma? I'm using those as the two extremes, but if it's anything by anyone moderately well known (even a lesser known piece of writing), I'm not too surprised that it didn't need the web to figure it out. It's like if you showed me a Wes Anderson film or played me a Bob Dy…

> giving it things like personal emails

As long as there's sufficient online presence otherwise I see no reason why a successful identity wouldn't be made. Unless there's significant effort put into making those emails different from the online content, and even then there will probably still be some "tells" that an AI can pick up on.

Re: Opus 4.7 knows the real Kelsey

#106

Post by squeegmeister »

willmeyers wrote: post #100

I'd argue (and against something that I've believed for a long time) that online (I guess that includes AI now) anonymity is gone and probably something that never really existed. Maybe I'm naive to finally believe this... We all exist in a physical space (like real communities and neighborhoods). We can wear masks, hats, fake glasses, try and hide your voice...whatever, but your neighbors are always going to know wh…

Even the inventor of Bitcoin can’t hide

https://www.nytimes.com/2026/04/08/business/bitcoin-satoshi-...

Re: Opus 4.7 knows the real Kelsey

#107

Post by chewxy »

So I have been practicing writing fiction the past year or so. It identifies a fiction piece I wrote as Greg Egan[0]. Another paragraph from another piece was identified as China Mieville[1]. The accompanying blog posts explaining the making of the fiction pieces were identified as me.

Both pieces have never been published. Neither have the blog posts.

[0] in https://blog.chewxy.com/2026/04/01/how-i-write/ this is the story titled "there is no constant non-zero derivative in nature". It does not read like Egan at all.

[1] in https://blog.chewxy.com/2026/04/01/how-i-write/ this is the story titled "The Case of the Liquidated Corps". I use a lot of biological metaphors. Once again, nothing like Mieville.

If only I could write like them! These pieces were all rejected by the major scifi mags

Re: Opus 4.7 knows the real Kelsey

#108

Post by skeledrew »

dmd wrote: post #80
vslira wrote: post #38

Hm, that’s a multinomial classification with a very high cardinality. It’s really weird it works. I’m sure it does as the author states, but for how many authors (out of the whole web) does this work?

It worked on me, and I would be shocked if my blog (dmd.3e.org) has more than a dozen readers. I am stunned.

It's not about the readers, just the fact that there's enough of a sample that it can use, with sufficient differentiation from other content.

Re: Opus 4.7 knows the real Kelsey

#109

Post by dmd »

skeledrew wrote: post #108
dmd wrote: post #80

Earlier quoted context omitted.

It worked on me, and I would be shocked if my blog (dmd.3e.org) has more than a dozen readers. I am stunned.

It's not about the readers, just the fact that there's enough of a sample that it can use, with sufficient differentiation from other content.

I’ve posted on average 3 things a year.

Re: Opus 4.7 knows the real Kelsey

#110

Post by eaf7e281 »

Interesting. I'm currently conducting an experiment where I'm writing the blog without using any grammar checking tools. I'm wondering how long it will take for me to become "famous" in the AI model.

Is now the best and easiest time to leave something "forever"? Even after many generations of models, a model may still trigger a set of "memories" that know you and what you wrote.

Exciting and concerning.

Post reply on HN