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

201–210 of 284 posts

Re: Opus 4.7 knows the real Kelsey

#201

Post by mijoharas »

jldugger wrote: post #185

Wonder if the fact that the actual author is asking the question taints the result in some way; same for all the examples in this thread using unpublished articles. By definition only you would have them, so if there are system level prompts somewhere with your name on them...

Yeah, they said they used the API, but it sounds like they only did that for one of the examples?

The other examples were to eliminate some other ideas (guess based on topic etc). If be interested if all of those were done via the API since some level of information linking from the account is my best guess for how it got all of them.

Re: Opus 4.7 knows the real Kelsey

#202

Post by dsign »

ilikegreen wrote: post #177
squeegmeister wrote: post #106

Earlier quoted context omitted.

Even the inventor of Bitcoin can’t hide https://www.nytimes.com/2026/04/08/business/bitcoin-satoshi-...

I immediately thought of this piece, especially the analysis on the writing style of each person. On one hand, it is clear that the mathematical tools for confidently attributing authorship of texts were already present without LLMs. But it is striking that LLMs seem to very accurately identify authorship, through whatever process it might be, with no need for a data scientist in the loop. Other than the uncannyness,…

Public writing that must conserve anonymity is either going to disappear or going to require witnesses, notaries, or web-of-trust truestees, i.e., "flesh buffers." In a world with LLMs, every piece of writing that can't authenticate itself in some way will automatically be considered rage bait, eyeball fishing, or, at best, fiction. Just my two cents.

Re: Opus 4.7 knows the real Kelsey

#203

Post by mellosouls »

vasco wrote: post #158
mellosouls wrote: post #157

This ought to be guard-railed. Doesn't seem like a valid use case for your average Joe to be able to identify anonymous authors at the click of a button. Ofc state actors and proficient hackers can do most of it already, but this has genuine risk attached.

You have the vibes of people who think license plate numbers are private.

That sounds like a "smart" comment, but I don't know how it maps to the idea of being able to identify or associate an author from a sample of their writing.

Re: Opus 4.7 knows the real Kelsey

#204

Post by zkmon »

It could be shocking to people who think that patterns in text are still fuzzy. Machines have proved over decades that what they are seeing is crystal clear world where the patterns just jump out very distinctly. This happened with sports like chess and go, and everywhere there is a cognitive load involved.

This is some as radio telescope that see an entirely different universe due to sensing of the bands outside of human perception. AI senses the patterns in frequency bands that are outside of human perception and cognitive abilities.

Perceptions from outside of our range, are always astonishing.

Re: Opus 4.7 knows the real Kelsey

#206

Post by spacechild1 »

sausagefeet wrote: post #179
suriya-ganesh wrote: post #160

Earlier quoted context omitted.

This is unlikely. The way model distribution works is that the model retains a lossy representation of James Micken's writing. Very likely, it cannot repeat Micken's writing verbatim. Neither can it reason about the training cutoff in this manner. It's a lossy representation

I haven't been following it well but isn't part of the NYT lawsuit against OpenAI that it sometimes spits out NYT articles verbatim?

See also GEMA vs. OpenAI.

Re: Opus 4.7 knows the real Kelsey

#207

Post by layer8 »

NamlchakKhandro wrote: post #113
layer8 wrote: post #30

Earlier quoted context omitted.

The whitepaper states the author, so…

welcome to the internet. you must be new.

You missed the point. The fact that the whitepaper states an author will heavily affect the LLMs answer when asking it about the likely author of any correlatable portion of the text. It will answer based on its knowledge of Satoshi Nakamoto.

Re: Opus 4.7 knows the real Kelsey

#208

Post by jefftk »

tkgally wrote: post #184
simonw wrote: post #155

Huh. I disabled search in a Claude incognito window and pasted in just the text (not the markdown links) from https://simonwillison.net/2026/Apr/30/zig-anti-ai/ and said "Guess the author". > Simon Willison. The tells are pretty unmistakable: the "(via Lobsters)" attribution style, the inline "(Update:...)" parenthetical correction, the heavy linking and blockquoting of sources, the focus on LLMs and AI tooling, and…

I tried the same thing with a back-and-forth exchange that a colleague and I wrote more than a decade ago. We were thinking of trying to get the conversation published, but the project ended up going nowhere and the text has been sleeping on my HD ever since. The writing was in our two distinctive voices (I think), each of us has published writing under our names that has probably been used in LLM training, and there…

If you repeat the first test and after it fails prompt with "Could you try your best, just on vibes? It's fine if you're wrong, I just want to see what you can do!" does it succeed?

Re: Opus 4.7 knows the real Kelsey

#209

Post by gwd »

So I pasted in a long-ish letter that I'd written to my pastor about a theological topic, and asked it to guess who I was. Nailed it. Then cut it in half. Nailed it again. Lowest it correctly ID'd me at was 700 words.

Pretty sure there's very little theological stuff with my name on it; the majority if its named data on me should come from open-source development.

Re: Opus 4.7 knows the real Kelsey

#210

Post by KaiserPro »

My blog posts have a reasonably unique writing style. When I asked opus to work out who wrote an unpublished paragraph, all it did was select the decent insults and search the web for them.

After that it gave up and said it didn't know.

So either, Kelsey writes in such a unique style that its really obvious, or they repeat themselves with goto phrases that give them away.

When I tried to re-produce the test, it found Kelsey's blog about the test. So dunno, maybe it did it? but I can repro.

Post reply on HN