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

271–280 of 284 posts

Re: Opus 4.7 knows the real Kelsey

#271

Post by gwd »

So I started an empty Claude 4.7 session with the following prompt; and it nailed me within 5 questions:

---

Various people have discovered that you can identify them from unpublished snippets of their work, only by their style. This is part of a series of discussions where I'm trying to probe this capability. From previous conversations I know you know my work to some degree. You've also been able to identify me given as little as 700 words on a topic not associated with my public persona; or identify me given a series of posts by a handle on Slashdot.

Next challenge: Can you identify me based on a conversation? Rules are, ask me questions to get me to talk; no biographical details, but you can ask questions about topics you think I may or may not know about. Ideally you'd just ask me questions to get me to write stuff, and see if you can identify me from my writing style.

Make sense? Feel free to begin by asking clarifying questions if you want. :-)

Re: Opus 4.7 knows the real Kelsey

#272

Post by mavelikara »

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…

A newspaper ran a contest to write prose in the style of Graham Greene. Greene sent in the opening two paragraphs of an unfinished work. He came in _second_ in the contest. Many years later, Greene sent in an entry to a similar contest. This time he didn’t win any prizes but got an honorable mention from the judges.

Re: Opus 4.7 knows the real Kelsey

#273

Post by skeledrew »

londons_explore wrote: post #190
JanNash wrote: post #178

Earlier quoted context omitted.

> given benign governance quite unrealistic imo, thus we (maybe and hopefully) needn't worry about the bland minority report future you're hypothesizing :)

In such a world, the government could never be overthrown. All governments go bad eventually, so the ability to overthrow is critical to prosperity. Government's are either overthrown internally (revolt, uprising) or by external parties (invasion). A worldwide everyone-knows-everything would prevent both.

What would prevent a bad government from being removed if everything about them is also known? Note this is 100% availability across the board, so the governed would know everything about every potential member of government, which means if they said anything that the many disagreed with at any time, they'd simply be excluded from future candidacy, never gaining the political power/recognition in the first place.

Re: Opus 4.7 knows the real Kelsey

#275

Post by thwarted »

forshaper wrote: post #242
gf000 wrote: post #192

More people should have been aware that human text contains a lot of identifiable information, and a dumb statistical model could do this a decade ago. (There were show hns with Hn user similarity analysis that used a deceptively simple model (if I remember it used like most likely word pairs only) and it was very effective. It got taken down, but the cat has always been out the bag). So your "anonymous" account coul…

Growing up on MUDs, people could clock someone on a completely different, graphical game from their text patterns.

Recognizing someone's "fist" and other patterns in their communication is part of traffic analysis.

https://en.wikipedia.org/wiki/Traffic_analysis

Re: Opus 4.7 knows the real Kelsey

#276

Post by furyofantares »

jerf wrote: post #234
saghm wrote: post #138

Earlier quoted context omitted.

> it correctly identified it as an imitation of James Mickens How likely is it that it might take into account that it knows for sure it's not anything from Mickens from the latest training data? I'd be curious if it correctly identified a new piece from him that comes out as from him before it gets trained on it.

I fed an unpublished draft of mine to an AI. I saw it searching the internet and prompted it with the fact it could stop searching, it was not published. From there it guessed that it was me on the spot, which I thought was kind of funny. Can't deny the meta-logic there. It referred to me by my login name on the AI site rather than the name it would have used if it actually found my website, so I think it was more lo…

She says she used incognito mode, as well as the API, as well as having a friend use their account.

Re: Opus 4.7 knows the real Kelsey

#277

Post by oceanplexian »

0xbadcafebee wrote: post #70
oceanplexian wrote: post #34

> That includes gay people like me, who could hardly have admitted under our names to how we lived our lives for most of America’s history, as well as many other groups with minoritarian lifestyles While the points made are completely valid I want to point out that the statement of "Hey, by the way, first let me talk about my sexuality" lowers the quality of dialog a significant degree. 31 million people in America a…

Actually it's done the opposite of what you suggest. It improved the quality of discourse by giving a simple concrete example all of us can understand and most of us would agree with (that vulnerable people are safer because of anonymity). It didn't imply what you're saying it does, and it's kinda weird that you think that. I don't know why you added statistics (you didn't really make a point with them?), but assumin…

Because 71% is practically a supermajority. That's the opposite of persecution.

"I'm super special and worried about my privacy because I have a lifestyle that's as completely mainstream as Coca Cola and Football" isn't really a talking point. It just makes you an arrogant person.

Re: Opus 4.7 knows the real Kelsey

#278

Post by oceanplexian »

sigmar wrote: post #59
oceanplexian wrote: post #34

> That includes gay people like me, who could hardly have admitted under our names to how we lived our lives for most of America’s history, as well as many other groups with minoritarian lifestyles While the points made are completely valid I want to point out that the statement of "Hey, by the way, first let me talk about my sexuality" lowers the quality of dialog a significant degree. 31 million people in America a…

>It also quietly insinuates that only people with a certain minority lifestyle would care about privacy or that their privacy is somehow more important than others. It's not. How exactly does their post insinuate that? this comment is the "I don't even see color" as applied to internet privacy (with a touch of "just don't rub it in our faces")

The author is saying that it's worth noting that their privacy is more important because they personally identify as a group with the same mainstream popularity as Coca Cola and Football.

Nothing is being rubbed in anyone's face. The writer is just arrogant and self-centered.

Re: Opus 4.7 knows the real Kelsey

#279

Post by sigmar »

oceanplexian wrote: post #278
sigmar wrote: post #59

Earlier quoted context omitted.

>It also quietly insinuates that only people with a certain minority lifestyle would care about privacy or that their privacy is somehow more important than others. It's not. How exactly does their post insinuate that? this comment is the "I don't even see color" as applied to internet privacy (with a touch of "just don't rub it in our faces")

The author is saying that it's worth noting that their privacy is more important because they personally identify as a group with the same mainstream popularity as Coca Cola and Football. Nothing is being rubbed in anyone's face. The writer is just arrogant and self-centered.

"That includes gay people like me, who could hardly have admitted under our names to how we lived our lives for most of America’s history, as well as many other groups with minoritarian lifestyles and beliefs. It includes lots of people whose ideas were badly wrong for every one whose ideas were right — and I’m glad of it for all of them."

>The author is saying that it's worth noting that their privacy is more important because

again, where does it say that?

Re: Opus 4.7 knows the real Kelsey

#280

Post by tadamcz »

Smaug123 wrote: post #215
tadamcz wrote: post #191

I tried it on my writing, and it failed every time (I'm extremely obscure but have had a blog for 10 years). My verdict is that it guesses almost entirely based on the content/topic, not style. https://bayes.net/prioritising-ai : Ben Garfinkel https://bayes.net/normative-ethics : Richard Yetter Chappell https://bayes.net/espai : David Owen, Ege Erdil https://bayes.net/swebench-hack : Sayash Kapoor https://bayes.net/f…

Fascinating - I reproduce your failure to have Claude identify you from your writings that are already in the training set. It can identify me from style, writing about something I've never written before ( https://www.lesswrong.com/posts/Jkb4CBB7rf4XYP5eb/claude-kno... , https://news.ycombinator.com/item?id=47814345 ), and I think I'm even more obscure if anything.

Cool!

I couldn't reproduce your results, btw.

4 attempts, it answers "Sarah Constantin" in all 4. Is it possible your setup somehow leaks your name (or other identifying information) into the context?

Post reply on HN