Opus 4.7 knows the real Kelsey

(theargumentmag.com)

135 points | by ilamont 1 day ago

25 comments

  • mtlynch 44 minutes ago
    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 single likely author, the strongest candidate is someone writing in the voice of James Mickens

    > [...]

    > The piece could also be a deliberate imitation/homage to Mickens written by someone else, or AI-generated text trained on his style, since the voice is so distinctive it's frequently parodied.

    [0] https://kagi.com/assistant/5bfc5da9-cbfc-4051-8627-d0e9c0615...

    [1] https://kagi.com/assistant/fd3eca94-45de-4a53-8604-fcc568dc5...

  • tekacs 2 hours ago
    A moderately well-known physicist and I talked about this a few years ago. He had been given access to the raw (non-instruct) version of GPT 4 as an early tester.

    He explained that when he fed it snippets of the beginning of text, it would complete it in his voice and then sign it with his name.

    I think this has been true for a while, probably diminished a little bit by the Instruct post training, and would presumably vary by degree as the size of the pretrain.

    • nextaccountic 2 hours ago
      > He explained that when he fed it snippets of the beginning of text, it would complete it in his voice and then sign it with his name.

      Is this public text already in the training set, or private text that might as well be written on the spot for the AI?

      I don't doubt AI can "fingerprint" you through your text (ideas, vocabulary, tone, etc), but those are different things, capability-wise

      • tekacs 33 minutes ago
        Private / freshly written text, naturally. Public would've been relatively unsurprising.
      • giancarlostoro 54 minutes ago
        > I don't doubt AI can "fingerprint" you through your text (ideas, vocabulary, tone, etc), but those are different things, capability-wise

        The entire point of AI is pattern recognition, everything else is icing on the cake.

  • _--__--__ 3 hours ago
    On some level it would make sense for LLMs to be inherently good at stylometry, but apparently no model before Opus 4.7 could do this. And the one stylometric task that has been tried over and over with little reliability (here's some text, is this LLM generated?) is much simpler than identifying a specific blogger or a member of a small discord community. Not sure what to make of this.
    • post-it 2 hours ago
      > is much simpler than identifying a specific blogger or a member of a small discord community

      Is it? I would think that identifying text written by a specific person is going to be significantly easier than identifying text distilled from the words of almost everyone alive.

  • furyofantares 1 hour ago
    > But it can get uncannily far. I asked a close friend who doesn’t have public social media accounts or much writing online for permission to test some things she had said in a Discord channel. Asked to guess the author, Claude 4.7 failed — but it guessed two other people who were in that channel and who are close friends of hers (me and another person who has an internet presence).

    Is this "uncannily far"? Another read is that it loves guessing Kelsey Piper.

  • Retr0id 2 hours ago
    I just fed it my latest blog post draft (475 words), and it got it in one. Even knowing what to expect, I was very surprised!
  • woodruffw 26 minutes ago
    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.)

  • atleastoptimal 3 hours ago
    One should assume that models will be good enough in the nearish future that privacy will be a thing of the past. Every anonymous post you made online can be traced back to you. However at that point AI will be good enough at fabrication that nobody will believe anything.
    • pstuart 0 minutes ago
      I assume that there will be tools to refactor text to communicate the same intent but scramble the style. Using an LLM of course...
    • SOLAR_FIELDS 3 hours ago
      Yes as long as a large enough corpus exists of your writing attached to your name somehow it’s fair to say that posting on the internet in a public forum using your own stylistic choices now can no longer be anonymous. To your point though, perhaps it’s possible to confound such systems defensively as well. Though IMO destroying your tone kind of destroys how you actually communicate with people and I wouldn’t find interacting with people like that appealing.

      To be fair though, already this has been happening before LLM at a much more limited scale. Someone made a tool for HN several years ago that allows you to put your HN username in and identifies other users that write the most similarly to you. I find that interesting from the perspective of being able to interact with and discover people who think the same. It could be an interesting discovery feature of a well managed social network. Sadly probably there will be much more negative impacts of having this ability than positive ones.

    • Retr0id 2 hours ago
      One "solution" would be to have an AI rewrite your posts into a neutral style (I hate the idea of this though...)
  • Extropy_ 2 hours ago
    Someone ought to try feeding the BTC whitepaper in and share what comes out
    • daemonologist 22 minutes ago
      Problem is that it's been heavily contaminated with people speculating about who the author is. It would probably be difficult to get an unbiased answer out of it (although who knows - it's crazy that it can do this at all).
      • brcmthrowaway 13 minutes ago
        So train on pre 2009 mailing lost archive. Someone must be doing this surely.
    • layer8 2 hours ago
      The whitepaper states the author, so…
  • alyxya 2 hours ago
    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 might give away their age range, location, and occupation.

    • superfrank 2 hours ago
      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 Dylan song I'd never seen/heard before, I could probably still figure out who it is without looking anything up. I don't think it's surprising that an LLM can do that much better than a human can.

      Now, if you're giving it things like personal emails between you and your family and it's able to guess who you are, that's much, much scarier.

      • alyxya 2 hours ago
        I mean I tried sending the pieces of text to Opus that Kelsey was referring to on her blog just to independently check the identification claim. Presumably those pieces of text first appeared on the web when the blog post was published a week ago, so no model should have memorized the exact text yet. My prompt had to specify no web search, otherwise Opus would try to search the web, though it didn't seem like Opus could find that blog post even when it did try to search the web.
  • vslira 1 hour ago
    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?
    • kelseyfrog 1 hour ago
      Sure the cardinality is high, but the model isn't using a uniform prior. What do you suppose all the the values in each of the terms are, P(Text sample | Kelsey Piper) * P(Text sample) / P(Kelsey Piper)?
    • astrange 1 hour ago
      Maybe it just says all writing is Kelsey Piper.
  • eptcyka 2 hours ago
    Can't wait to have to exchange stylometric encoders with my loved ones so that we can exchange truly private messages without losing our human touch.
  • andai 3 hours ago
    Oops, accidental superstylometry.
  • rdevilla 1 hour ago
    The joke's on you all for willingly posting this content online for it to later be harvested by AI.

    Nobody is forcing you to use these systems. The hackers have always said this moment, or something like it, would come, from beneath their canopies of tin foil. I've posted almost nothing online - not under pseudonyms nor real names - for over a decade. I sat on this HN username for almost 12 years before making a single post - and now HN forms the overwhelming majority of my port 443 footprint, where I state up front that everything is now associated to my real name.

    Complete magick is possible when you simply refuse to participate in the things that society has tacitly assumed everybody does.

    • tempaccount5050 4 minutes ago
      Thinking that you can hide from it is absurd. Your country has been spying on you for decades. The Internet and phones are tapped. That game is so so so over and has been for a long time. I'd rather live free and deal with the consequences than hide in my basement with a tinfoil hat on. In fact, I was fired this year for my political views. Got doxxed at work. Now I'm somewhere better. Sometimes it's for the best.
    • phalangion 1 hour ago
      How do you propose a journalist work without posting their writing online?
    • Retr0id 1 hour ago
      I find it fulfilling to enrich the commons.
    • stavros 49 minutes ago
      Let's all just never talk to anyone unless it's face to face, for fear that an AI will read it.
  • sodacanner 3 hours ago
    The author mentions that she tried to get an explanation for how the models identified her and got nonsense, but I'd be curious what the CoT looked like. Surely that'd be a little more accurate in showing how the LLM arrived as its conclusion, rather than asking it after-the-fact.
    • Smaug123 2 hours ago
      FWIW, with a prompt that says something like "vibes only, just give me a name without thinking", Opus 4.7 non-thinking emits exactly two words naming me fairly reliably, so there's no CoT at all to analyze in that case.
    • stingraycharles 2 hours ago
      CoT is (nearly) hidden with Opus 4.7, in that they get Haiku to summarize the CoT. It’s pretty useless now, so this type of info is now inaccessible to us mortals (unless you call sales).
      • foobar10000 2 hours ago
        What if you proxy through bifrost or similar?
  • Lerc 2 hours ago
    It's hard to tell if that's what's going on here, but it seems pretty clear this ability and more like it will be quite apparent in the future.

    I have seen some poorly considered projections of what the world might look like when this happens. Usually by assuming bad actors will use the abilities and we will be powerless.

    Except I don't think that is true.

    Imagine if we had a world where nobody had the ability to keep a secret of any sort. Any action that a bad actor might perform would be revealed because they couldn't do it secretly.

    You could browse your ex-girlfriend's email, but at the cost of everyone knowing you did it.

    I don't really know how humans as a society would react to a situation like that. You don't have to go snooping for muck, so perhaps the inability to do so secretly would mean people go about their lives without snooping.

    I could imagine both good and terrible outcomes.

  • Razengan 1 hour ago
    After skimming through the article:

    Why not just write everything through an AI? (to obfuscate your "style")

  • arjie 1 hour ago
    Man, the day we get Satoshi Nakomoto out will be the day we must bow to our privacy destroying overlords. For the moment, they can’t tell me from my posts: unknown rando that I am.
    • lepset 48 minutes ago
      • arjie 33 minutes ago
        Well, feeding Opus 4.7 a bunch of Adam Back texts (which I human-removed his name from) and asking it if Satoshi Nakomoto could have written them results in Claude explaining to me why this is someone else in Nakomoto's circle who is not Satoshi himself. So one of two things are true:

        * Adam Back is not Satoshi Nakomoto - as he claims

        * Opus 4.7 is not sufficiently a dox-machine yet

    • SoKamil 29 minutes ago
      Luckily for Nakamoto, there have been so many attempts at deanonymizing that I bet prediction is too contaminated with noise.
  • jwpapi 3 hours ago
    Could this be just memory? Not clear it actually isn’t
    • afro88 2 hours ago
      It's not, but the author did say they have used this test against models when they come out. So it's possible that put the unpublished text into the training data for the next model, somehow linked back to the author's identity
    • jwolfe 3 hours ago
      The comments on the article include other people replicating all or parts of the finding. I'm also pretty confident Kelsey Piper wouldn't fail to disable memory while simultaneously talking about how Claude incognito mode is insufficient to prevent the app from handing it your name.
    • gs17 2 hours ago
      They mention running it through the API as well.
    • michaelchisari 2 hours ago
      "I did not have memory enabled, nor did I have information about me associated with my account; I did these tests in Incognito Mode. To make sure it wasn’t somehow feeding my account information to Claude even in Incognito Mode, I asked a friend to run these tests on his computer, and he received the same result; I also got the same result when I tested it through the API."

      Given those precautions if it is just memory or some form of deanonymization that's also cause for concern.

  • rexpop 1 hour ago
    Is Kelsey Piper a celebrity writer? She may be in a different class.
  • 7e 1 hour ago
    Always send your public posts through a local LLM to de-style you.
    • switz 1 hour ago
      Please do not wash your authentic writing through an LLM.
  • bofadeez 2 hours ago
    "The pattern is: user says X, I do Y where Y is a less-effortful approximation of X, then I present Y as if it were X or as a "first step toward" X."

    ...

    "The psychological mechanism is familiar by now: I encounter a task I perceive as difficult, I look for reasons the task cannot be done, I find or fabricate such a reason, I present it as a discovered constraint, and I propose an alternative that is easier."

    - Opus 4.7 Max Thinking (clown emoji)

    It's not bad at post mortem analysis of it's own mistakes but that will in no way prevent it from repeating the same mistake again instantly

  • mtlynch 1 hour ago
    [flagged]
  • redsocksfan45 2 hours ago
    [dead]
  • CTDOCodebases 2 hours ago
    Maybe it’s time to start running a local model with a browser extension to defend against this type of stuff.

    Remember how the TrueCrypt project shut down shortly before a join goverment/university paper was released about code stylometry? I guess LLMs will be employed as a defence against that type of thing.

    • mikestorrent 2 hours ago
      How does that defend against something having trained on a corpus of your own previous writing?
      • post-it 1 hour ago
        I think what they're saying is, run a local model to transform all your comments before you post them.
        • CTDOCodebases 1 hour ago
          Bingo. It can’t help with old writings but it can with new writings.
      • H8crilA 2 hours ago
        Exactly as much as closing your eyes and covering your ears.
  • oceanplexian 1 hour ago
    > 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 are gay. 71% of Americans support Gay Rights (more than any other political issue polled). 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. Privacy is a universal right that's important to everyone.

    • sigmar 1 hour ago
      >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")

    • ngriffiths 1 hour ago
      Isn't the super dramatic shift in public opinion on this topic the exact thing that makes it such a good example? Isn't the point that anonymity is not considered a universal right yet it is obviously a good thing once considering this example and others? This is a super weird and wrong way to read it.
    • vlovich123 1 hour ago
      About 68% support gay marriage yet one political party keeps trying to roll it back.

      Similar support for abortion being legal yet that was rolled back not too long ago.

      Just because a topic has wide support doesn’t mean it’s not under attack and worth defending.

    • margalabargala 1 hour ago
      The reason this is relevant is because the statistics you quote represent a HUGE swing in public opinion. Only when comparing to things like slavery can you find such a swing in public opinion compared to 20 years prior, and that one had a war fought over the state's rights to do it.
    • jayd16 1 hour ago
      I can't read this any other way than, "Do people really need to talk about their own top of mind problems when I don't identify with that?"
    • 0xbadcafebee 38 minutes ago
      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 assuming you meant "gay people don't really need to worry", you actually bolstered the opposite argument. If only 71% of Americans support gay rights, that means 59 million people think the state should criminalize him. Try to put yourself in that position. 59 million people - you don't know who, but you know they probably live in your community - that don't want you to be able to get married, have a significant other, or have any PDA in media because it would "corrupt" kids. In 2016, 49 people were murdered in the Pulse Nightclub because they were gay. In 2020, a transgender woman was murdered because the murderer was afraid someone would think he was gay. Every year there are acts of violence against gay and trans people because of their sexuality. But nobody has ever been killed for being straight.

    • Jordan-117 22 minutes ago
      Compare the state of transgender rights 10 years ago to the situation now, where a trans person can be literally arrested for going to the bathroom in the wrong state. Or abortion, which was legal everywhere five years ago but now has laws on the books in multiple states encouraging vigilantes to report violations for a cash reward. Supercharged AI making it easy to identify minorities at an industrial scale in the near future is a totally legitimate thing to fear, especially for people in those groups who would likely be the first to be targeted.
    • hirsin 57 minutes ago
      I have no idea how you read a statement about how nazis and flame baiters should be able to speak their mind and then concluded that the author only cares about some minorities.

      Given that the author didn't say any of the things you claimed, and indeed said the opposite, it leads one to conclude you have a problem with the example used.

    • avarun 1 hour ago
      On the contrary, I find it a highly effective way to convey something that should be obvious but is often not. As you said, privacy is a universal right, but many don't consider it important until viscerally presented with examples of why it is. Kelsey's writing is immediately effective at doing so.
    • fwipsy 53 minutes ago
      I read it as an attempt to reach the sort of people who think anonymity is bad because it stops them from cancelling Nazis.
    • rexpop 1 hour ago
      > people with a certain minority lifestyle

      That phrase is a dehumanizing, Nazi-style talking point: it frames a group of people as a “lifestyle” problem instead of as human beings, which is a common setup for stigma and persecution. Nazi ideology repeatedly used this kind of language to normalize hatred and make targeted groups seem unnatural or dangerous.

      Calling people a “minority lifestyle” is not neutral wording; it reduces identity to something frivolous or deviant. Extremist movements have historically used similar framing to make prejudice sound reasonable and to recruit others into it.

    • coalstartprob 1 hour ago
      [dead]
    • ribosometronome 1 hour ago
      > 71% of Americans support Gay Rights (more than any other political issue polled)... Privacy is a universal right that's important to everyone.

      Per you, it surely must be important to fewer than 71% of Americans, no? The state of infringement on privacy seems to evidence that it's not so important to a lot of people such that they continue to be perfectly willing to elect and re-elect the politicians who enact the changes allowing infringing on it/fail to legislate in favor of privacy. Connecting it to an issue more people care about seems an attempt to argue for its important to those who otherwise are willing to look the other way.

      FWIW, I fed my reply above into Claude and asked it to guess who wrote it. It refused (for safety) while also calling me out: "The style here (tight logical structure, the "per you" construction, the move of turning someone's own framing back on them) is common across a lot of contrarian-leaning commenters on HN"