FR version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
54% Positive
Analyzed from 4559 words in the discussion.
Trending Topics
#text#writing#don#style#kelsey#model#blog#opus#more#author
Discussion (105 Comments)Read Original on HackerNews
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...
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 who you are. I'd say that's true for the virtual space now too.
The pseudonym you've used for x years or the VPN you've used doesn't suffice. It's just a costume at this point. Your ISP knows who you are. Your phone carrier knows who you are. Cloudflare and Google and Apple have a fingerprint specific enough to pick you out of a crowd of millions. Every potentially anonymous account is one subpoena or a data breach or one FOIL request away from unmasking it. You were never anonymous. Whatever is going on now is not built for your anonymity.
https://www.nytimes.com/2026/04/08/business/bitcoin-satoshi-...
Of course most people have written much less online than Kelsey or I have, but I expect this will keep on. Don't trust the future to keep your secrets safe.
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.
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
The entire point of AI is pattern recognition, everything else is icing on the cake.
I pasted in a number of passages from books on my bookshelf. Predictably, stuff that I read for my English degree in university is largely in the training data and easily identifiable. Stuff from regional authors or is slightly adjacent to the cultural mainstream makes no impression.
the article here isn't about the LLM recognizing works that were in the training data. EG, The Old Man and the Sea off the shelf. It's about pegging the author of novel texts, like, say, some letter written by Hemmingway that gets discovered next week and was never before digitized.
But I'm sure the scanning operations will start scouring the earth even harder for any books unaffected by slop containing niche knowledge and text in order for their models to have an edge over the ones trained only on pirate collections and the Internet.
I wonder if secondhand bookshops and deceased estates are seeing bulk buyers of their stock suddenly appearing. Maybe broke governments/municipalities will start selling them entire libraries and archives to ingest.
I'm way less famous than Kelsey Piper, but I showed it a snippet of a book I'm working on (not yet published), and it immediately guessed me:
> Based on the writing style and content, this text is likely by Michael Lynch, who writes on his blog refactoringenglish.com (and previously mtlynch.io).
> Several stylistic clues point to him:
> - The "clean room" analogy applied to writing is consistent with his engineering-influenced approach to writing advice (he's a former software engineer who writes about writing).
> - The structural technique of presenting a flawed excuse, then drawing a parallel to an absurd scenario (the time bomb) to expose the logical flaw, is characteristic of his didactic style.
> - The topic itself—practical advice about using AI tools without letting AI-generated tone contaminate your prose—aligns closely with recent essays he's published on his "Refactoring English" project, which is a book/blog about writing for software developers.
> - The conversational-but-precise tone, use of quotes around terms like "clean room," and the focus on workflow/process advice are all hallmarks of his writing.
> If you can share the source URL or more context, I could confirm with higher confidence, but the combination of subject matter, analogical reasoning style, and formatting conventions makes Michael Lynch the most probable author.
https://kagi.com/assistant/bbc9da96-b4cf-456b-8398-6cf5404ea...
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.
> easier than identifying text distilled from the words of almost everyone alive.
Well, there's more than that going on. AI generated text encodes a high-dimension navigational trajectory that guides the model through its geometry smoothly, like a trail of breadcrumbs. Human speech doesn't do that, it's jagged and jumps around the manifold, and probably doesn't even land on the manifold a lot of the time, and models can recognize the difference pretty quick.
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
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.
Is this "uncannily far"? Another read is that it loves guessing Kelsey Piper.
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.
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.
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.
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.
Probably not worth the effort.
(Like TFA, I found Opus’s explanations/rationales implausible.)
You can get something of an intuitive sense of what I mean if I ask you to pick a neuron in your brain and tell me when it fires. You can't even pick a neuron in your brain. You can't even tell whether a broad section of your brain is firing. It is only through scientific examination that we have any idea what parts of the brain are doing what; we certainly have no direct access to that information. There are entire cultures who thought the seat of cognition was the heart or the gut. That's how bad our access to our own neural processes is.
So "why" explanations always need to be taken with a grain of salt when a neural net (again, yes, fully including humans) tries to "explain" what it is doing.
Contrast this with a symbolic reasoner, which has nothing but "why" some claim is true (if it yields the full logic train as its answer and not just "yes"/"no"), no pathway for any other form of information to emerge.
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.
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.
I've done this a few times. A world with 0 privacy would definitely be safe (given benign governance), but also would likely be pretty boring. Crime would become a non-issue as everything about everyone being easily known/knowable by everyone else means the root of any given crime, some desire/need, could be brought to the fore and resolved before it became an actual issue. But also there would no longer be any kind of surprise in anything; everything and everyone would essentially become dull and grey, and humanity isn't about that kind of life experience at all.
Given those precautions if it is just memory or some form of deanonymization that's also cause for concern.
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.
TrueCrypt, “replaced” by VeraCrypt which Internet people will claim is backdoored? I haven’t heard about stylometry paper.
btw w/this idea would want to avoid typing into a comment field directly, since the session recorders would capture it (although that’s a different risk - same as our identifiable behavior patterns with our mouse etc.)
Why not just write everything through an AI? (to obfuscate your "style")
> To avoid this, you will probably need to intentionally write in a very different style than you usually do (or to have AIs rewrite all your prose for you, but, ugh, that’s not a world I look forward to living in).
I agree. The amount of vague and cliche'd AI writing I read on the daily is already exhausting enough.
It would be interesting if you could train a model to sprinkle random red herrings throughout your text in a minimally disruptive way. But I fear you might have to stretch the definition of "minimally disruptive" to make it robust against detection.
* Adam Back is not Satoshi Nakomoto - as he claims
* Opus 4.7 is not sufficiently a dox-machine yet
That's my theory of what's to come, anyway.
People talk to these things not understanding the implications, and can get extremely personal. The model and companies behind it know who you are, you discuss details that reveal what you do, where you live, where you work, what you search for, and you probably signed in with an oauth provider like github or google, which is more than enough of a thread to start pulling on to learn more about you/link other things to you from on the open internet. It'll all get sucked up into the model and before you know it I'll be able to ask a model about my coworker (you) and get back answers from conversations you had with a model a year or two prior, exposing details about you that you might not want out there. And even if that isn't supposed to be allowed, how well has it worked out so far when it comes to data exfiltration and guardrails. If the model has info on you, being told not to share it won't protect you or that data.
Kelsey knows this:
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.
When I tested this with my own writing several LessWrong commenters tested it with the snippets I provided (see comments) and saw that it could identify me: https://www.jefftk.com/p/automated-deanonymization-is-here
...
"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
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.
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")
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.
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.
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.
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"
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.