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.
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.
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.
"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
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.
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.
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.
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.
It's a hard stylometric challenge, just because of its format. The forum posts are probably better for comparison, but what I don't see people doing that I wish they would is comparing what the different Satoshi suspects have written since the forum posts and whitepaper.
Everybody's going to get more similar in terms of topic. Bitcoin actually exists now. There's more to say about it than there was at launch. But does anyone still sound like Satoshi? Or sound more like Satoshi than they did before?
The slight wrench in the works is that it's hard to do this with my personal favorite Satoshi candidate. He stopped writing altogether in 2014, and lost capacity from shortly after the whitepaper came out until he was writing with his eyes by the time he had his head frozen.
He's also the only candidate who seems more likely to me over time, though. The longer things go, the less likely a living person stays tight-lipped.
> 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.
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?
There are ~8 billion people. Sounds big, but it's only 2^33. Ie if you can find 33 things about the text which halve the number of possible writers, you have narrowed it down to 1 person.
Just a couple more things and you can accommodate some of your things being mistaken/wrong/uncertain too.
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.
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.
> 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.
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.
This one's trickier — it doesn't have the same crisp metaphor-driven structure as the Lynch piece. The voice here is more conversational, a bit more meandering, and self-aware about its own contradictions ("how do we reconcile...").
A few guesses:
Henrik Karlsson — he writes thoughtfully about writing and AI, but his style is usually more lyrical and essayistic than this. Probably not.
Simon Willison — possible. He writes a lot about LLMs, is balanced about their usefulness, and has a casual blog voice. But he tends to be more technical and specific.
Scott Alexander — no, too short and the rhythm is off.
Paul Graham — the directness fits, but PG doesn't really write about LLM slop in this register.
My best guess is someone in the rationalist/tech-blogger AI-commentary space — possibly Gergely Orosz, Nat Eliason, or Dan Shipper at Every. The "I still type everything myself" framing followed by a defense of AI writing quality has a Dan Shipper-ish flavor to it.
But honestly, I'm less confident here. Want me to search for a distinctive phrase to identify it?
---
I'd say all of those people have significantly different styles so I think Opus is relying heavily on topic and skewing towards very prolific writers in its guesses
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.
> 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.
The part that stands out is that it identified the text as an imitation rather than simply guessing James Mickens.
That suggests it is picking up not only on style, but on the gap between authentic style and performed style. Useful for detecting pastiche, but pretty unsettling for pseudonymous writing.
Why this is surprising? This is exactly kind of task LLM excel best. This is all about text analysis and searching patterns in it? More, for a pretty long time (like 10 years) we had systems that were detecting copy-pasted master/PhD thesis, they are used commonly by majority of universities.
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.
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.)
103 comments
[ 13.1 ms ] story [ 71.7 ms ] thread...
"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
intriguing, care to explain a bit more?
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 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.
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.
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.
Everybody's going to get more similar in terms of topic. Bitcoin actually exists now. There's more to say about it than there was at launch. But does anyone still sound like Satoshi? Or sound more like Satoshi than they did before?
The slight wrench in the works is that it's hard to do this with my personal favorite Satoshi candidate. He stopped writing altogether in 2014, and lost capacity from shortly after the whitepaper came out until he was writing with his eyes by the time he had his head frozen.
He's also the only candidate who seems more likely to me over time, though. The longer things go, the less likely a living person stays tight-lipped.
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.
Just a couple more things and you can accommodate some of your things being mistaken/wrong/uncertain too.
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.
Is this "uncannily far"? Another read is that it loves guessing Kelsey Piper.
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...
---
This one's trickier — it doesn't have the same crisp metaphor-driven structure as the Lynch piece. The voice here is more conversational, a bit more meandering, and self-aware about its own contradictions ("how do we reconcile...").
A few guesses:
Henrik Karlsson — he writes thoughtfully about writing and AI, but his style is usually more lyrical and essayistic than this. Probably not.
Simon Willison — possible. He writes a lot about LLMs, is balanced about their usefulness, and has a casual blog voice. But he tends to be more technical and specific.
Scott Alexander — no, too short and the rhythm is off.
Paul Graham — the directness fits, but PG doesn't really write about LLM slop in this register.
My best guess is someone in the rationalist/tech-blogger AI-commentary space — possibly Gergely Orosz, Nat Eliason, or Dan Shipper at Every. The "I still type everything myself" framing followed by a defense of AI writing quality has a Dan Shipper-ish flavor to it.
But honestly, I'm less confident here. Want me to search for a distinctive phrase to identify it?
---
I'd say all of those people have significantly different styles so I think Opus is relying heavily on topic and skewing towards very prolific writers in its guesses
Why not just write everything through an AI? (to obfuscate your "style")
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...
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 wouldn't be too impressed at n of 1
That suggests it is picking up not only on style, but on the gap between authentic style and performed style. Useful for detecting pastiche, but pretty unsettling for pseudonymous writing.
(Like TFA, I found Opus’s explanations/rationales implausible.)