Opus 4.7 knows the real Kelsey • Hacker News Board

Re: Opus 4.7 knows the real Kelsey

#71

Post by tekacs » Fri, May 01, 2026, 12:48 AM UTC

nextaccountic wrote: post #25

tekacs wrote: post #23

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 presumabl…

> 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

Private / freshly written text, naturally. Public would've been relatively unsurprising.

Re: Opus 4.7 knows the real Kelsey

#72

Post by arjie » Fri, May 01, 2026, 12:49 AM UTC

lepset wrote: post #68

arjie wrote: post #53

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.

https://www.nytimes.com/2026/04/08/business/bitcoin-satoshi-...

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

Re: Opus 4.7 knows the real Kelsey

#73

Post by SoKamil » Fri, May 01, 2026, 12:52 AM UTC

arjie wrote: post #53

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.

Luckily for Nakamoto, there have been so many attempts at deanonymizing that I bet prediction is too contaminated with noise.

Re: Opus 4.7 knows the real Kelsey

#74

Post by woodruffw » Fri, May 01, 2026, 12:56 AM UTC

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.)

Re: Opus 4.7 knows the real Kelsey

#75

Post by daemonologist » Fri, May 01, 2026, 12:59 AM UTC

Extropy_ wrote: post #27

Someone ought to try feeding the BTC whitepaper in and share what comes out

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).

Re: Opus 4.7 knows the real Kelsey

#76

Post by Jordan-117 » Fri, May 01, 2026, 1:00 AM UTC

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…

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.

Re: Opus 4.7 knows the real Kelsey

#77

Post by brcmthrowaway » Fri, May 01, 2026, 1:09 AM UTC

daemonologist wrote: post #75

Extropy_ wrote: post #27

Someone ought to try feeding the BTC whitepaper in and share what comes out

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).

So train on pre 2009 mailing lost archive. Someone must be doing this surely.

Re: Opus 4.7 knows the real Kelsey

#78

Post by tempaccount5050 » Fri, May 01, 2026, 1:18 AM UTC

rdevilla wrote: post #41

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 sing…

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.

Re: Opus 4.7 knows the real Kelsey

#79

Post by pstuart » Fri, May 01, 2026, 1:21 AM UTC

atleastoptimal wrote: post #2

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.

I assume that there will be tools to refactor text to communicate the same intent but scramble the style. Using an LLM of course...

Re: Opus 4.7 knows the real Kelsey

#80

Post by dmd » Fri, May 01, 2026, 1:23 AM UTC

vslira wrote: post #38

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?

It worked on me, and I would be shocked if my blog (dmd.3e.org) has more than a dozen readers. I am stunned.