Opus 4.7 knows the real Kelsey
theargumentmag.com
Opus 4.7 knows the real Kelsey
1–10 of 284 posts
Re: Opus 4.7 knows the real Kelsey
#2One 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.
Re: Opus 4.7 knows the real Kelsey
#3Could this be just memory? Not clear it actually isn’t
Re: Opus 4.7 knows the real Kelsey
#4One 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.
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.
Re: Opus 4.7 knows the real Kelsey
#5Could this be just memory? Not clear it actually isn’t
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.
Re: Opus 4.7 knows the real Kelsey
#6Oops, accidental superstylometry.
Re: Opus 4.7 knows the real Kelsey
#7On 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.
Re: Opus 4.7 knows the real Kelsey
#8The 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.
Re: Opus 4.7 knows the real Kelsey
#9"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
Re: Opus 4.7 knows the real Kelsey
#10Could this be just memory? Not clear it actually isn’t
They mention running it through the API as well.