Comment by lmz
2 days ago
> Model rewrites remove much of specific human dimension
Great. Isn't that part of being anonymous if one so desires? This would have decent potential to avoid stylometry deanonymization, no?
2 days ago
> Model rewrites remove much of specific human dimension
Great. Isn't that part of being anonymous if one so desires? This would have decent potential to avoid stylometry deanonymization, no?
Great? If you're worried that somebody's actively trying to identify your HN comments against some other source of your writing perhaps. But using a LLM to "avoid deanonymization" is about as sensible for some everyday Joe, as wearing a tinfoil hat in public to avoid 5G radiation is.
Yeah it's great if that's what you want to do. Whether it makes sense for any rando to do that is another question.
Whether it makes sense for anybody to do it is the real question. The threat model where this is a useful thing to do doesn't really exist in my opinion, at least not for obfuscating random comments. Perhaps if you're doing some anonymous journalism that's uncomfortable for your country's regime, and you've previously written other stuff using your real name, it might make sense to run your writing through a LLM, maybe. In addition to a bunch of other Snowden-esque countermeasures.
2 replies →