Large-scale online deanonymization with LLMs · HackerPapers discussions

Large-scale online deanonymization with LLMs — mentioned by Anon84

Tue, 26 May 2026 00:00:20 GMT

If by “one day” you mean Feb 2026… https://arxiv.org/abs/2602.16800

Paper and discussion history. A mention is not an endorsement.

Large-scale online deanonymization with LLMs — mentioned by leoc

Fri, 01 May 2026 17:06:56 GMT

> 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 In other words, that there's a bit of Akinator to how Claude is doing so well at identifying famous or somewhat-famous online writers. And of course it's not surprising that a machine-learning system will take every opportunity left open to it to "cheat". OTOH there are things like the "Large-scale online deanonymization with LLMs" paper https://arxiv.org/abs/2602.16800 which seem to show that current LLMs really can deanonymise…

Paper and discussion history. A mention is not an endorsement.

Large-scale online deanonymization with LLMs — mentioned by robotswantdata

Tue, 28 Apr 2026 18:29:28 GMT

See http://arxiv.org/abs/2602.16800 And http://news.ycombinator.com/item?id=33755016 Also http://github.com/antirez/hnstyle Glhf

Paper and discussion history. A mention is not an endorsement.

Large-scale online deanonymization with LLMs — mentioned by simianwords

Wed, 15 Apr 2026 16:29:10 GMT

It should be obvious that LLMs would be able to beat this with ease. Not sure why this paper deliberately skipped comparing to current LLMs Example of LLMs doing well in similar tasks: https://arxiv.org/abs/2602.16800

Paper and discussion history. A mention is not an endorsement.

Large-scale online deanonymization with LLMs — HN submission

Thu, 26 Mar 2026 11:00:05 GMT

Large-scale online deanonymization with LLMs

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large-scale online deanonymization with LLMs — HN submission

Mon, 23 Mar 2026 17:53:16 GMT

Large-scale online deanonymization with LLMs

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large-scale online deanonymization with LLMs — mentioned by Noaidi

Fri, 27 Feb 2026 14:24:13 GMT

Hey, iamnothere, look at this! https://arxiv.org/abs/2602.16800 "We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hacker News users and Anthropic Interviewer participants at high precision, given pseudonymous online profiles and conversations alone, matching what would take hours for a dedicated human investigator. "

Paper and discussion history. A mention is not an endorsement.

Large-scale online deanonymization with LLMs — mentioned by FrasiertheLion

Wed, 25 Feb 2026 17:31:24 GMT

Recent paper by Nicholas Carlinini and others really showcases how little it takes to deanonymize users across platforms with LLMs: https://arxiv.org/abs/2602.16800

Paper and discussion history. A mention is not an endorsement.

Large-scale online deanonymization with LLMs — HN submission

Wed, 25 Feb 2026 16:44:58 GMT

Large-scale online deanonymization with LLMs

https://arxiv.org/pdf/2602.16800

78 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large-scale online deanonymization with LLMs — HN submission

Tue, 24 Feb 2026 17:18:17 GMT

Large-Scale Online Deanonymization with LLMs

Pdf: https://arxiv.org/pdf/2602.16800 (via https://arxiv.org/abs/2602.16800)

364 points; 234 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large-scale online deanonymization with LLMs — HN submission

Sun, 22 Feb 2026 17:01:52 GMT

Large-scale online deanonymization with LLMs (including HN users)

3 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large-scale online deanonymization with LLMs — HN submission

Sat, 21 Feb 2026 17:44:36 GMT

Large-scale online deanonymization with LLMs

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large-scale online deanonymization with LLMs — HN submission

Fri, 20 Feb 2026 17:25:01 GMT

Large-scale online deanonymization with LLMs

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.