Large-Scale Online Deanonymization with LLMs
We measure the capabilities of LLMs to deanonymize users online.
TL;DR: We show that LLM agents can figure out who you are from your anonymous online posts...
Similar Articles (10 found)
🔍 65.8% similar
The Modern Data Toolbox: Combining LLMs, ML, and Statistics for Greater Impact
Co-written with
Matching the Tool to the Task
A Quick Recap
In our prev...
🔍 65.4% similar
Agree with much of this—particularly that these systems are uncannily good at inferring how to 'play along' with the user and extreme caution is there...
🔍 65.1% similar
Member-only story
How to 10x Productivity with AI
Unlock 5 high-impact techniques to apply LLMs
The development of LLMs has fundamentally changed the ...
🔍 63.6% similar
The three types of LLM workloads and how to serve them
We hold this truth to be self-evident: not all workloads are created equal.
But for large langu...
🔍 63.2% similar
Introduction
Artificial Intelligence (AI) dominates today’s headlines—hailed as a breakthrough one day, warned against as a threat the next. Yet much ...
🔍 62.6% similar
> the generation of 281,128 augmented examples, from which 1,000 were
held out as a benchmark test set.
This model is trained on a custom dataset of 2...
🔍 62.6% similar
You are a machine learning engineer at Facebook in Menlo Park. Your task: build the best butt classification model, which decides if there is an expos...
🔍 61.8% similar
Introduction
Zillow has been at the forefront of applying artificial intelligence (AI) in the real-estate domain since the release of the first Zestim...
🔍 61.1% similar
Frontier LLMs such as Gemini 2.5 PRO, with their vast understanding of many topics and their ability to grasp thousands of lines of code in a few seco...
🔍 60.5% similar
However, these benchmarks have an inherent flaw: The companies releasing new front-end models are strongly incentivized to optimize their models for s...