Tag
The article argues that LLMs are increasingly capable of linking pseudonymous identities by analyzing writing style, and predicts a future where all high-bandwidth interactions leave unique fingerprints that can be traced.
This article discusses passive browser identification techniques using HTTP header order, IP options, user-agent strings, and random number generator patterns.
This paper introduces algometrics, a framework for time series forecasting under algorithmic feedback, proving that deployment risk differs from historical risk and is not identifiable from passive data alone. It provides methods for estimating deployment risk using interventions or randomized actions.