Federico Torrielli's picture

Federico Torrielli

EvilScript

·

https://federicotorrielli.github.io

AI & ML interests

AI Safety & Mechanistic interpretability

Recent Activity

upvoted a paper about 3 hours ago

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

new activity 3 days ago

aisilab/moltbook-files-new-language-signals:Add paper link, GitHub repository, and task category

authored a paper 4 days ago

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

View all activity

Organizations

EvilScript 's papers 3

arxiv:2605.31170

arxiv:2605.26045

arxiv:2605.07462