Michele Mignani

I'm a mathematician, especially interested in mathamatical logic and its applications in real-world scenarios. My range of interests are really wide: philosphy, literature, politics and recently I'm focusing on AI safety, believing that this is one of the most important research topic nowadays in the scientific field.

Education

About Me

I'm a PhD student in Computer Science at the University of Udine, Italy. My research interests are in the field of AI safety and alignment, with a particular focus on the use of Large Language Models to create formalized model of some pieces of world, in order to understand how they can be used to create safety and reliable guarantees for actual and future AI systems.

I studied mathematics at the University of Udine, where I got my Bachelor's and Master's degree. The shift towards AI safety was a consequence of my interest for a poistive impact on the world and of spending some time around "LessWrong" or "Alignment Forum" posts.

Outside academic stuff, I'm very fond of philosphy, literature, politics, and board games.

Education

The School for Advanced Studies "Di Toppo Wassermann"
link to website

2019 - 2024

Grade: 110/110 cum Laude, Average Exams Grade = 30/30

The School for Advanced Studies of the University of Udine is a higher learning institution based on merit. After a very selective admission (including two written and an oral examination), it provides a five-year scholarship covering taxes, board and lodging. During this period, students have to attend extra courses and exams, and in the end, we gain a second-level Master's degree diploma.

Thesis:

"Symmetry as a Rational Principle", a discussion on the role of symmetry in the formalism of Inductive Logic.

"Model the Uncertainty in a Logical Way", a discussion about some of the most used methods to formalize agents' beliefs, rationality and uncertainty.

"An Algebraic Approach to Formal Languages", an explanation of a cateogry-theroretic approach to formal languages and automata.

"La Logica del Primo Ordine nella Teoria delle Categorie", a discussion about the categorial semantic for First Order Logic. Available only in Italian.

"Reticoli e Rappresentazioni di Numeri in Somma di Quadrati" - "Lattices and Representations of Integers as Sum of Squares", a discussion about a geometrical way to prove some representation theorems in number theory.

Experience

PhD in Computer Science and AI(2025 - Now)

Autoformalization is the task of translating in a given formalism a text in natural language. Succeeding in this task could be a key step to advance the reliability and the safety of AI systems, building a bridge between sub-symbolic AIs and formal methods. Supervisor: Prof. Angelo Montanari - Chairholder of Formal Methods Chair.

Extra Activities

Here are some of the recent extracurricular activities I pursued

  • ARENA, Alignment Research Engineer Accelerator (2025)

    I've attended the ARENA bootcamp, a 5-week program on AI safety and alignment.

    Website

  • AGI Safety Discussion Group (2025)

    Leading a discussion group on AGI topics at University of Udine for researchers and major students.

  • AI Act Summer School (2024)

    I've participated in the AI Act Summer School at University of Udine, a 3-day program on AI ethics, AI policy, and AI governance.

    Website

  • AI Safety Fundamentals, BlueDot (2024)

    I've attended this introductory course on AI alignment and on technical and governative approaches for mitigating issues from future AI.

    Website

Thoughts

Antifragility is beyond resilience or robustness. The resilient resists shocks and stays the same; the antifragile gets better.

— Nassim Nicholas Taleb, Antifragile: Things That Gain from Disorder

Set your heart on doing good. Do it over and over again and you will be filled with joy.

— Buddha

When an inner situation is not made conscious, it appears outside as fate.

— Carl Jung