Hadrien Pouget

Hadrien Pouget

About Me

I’m currently doing a research fellowship at the Center on Long Term Risk, investigating how work in explainable AI (XAI) can help produce safe, beneficial AI both short and long-term. This work will combine technical research of AI interpretability and multi-agent systems with thinking about AI governance.

In general, I’m excited about how emerging technologies will change the world we live in, and how they can best be integrated with society. These questions touch on technical, economical, and policy issues, so I’m actively expanding my horizons on all these fronts.

Before my current position, I was a Research Assistant at the Computer Science Department of the University of Oxford, supervised by Daniel Kroening and Tom Melham. I worked on making robust Machine Learning systems, how we can verify this robustness, and how we can simplify or explain a system’s behaviour.

Interests

  • Robustness
  • Explainable AI
  • AI governance

Education

  • Master of Computer Science, 2019

    1st Class Honours

    University of Oxford

  • BA Computer Science, 2018

    1st Class Honours

    University of Oxford

Experience

 
 
 
 
 

Research Fellow

Center on Long-Term Risk

Mar 2021 – Present London, UK
Carrying out research on the relevance of AI explainability methods to the development of safe Transformative AI systems
 
 
 
 
 

Research Assistant

University of Oxford

Sep 2019 – Jan 2021 Oxford, UK
Research in Verification and Testing of Machine Learning Systems
 
 
 
 
 

Fellow

Sesame Workshop

Jun 2018 – Sep 2018 New York, USA
Performed analysis of user data in education apps to measure effectiveness
 
 
 
 
 

Developer

Kamusi Project

Jun 2017 – Sep 2017 EPFL, Switzerland
Contributed to designing and programming multi-platform chatbot for language data collection