to the personal website of:

Matthew Farrugia-Roberts
Research Assistant (AI Alignment and Reward Hacking)
Krueger AI Safety Lab

Nouns: Matthew, Matt, he/him, they/them (singular)—all fine.

Contact: ‘matthew’ at this domain.

Website perpetually under construction. This page includes my bio, announcements, research interests, publications, teaching, coursework, and affiliations.

About me

I am a student, researcher, and teacher from Melbourne, Australia. I’m working on understanding goal misgeneralisation with Usman Anwar at Krueger AI Safety Lab. I also collaborate on developmental interpretability research at Timaeus.

Previously, I completed a Master of Computer Science degree at the University of Melbourne, with a thesis on lossless compression of neural networks, supervised by Daniel Murfet. During the degree I completed a virtual research internship at the Center for Human-compatible AI studying reward learning theory with Adam Gleave and Joar Skalse, and I helped run a virtual AI safety reading group at metauni. I also completed an exchange semester at ETH Zürich.

Before that, I worked as a tutor and lecturer at the University of Melbourne, for classes on programming, algorithmics, artificial intelligence, theoretical computer science, networks, and operating systems. I also completed a Bachelor of Science (taking these classes and others) shortly beforehand.


Coming soon:

Recent news:

More announcements…

Research interests

Broad research interests:

So far, I’m still a student on these topics, with much to learn.

While I’m establishing myself as an academic, I have focussed on some narrower topics:

Publications by topic

Developmental interpretability:

Neural network geometry:

Reward learning theory:

Computer science education:

See also my Google Scholar profile


Teaching in 2024:

Teaching in 2023:

Teaching in 2021:

Teaching since 2016:


Master of Computer Science, University of Melbourne, part-time 2019–2022

Exchange semester, ETH Zürich, 2020

Bachelor of Science, University of Melbourne, 2014–2016


Current affiliations:

Past affiliations:

Any views expressed on this website are not intended to represent the views of any of my affiliated institutions.