Each dot is a unit on a drifting graph. It fires once r of its neighbours have fired at it within a short window, then rests. The slate squares are inhibitory: each of their spikes cancels half of an excitatory one. A cascade either fizzles or sweeps the graph. This is the model from my PhD work on bootstrap percolation with inhibition.
Click to ignite. Hold to widen the ignition front.
Machine learning research
Associate Professor and Head of Faculty, University of Iceland
How I turned seven arguments about AI risk into seven short animated films in Icelandic and English in about two days, with a cloned voice, a few hundred generated images, and a set of agents doing most of the production while I approved three things.
Read the post →
Media On Samstöðin's Rauða borðið, talking about whether AI development is out of control (in Icelandic).
Media Interviewed by Vísir on whether AI will destroy humanity (in Icelandic).
Paper Group presenting seven papers at LREC 2026 in Palma de Mallorca.
Gæti gervigreindin grandað okkur?
It is hard to picture how AI could actually harm us, so I made seven short films that each retell one serious argument, from an experiment in which an AI tried to blackmail an executive to a future where we lose control without noticing. I wrote the scripts. The images, music and my voice are generated with AI.