Writing

Thoughts and research on AI Alignment, interpretability, computational neuroscience, and... other stuff. These posts vary greatly in terms of quality, content, depth, and style. They reflect my thoughts at the moment of writing, and do not always reflect my current views. I hope they can be of some value. You can subscribe to my personal Substack and AISIG's Substack to get notified about new posts. All of my writing goes on those Substacks, and I will likely fail at keeping this website updated. Although I am associated with AI Safety Initiative Groningen (AISIG), this blog is not affiliated with AISIG, my opinions do not necessarily represent the initiative, and so on.