Writing

Thoughts and research on AI Alignment, interpretability, and computational neuroscience. 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 Substack to get notified about new posts. 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.