Writing

Thoughts and research on AI alignment, interpretability, computational neuroscience, and other topics. These posts vary in quality, content, depth, and style. They reflect my thinking at the time of writing and do not always reflect my current views. Subscribe to my personal Substack and AISIG's Substack for more regular writing. Although I am associated with AISIG, this blog is not affiliated with AISIG and my opinions do not necessarily represent the initiative.