Lauro Langosco

See here for what I’m currently working on.

I’m a PhD student with David Krueger in the Computational and Biological Learning lab at Cambridge. My main research interest is AI alignment: the problem of building intelligent systems that do what we want them to even when they are smarter than us. In particular, I am interested in

• Demonstrations of alignment failures (for example).
• Figuring out how to scale interpretability methods to large models.
• Better understanding ML systems (“science of deep learning”) in ways that help with alignment schemes.

Previously, I interned at the Center for Human-Compatible AI in Berkeley and studied mathematics at ETH Zurich. I also helped run Effective Altruism Zurich for four years and co-organized a reading group on AI alignment.

In the long term, I hope this site can be a place where I write about the things I’m working on, with less of a filter than a preprint would have. I’ll probably also write about non-research stuff.

I’m usually happy to hop on a call to chat about research. You can contact me at langosco.lauro@gmail.com.