Ben Plaut

Ben is a postdoctoral research fellow at CHAI, mentored by Stuart Russell. He received his PhD from Stanford under the supervision of Ashish Goel. He does a mix of theory and empirical research, focusing on generalization: how a model handles unfamiliar inputs. Ben thinks that many safety failures can be framed as misgeneralization. Overall, he aims to design safety methods that are theoretically grounded and can potentially scale to very advanced AI systems, but which can be tested on (and are useful for) systems we have today. You can read more on Ben’s website.