Leon Lang

Nov 16, 2024 | lesswrong.com | Seth Herd |Thane Ruthenis |Leon Lang |Thomas Kehrenberg

As part of the court case between Elon Musk and Sam Altman, a substantial number of emails between Elon, Sam Altman, Ilya Sutskever, and Greg Brockman have been released. I have found reading through these really valuable, and I haven't found an online source that compiles all of them in an easy to read format. So I made one. I used some AI assistance to generate this originally, and then went meticulously through each email and checked them for differences.

Oct 22, 2024 | lesswrong.com | Leon Lang

This is a post on our recent paper “When Your AIs Deceive You: Challenges with Partial Observability in Reinforcement Learning from Human Feedback”, done with my great co-authors Davis Foote, Stuart Russell, Anca Dragan, Erik Jenner, and Scott Emmons. It has recently been accepted to NeurIPS (though with the camera-ready version not yet available).

Jul 16, 2023 | lesswrong.com | Leon Lang

This post is an attempt to make an argument more explicit that sometimes seems to be implied (or stated without deeper explanation) in AI safety discussions, but that I haven’t seen spelled out that directly or in this particular form. This post contains nothing fundamentally new, but a slightly different – and I hope more intuitive – perspective on reasoning that has been heard elsewhere. Particularly I attempt to make the argument more tangible with a visualization.

Apr 20, 2023 | lesswrong.com | Daniel Kokotajlo |Christopher King |Leon Lang |Shoshannah Tekofsky

Summary: Collective Human Intelligence (CHI) represents both the current height of general intelligence and a model of alignment among intelligent agents. However, CHI's efficiency and inner workings remain underexplored. This research agenda proposes six experimental directions to enhance and understand CHI, in pursuit of potential runway for alignment solutions and a possible paradigm shift similar to neural networks in early AI.