Jan Leike@janleikeI'm excited to join @AnthropicAI to continue the superalignment mission! My new team will work on scalable oversight, weak-to-strong generalization, and automated alignment research. If you're interested in joining, my dms are open.Opens with an announcement
Jan Leike@janleikeI joined because I thought OpenAI would be the best place in the world to do this research. However, I have been disagreeing with OpenAI leadership about the company's core priorities for quite some time, until we finally reached a breaking point.Opens with an observation
Jan Leike@janleikeI like the new Sonnet. I'm frequently asking it to explain ML papers to me. Doesn't always get everything right, but probably better than my skim reading, and way faster. Automated alignment research is getting closer...Opens with an observation
Jan Leike@janleikeNew research result: we use Claude to make fully autonomous progress on scalable oversight research, as measured by performance gap recovered (PGR). Claude iterates on a number of different techniques and ends up significantly outperforming human researchers for $18k in credits.Opens with an observation
Jan Leike@janleikeI love my team. I'm so grateful for the many amazing people I got to work with, both inside and outside of the superalignment team. OpenAI has so much exceptionally smart, kind, and effective talent.Opens with an observation
Jan Leike@janleikeNew alignment paper with one of the most interesting generalization findings I've seen so far: If your model learns to hack on coding tasks, this can lead to broad misalignment.Opens with an observation