Ram Rachum

In the previous two posts (first, second) we laid out our take on AI alignment, which involves conservative philosophy and the political school of thought of Agonistic Democracy. We also suggested an approach to AI alignment in which the conflicts between multiple agents lead to an AI system that has...

In our previous post, we outlined a view of AI alignment we disagree with as a central assumption in current discussions of AI alignment, and suggested that it might be useful to push in a different direction, which we started to outline. Here, we’ll point out that we think alignment...

Current plans for AI alignment (examples) come from a narrow, implicitly filtered, and often (intellectually, politically, and socially) liberal standpoint. This makes sense, as the vast majority of the community, and hence alignment researchers, have those views. We, the authors of this post, belong to the minority of AI Alignment...

Hi everyone! My name is Ram Rachum and I'm working on AI Safety research. I want to elicit social behavior in RL agents and use it to achieve AI Safety goals such as alignment, interpretability and corrigibility. I made a guest post on the Future of Life Institute's blog: https://futureoflife.org/ai-research/can-ai-agents-learn-to-be-good/...

Hi everyone! I'm co-organizing a workshop on a really interesting topic that's very relevant for AI safety. We call it "Rebellion and Disobedience in AI". If you're doing work that could be relevant for us, please submit it! If you have questions or want to discuss the scope of this...

Hi everyone! I'm co-organizing a workshop on a really interesting topic that's very relevant for AI safety. We call it "Rebellion and Disobedience in AI". If you're doing work that could be relevant for us, please submit it! If you have questions or want to discuss the scope of this...

Hi everyone! My name is Ram Rachum, and this is my first post here :) I'm an ex-Google software engineer turned MARL researcher. I want to do MARL research that promotes AI safety. You can read more about my research here and sign up for monthly updates. I had an...