deepmindsafetyresearch.medium.com 的前十大競爭對手

adamkarvonen.github.io

Sparse Autoencoders (SAEs) have recently become popular for interpretability of machine learning models (although sparse dictionary learning has been around since 1997). Machine learning models and LLMs are becoming more powerful and useful, but they are still black boxes, and we don’t understand how they do the things that they are capable of. It seems like it would be useful if we could understand how they work.

alignmentforum.org

A community blog devoted to technical AI alignment research

bluedot.org

Contributing to AI Governance

effectivealtruism.org

Frequently asked questions about effective altruism, and responses to common objections.

lesswrong.com

A community blog devoted to refining the art of rationality

transformer-circuits.pub

We investigate the internal mechanisms used by Claude 3.5 Haiku — Anthropic's lightweight production model — in a variety of contexts, using our circuit tracing methodology.