The Survival of Humanity Depends on Which Theory of Mind is Correct| treeofwoe.substack.com
And in that future, most of the creative class is already obsolescent.| treeofwoe.substack.com
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms| www.anthropic.com
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.| Transformer Circuits