New research from @AISecurityInst and Goodfire

As a field, AI moves forward on the basis of doing ever larger experiments that utilize more and more inputs (e.g, data and compute). Every so often, humans come up with some paradigm-shifting idea which can make it dramatically more resource efficient to do things – a good example here is the transformer architecture and another is the idea of mixture-of-expert models.

These skills act as an orchestration layer that helps scientists work through broad, ambiguous, and multi-step questions more effectively.

Progress in the life sciences is constrained not only by the difficulty of the underlying science, but by the complexity of the research workflows themselves.

Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-relevant behavior.

Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-relevant behavior.