Isaac Kauvar is a researcher on the Interpretability team at Anthropic who builds and applies tools to understand links between neural activity and behavior in AI systems.
How media typically covers Isaac Kauvar
Isaac Kauvar as author
Anthropic researchers discovered that language models develop cross-modal visual features that recognize semantic concepts like eyes and faces consistently across ASCII art, SVG code, and text across multiple languages.
“Co-author of the research article on visual features across modalities”