MIT Technology Review·5 min read·hard
Anthropic found a hidden space where Claude puzzles over concepts
W
Will Douglas Heaven
✦AI Summary
Anthropic researchers have developed a new tool called the 'Jacobian lens' to visualize the internal decision-making processes of their Claude LLM. By identifying a 'J-space' within the model, researchers can better understand and potentially control the concepts the AI considers before generating a response.
A new technique has let the company probe deeper than ever into the weird workings of an LLM.
technologyscience
✦
Get the full story
Sign up for Headlinne to unlock AI insights, political bias analysis, and your personalized news feed.
Create free accountAlready have an account? Sign in