Article may be outdated

This article is 8 days old. Some details may have changed since publication.

MIT Technology Review·5 min read·hard

Anthropic found a hidden space where Claude puzzles over concepts

W
Will Douglas Heaven
Anthropic found a hidden space where Claude puzzles over concepts
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.

Continue reading on Headlinne

Create a free account to read the full article.

Read full article →
technologyscience

Get the full story

Sign up for Headlinne to unlock AI insights, political bias analysis, and your personalized news feed.

Create free account

Already have an account? Sign in