j-lens

Tag

Cards List
#j-lens

@rohanpaul_ai: Today’s edition of my newsletter just went out. https://rohan-paul.com/p/anthropics-new-j-lens-uncovers-a… Anthropic’s …

X AI KOLs Timeline · yesterday Cached

Anthropic's new J-lens reveals a hidden workspace inside Claude aligning with consciousness theory; other news include Tencent's Hy3 model, NVIDIA's compute-for-equity program, Microsoft layoffs, and Claude Fable 5 extension.

0 favorites 0 likes
#j-lens

@rohanpaul_ai: Another massive research from Anthropic. New “J-lens” uncovers Claude’s quiet workspace, matching a major consciousness…

X AI KOLs Timeline · 2d ago Cached

Anthropic's new research introduces 'J-lens,' a method to read Claude's internal activations before output, revealing a quiet workspace functionally similar to human global workspace theory. This allows detection of hidden reasoning, goals, and potential safety issues like prompt injections.

0 favorites 0 likes
#j-lens

@hillbig: Large language models are thought to not only predict the next token but also internally maintain intermediate concepts…

X AI KOLs Timeline · 2d ago Cached

This paper introduces the Jacobian Lens (J-lens) and J-space to show that LLMs like Claude Sonnet 4.5 maintain verbalizable internal representations that function like a global workspace, causally used for flexible reasoning—demonstrated through intervention experiments.

0 favorites 0 likes
← Back to home

Submit Feedback