Anthropic can now track the bizarre inner workings of a larg...

Anthropic can now track the bizarre inner workings of a large language model

Will Douglas Heaven technologyreview.com

RelatedInsightsCollectionsHighlights

Tracing the Thoughts of a Large Language Model

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms. https://t.co/PboGlLFnHG

Anthropic x.com

On the Biology of a Large Language Model

transformer-circuits.pub

Large language models, explained with a minimum of math and jargon

Timothy B Lee understandingai.org

12ft | ChatGPT Is a Blurry JPEG of the Web | the New Yorker

The NewYorker 12ft.io