Natural Language Autoencoders

Anthropic's Natural Language Autoencoders (NLAs), a new interpretability method for large language models, use an activation verbalizer and reconstructor to convert activations into natural language a…

Anthropic's research reveals that language models can only verbally report about 10% of their internal activations, confined to a 'J-space' mental workspace. A new experiment using Natural Language Au…

On June 9, 2026, Anthropic released Claude Fable 5, the most capable AI model publicly available at the time, but access was cut off within 72 hours after U.S. government intervention. The underlying …