What is Interpretability?

A surprising fact about modern large language models is that nobody really knows how they work internally. At Anthropic, the Interpretability team strives to change that — to understand these models to better plan for a future of safe AI.

Previous
Previous

AI robotics will take on human labor so humans can ‘engage their brains better,’ former Amazon exec says

Next
Next

How Generative AI is Transforming the Rollout and Performance of Amazon’s Robots