This startup’s new mechanistic interpretability tool lets you debug LLMs
via technologyreview.com
Short excerpt below. Read at the original source.
The San Francisco–based startup Goodfire just released a new tool, called Silico, that lets researchers and engineers peer inside an AI model and adjust its parameters—the settings that determine a model’s behavior—during training. This could give model makers more fine-grained control over how this technology is built than was once thought possible. Goodfire claims Silico […]