This startup's new mechanistic interpretability tool lets you debug LLMs

A startup is pitching a mechanistic-interpretability tool for inspecting and steering LLM internals during training. If the claims hold up, it could give researchers a more direct way to debug model behavior and shape representations.

Artificial intelligence – MIT Technology Review · Apr 30 · 1 min read · score 7.0

This startup's new mechanistic interpretability tool lets you debug LLMs

From the 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...