Best AI News — Updated Every 3 Hours
Story Page
← All Stories
Home Policy & Culture Story
Policy & Culture

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

Via MIT Tech Review AI
Thursday, Apr 30, 2026 · 3:59PM
Summary

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

Continue reading the full article
Read at MIT Tech Review AI
www.technologyreview.com
Back to all stories