Rick W / Thursday, April 30, 2026 / Categories: Artificial Intelligence This startup’s new mechanistic interpretability tool lets you debug LLMs 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… Previous Article Mastering Agentic AI: Governance, Trust, and Enterprise Success with Barndoor AI CEO and Founder Oren Michaels Next Article Making the case for curiosity-driven science Print 5 Tags: ModeModelAI