Neel Somani explains why interpretability must evolve faster than model size

When systems lack interpretability, organizations face delays, increased oversight, and reduced trust. Engineers struggle to isolate failure modes. Legal and compliance teams lack the visibility ...
MIT Technology Review

Mechanistic interpretability

But last year we got the best sense yet of how LLMs function, as researchers at top AI companies began developing new ways to ...
Analytics Insight

Best Tools to Visualize and Understand Machine Learning Models: Top Picks

Overview: Interpretability tools make machine learning models more transparent by displaying how each feature influences ...
NetNewsLedgerOpinion

Why Researchers Are Divided on Neel Somani’s Mechanistic Interpretability Framework

In the rapidly evolving world of Large Language Models (LLMs), a quiet but critical tug-of-war is taking place over how we ...
insideHPC

Machine Learning Interpretability with Driverless AI

Data visualization techniques for representing high-degree interactions and nuanced data structures. Contemporary linear model variants that incorporate machine learning and are appropriate for use in ...
SiliconANGLE

Goodfire AI raises $7M to demystify AI systems using mechanistic interpretability techniques

Goodfire AI, a public benefit corporation and research lab that’s trying to demystify the world of generative artificial intelligence, said today it has closed on $7 million in seed funding to help it ...
TechRepublic

Anthropic CEO: “We Do Not Understand How Our Own AI Creations Work”

Anthropic CEO: “We Do Not Understand How Our Own AI Creations Work” Your email has been sent Dario Amodei predicts the “MRI for AI” will be here in five to 10 years. And, he outlines three ways to ...
Harvard Medical School

Hayley Song

Hae Jin (Hayley) Song is a Fellow at the Berkman Klein Center at Harvard University and an AI Research Fellow at ThoughtWorks, where she works on the geometric foundations of AI interpretability and ...