About this episode

The episode explores the internal structures of neural networks and their implications for AI interpretability and safety.

What if neural networks are less like mysterious black boxes and more like systems we can inspect, debug, and eventually design with intention? In this episode of The Neuron: AI Explained , Corey Noles and Grant Harvey talk with Eric Ho, Cofounder & CEO of Goodfire , an AI interpretability company working to understand what’s happening inside neural networks. Eric explains why models may contain meaningful internal structures — including features, representations, circuits, and curved manifolds — and how mapping those structures could make AI systems safer, more reliable, and more useful. They discuss why models may “think in shapes,” how Goodfire uses AI to interpret other AI systems, what neural geometry can reveal about hallucinations and model behavior, and why interpretability could change how companies train and control their own models. They also get into consciousness, robotics, multimodal models, the bitter lesson, and why Eric thinks more people should be looking under the hood of the most consequential technology of our time. Subscribe to The Neuron for more grounded conversations about how AI actually works: https://www.theneuron.ai/ Sponsored by SAS AI…

People in this episode

Hosts: Corey Noles, Grant Harvey

Guest: Eric Ho

Topics covered

• AI interpretability
• neural networks
• model behavior
• AI safety
• consciousness
• robotics
• multimodal models

Keywords

• neural networks
• AI interpretability
• model behavior
• AI safety
• consciousness
• robotics
• multimodal models
• Goodfire
• Eric Ho

Sponsors

SAS AI Governance

Mentioned in this episode

Organizations: Goodfire

More episodes of The Neuron: AI Explained

• BONUS: AI Agents Are Here. Now What? · July 17, 2026 · 2h 58m
• AI That Rides Along With Truck Drivers · July 13, 2026 · 42 min
• BONUS: GPT-5.6 Sol Goes Live: Must-Try Use Cases We’re Testing Live · July 10, 2026 · 2h 14m
• ComfyUI Proves AI Art Is Not Zero Effort · July 8, 2026 · 58 min
• BONUS: Government Banning AI Fallout: China, the economy, what's at risk, and what you should do. · July 3, 2026 · 1h 24m
• Can AI Agents Learn From Expert Corrections? · July 1, 2026 · 53 min

Explore listener stats, chart rankings, contacts and more on the The Neuron: AI Explained podcast page.