Summary

In this episode, we sit down with Dr. Umang Bhatt, Assistant Professor at NYU and Senior Research Associate at the Alan Turing Institute. Umang is a world-class researcher at the intersection of AI explainability and human-machine interaction.

The conversation focuses on the "how" and "why" of model transparency, exploring practical methods for explaining generative AI outputs to non-technical end-users and the importance of establishing robust feedback loops between internal stakeholders.

You can listen on Spotify or Apple Music or watch the episode here on YouTube.

Key takeaways

• Differentiating between interpretability for engineers and explainability for end-users.

• Technical approaches to restricting generative AI outputs to ensure safety.

• Closing the loop: Why compliance teams must communicate with development leads.

• Leveraging AI for personalized education while maintaining high ethical standards.

• Global perspectives: Promoting responsible AI frameworks beyond the US, EU, and China.