Why Accuracy Isn't Enough: A New Quality Model for Real-World ML Components

Name: Radio and Podcast
Availability: InStock

Software Engineering Institute (SEI) Podcast Series by Carnegie Mellon University Software Engineering Institute

Sep 17, 202624:02Technology

AI components, whether traditional machine learning or generative AI, are embedded in many present-day systems. However, despite advances in automation, infrastructure, and tooling for developing AI components, many do n...

Related Episodes

Continue listening to more episodes from Software Engineering Institute (SEI) Podcast Series.

Breaking Down Barriers: How LLMs Enable Software Analysis in Classified Environments

Aug 6, 2026 - 21:58

The recent explosion in large language model (LLM) technology has highlighted the challenges of using pub...

Data-Driven Defense: Cyber Resilience in the Age of AI

Jul 31, 2026 - 16:54

Data breaches remind us of the importance of cyber resilience as an essential element of survivability an...

Software-Defined Warfare: Expanding the Frontier

Jul 8, 2026 - 12:43

Software-defined warfare is today's reality for national security, shifting the emphasis in military oper...

From Coordination Chaos to Mission Focus: The Waypoints Framework

Jun 24, 2026 - 18:38

In aviation, waypoints guide pilots through complex flight plans, providing some structure but maintainin...

An LLM Evaluation Framework for High-Stakes AI

Jun 11, 2026 - 16:33

Experimentation and validation of LLM performance is critical when building LLM-driven systems that must...

Protecting AI Systems Against Data Poisoning

Jun 4, 2026 - 20:01

Data poisoning—where adversaries tamper with training data to corrupt model behavior—poses significant ri...

Goal-Line Defense: A Tool to Discover and Mitigate UEFI Vulnerabilities

Apr 15, 2026 - 41:19

As recently as December 2025, the Carnegie Mellon University Software Engineering Institute (SEI's) CERT...

Leadership, Legacy, and the Power of Mentors: Insights from Dr. Paul Nielsen

Apr 6, 2026 - 18:58

In February 2026, Paul Nielsen announced that he will transition out of his role as director and chief ex...