Measuring AI Progress
Ken discusses the complexities of AI performance measurements, particularly in tasks like speech recognition and part of speech tagging. He emphasizes the challenges in distinguishing between machine errors and subjective human interpretations, highlighting a critical gap in how we assess AI's capabilities compared to human performance. The conversation reveals the nuanced landscape of AI advancements and the importance of accurate measurement in evaluating progress.In this clip
From this podcast
Eye on AI
Episode 15 - Ken Church
Related Questions