COMPLEXITY cover image

Paul Smaldino & C. Thi Nguyen on Problems with Value Metrics & Governance at Scale (EPE 06)

COMPLEXITY

NOTE

Metrics: Something That Is Measurable Across Contexts?

The difference between evaluation and a metric lies in the fact that a metric proceeds from the shared application of a measurement procedure that can be executed by different people across different contexts. For something to be considered a metric, the measurement input procedure must be exportable across context, and the criteria for the metric must be something that many people can share and understand. However, there are many standards of evaluation that don't allow for this cross-contextual universalization, posing a challenge similar to the barrier of meaning in artificial intelligence and the elusive nature of trans-contextuality in machine learning.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner