Software vendors are pushing explainable A.I., but those explanations may be meaningless | Fortune

Researchers sound alarm over explanations used to engender trust in A.I.

A.I. has an explainability crisis. But it’s not the one you probably think. For a long time, the problem seemed to be that A.I. algorithms, especially cutting-edge deep learning methods, were black boxes. It was impossible to explain exactly why the software made a prediction in a particular case. This lack of interpretability has made businesses think twice about using A.I., especially in critical areas such as healthcare, finance, and government. This is the A.I. explainability crisis you may have heard of . To overcome this impediment, though, in the past few years, companies selling A.I. s

related reading

• Understanding Explainable AIforbes.com
• The Artificiality of Alignmentjoinreboot.org
• AI for medicine is overhyped right now - by Dan Eltonmoreisdifferent.substack.com
• You Can’t Trust the AI Hypepalladiummag.com
• Assessing skeptical views of interpretability research | Christopher Pottsweb.stanford.edu
• Is AI Reasoning Right for the Wrong Reasons? | Quanta Magazinequantamagazine.org
• On Optimism for Interpretabilitygoodfire.ai
• In (highly contingent!) defense of interpretability-in-the-loop ML training — AI Alignment Forumalignmentforum.org
• AI experts are increasingly afraid of what they’re creatingvox.com
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• Who will explain the machines of loving grace?substack.com
• AI Safety Seems Hard to Measurecold-takes.com