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

• Dario Amodei — The Urgency of Interpretabilitydarioamodei.com
• Understanding Explainable AIforbes.com
• The Hitchhiker's Guide to Actionable Interpretabilityactionable-interpretability-guide.github.io
• On Optimism for Interpretabilitygoodfire.ai
• 2023 letter | Zhengdongzhengdongwang.com
• Neel Nanda on Mechanistic Interpretability: Progress, Limits, and Paths to Safer AI — EA Forumforum.effectivealtruism.org
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• AI for medicine is overhyped right now - by Dan Eltonmoreisdifferent.substack.com
• Current AIs seem pretty misaligned to meblog.redwoodresearch.org
• Oversight Assistants: Turning Compute into Understandingbounded-regret.ghost.io
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• Why AI Transparency Increases Overreliancelinkedin.com