Safety, Ethics & Future
What Is Explainable AI (XAI)?
Explainable AI (XAI) is the effort to make AI systems’ decisions understandable to people. Because many models act as “black boxes,” explainability techniques try to show which inputs drove a result and why. This matters most in high-stakes settings — medicine, lending, law — where decisions must be justified and audited.
Go deeper: Harms and Risks
Further reading
Read more about Explainable AI — articles and blogs from around the web: