Free to follow every thread. No paywall, no dead ends.
AI safety: stories to listen to | HearLore
Category
AI safety
AI alignmentIn 1960, the pioneering cyberneticist Norbert Wiener issued a warning that would echo through the next six decades of artificial intelligence development.
AI safetyIn 2013, researchers discovered that adding specific, imperceptible noise to an image could cause a machine learning model to misclassify it with high…