Been Kim Is Building a Translator for Artificial Intelligence | Quanta Magazine
▻https://www.quantamagazine.org/been-kim-is-building-a-translator-for-artificial-intelligence-201901
We know from repeated studies in cognitive science and psychology that humans are very gullible. What that means is that it’s actually pretty easy to fool a person into trusting something. The goal of interpretability for machine learning is the opposite of this. It is to tell you if a system is not safe to use. It’s about revealing the truth. So “trust” isn’t the right word.
#AI #recherche ; j’ai eu la chance d’assister à un exposé de Been Kim à Berlin l’automne dernier — elle est suuuuuuper forte.