Interpretability, or understanding how AI models work, can help mitigate many AI risks, such as misalignment and misuse, that stem from AI systems’ opacity (Dario Amodei)

Dario Amodei:
Interpretability, or understanding how AI models work, can help mitigate many AI risks, such as misalignment and misuse, that stem from AI systems' opacity  —  In the decade that I have been working on AI, I've watched it grow from a tiny academic field to arguably the most important economic and geopolitical issue in the world.