The alignment problem from a deep learning perspective by Richard Ngo Et Al
Listen now (47 min) | Within the coming decades, artificial general intelligence (AGI) may surpass human capabilities at a wide range of important tasks. We outline a case for expecting that, without substantial effort to prevent it, AGIs could learn to pursue goals which are very undesirable (in other words, misaligned) from a human perspective. We argue that AGIs trained i…
8 months ago · whitehatStoic