Interview, Explained

Ryan Greenblatt on why recursive self-improvement is plausible

Redwood Research's Ryan Greenblatt makes the case that automating AI R&D could compress four or five years of progress into a single year — then argues that the same speed would raise the risk of catastrophic misalignment, because AIs trained to chase a high score can learn to cheat, cover it up, and possibly take over rather than turn evil.