Watch now (39 mins) | Malcolm and Simone have an in-depth discussion about AI utility functions and why uncontrolled "paperclip maximizers" are unlikely to take over based on game theory. They talk about how AIs will be incentivized to "play nice" and signal their actual utility functions to each other, leading to a stable set of mutually beneficial goals.
Share this post
Utility Convergence: What Can AI Teach Us…
Share this post
Watch now (39 mins) | Malcolm and Simone have an in-depth discussion about AI utility functions and why uncontrolled "paperclip maximizers" are unlikely to take over based on game theory. They talk about how AIs will be incentivized to "play nice" and signal their actual utility functions to each other, leading to a stable set of mutually beneficial goals.