『21 - Unpacking the Alignment Problem in AI: Navigating Morality, Politics, and Market Structures』のカバーアート

21 - Unpacking the Alignment Problem in AI: Navigating Morality, Politics, and Market Structures

21 - Unpacking the Alignment Problem in AI: Navigating Morality, Politics, and Market Structures

無料で聴く

ポッドキャストの詳細を見る

このコンテンツについて

Join Noah and Marty as they delve deep into the immense conceptual and computational difficulties involved in ensuring advanced AI remains aligned with human ethics and values over the long-term. We discuss using "negotiation games" to help align AI systems' goals with human values and interests over time. The idea is to incentivize AI systems to make accurate long-term forecasts that benefit humanity.

Also we touch on paradoxes and intractable complications that plague the approaches and thinking at the foundations of current deployment of AI systems.

まだレビューはありません