Humanity is on the brink of inventing Artificial General Intelligence, an achievement that could bring about utopia or utter annihilation. Experts call AGI "humanity's final creation" because it will either usher in a new era of peace and prosperity or it will destroy us entirely. The clock is ticking until AGI is invented, and we must be prepared.
The Control Problem is the question of how do we leash an ultra-powerful AGI? How do we prevent AGI from taking over the world and killing us all?
The optimal solution is not an AGI that we can control, but an AGI that doesn't need to be controlled. In his ongoing research, David Shapiro proposes a solution to the control problem called the Core Objective Functions, a set of heuristic imperatives that will guarantee that an AGI will remain benevolent indefinitely. Those Core Objective Functions are: Reduce suffering, increase prosperity, and increase understanding.
In this book, David reveals his exhaustive research into these functions, how to implement them, and how we can expect AGI to behave when it abides by the Core Objective Functions. Most importantly, this book details how and why an AGI will remain benevolent for all eternity with these Core Objective Functions.
Humanity is on the brink of inventing Artificial General Intelligence, an achievement that could bring about utopia or utter annihilation. Experts call AGI "humanity's final creation" because it will either usher in a new era of peace and prosperity or it will destroy us entirely. The clock is ticking until AGI is invented, and we must be prepared.
The Control Problem is the question of how do we leash an ultra-powerful AGI? How do we prevent AGI from taking over the world and killing us all?
The optimal solution is not an AGI that we can control, but an AGI that doesn't need to be controlled. In his ongoing research, David Shapiro proposes a solution to the control problem called the Core Objective Functions, a set of heuristic imperatives that will guarantee that an AGI will remain benevolent indefinitely. Those Core Objective Functions are: Reduce suffering, increase prosperity, and increase understanding.
In this book, David reveals his exhaustive research into these functions, how to implement them, and how we can expect AGI to behave when it abides by the Core Objective Functions. Most importantly, this book details how and why an AGI will remain benevolent for all eternity with these Core Objective Functions.
Benevolent by Design: Six words to safeguard humanity
170
Benevolent by Design: Six words to safeguard humanity
170
Product Details
| ISBN-13: | 9798765534694 |
|---|---|
| Publisher: | Barnes & Noble Press |
| Publication date: | 02/26/2022 |
| Pages: | 170 |
| Product dimensions: | 6.00(w) x 9.00(h) x 0.36(d) |