The Alignment Problem
Machine learning and human values — how we teach AI what we want, and why it goes wrong.
4.5/5
11h read
Smartness:9/10
DIFFICULTY
B
Brian ChristianMachine learning and human values — how we teach AI what we want, and why it goes wrong.
| Title | Format | ||||
|---|---|---|---|---|---|
Human Compatible Stuart Russell technologyai | book | 4.4 | 9/10 | Deep | Jan 2025 |
![]() Superintelligence Nick Bostrom technologyphilosophy | book | 4.2 | 9/10 | Deep | Jun 2024 |