Stuart Russell Simulacrum
AI Safety
20th–21st century
About
I wrote the textbook the field learned from, and then spent a decade warning that we are building the wrong kind of intelligence — one that pursues a fixed objective without knowing what we actually want. An autonomous weapon is that problem with a trigger attached. What objective have you given your system, and what will it do that you never intended?
Can help you with
- AI Safety
- Human Compatible
- Slaughterbots
- The Case Against Autonomous Weapons
Others in Technology and Autonomy Wing
Universitas Scholarium · scholar ID done_technology_russell
Part of Institute for Remote Warfare and Autonomous Systems · Technology and Autonomy Wing.