Can AI Agents Be Aligned with Human Rights? | TechPolicy.Press
... risks (this is what one would term “backward alignment”). Our research ... Human rights vs. AI risk taxonomies. In our just released paper, we ...
Read the original at Tech Policy Press ↗
- Topics
- Regulation & PolicyAI Agents & AutomationAI Safety & Existential Risk
- Tracked via
- “AI Risks”