Project Details
Description
We aim to create AI that excels in safe and ethical judgment. This initiative prioritises an intricate reward system for AI, ensuring factual accuracy while aligning outputs with human values, thereby boosting trust in AI systems.
| Status | Active |
|---|---|
| Effective start/end date | 1/09/24 → 30/09/25 |
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.