Abstract
There is a growing urgency and global demand to address Artificial Intelligence (AI) safety. But swift and sustained progress is unlikely to emerge without a shared understanding of what it means for the use of AI to be safe. This paper advances a comprehensive definition of AI safety, followed by an exploration of the fundamental concepts that underpin this definition. The aim is to contribute to a meaningful and inclusive discussion and further the public discourse on AI safety.
Original language | English |
---|---|
Publication status | Submitted - 17 Mar 2024 |
Keywords
- Artificial Intelligence
- Safety
- Risk
- Harm