AI safety
The practice of protecting against harm that an AI system may cause or help cause, whether by its own mistakes or by doing what a person asks when it shouldn't.
AI systems can sometimes act in a way that is harmful (e.g. deleting the wrong files, giving bad advice) even without an external party that has malicious intent. Systems need to be protected against themselves by having guardrails and safety nets to prevent unintended outcomes.
The other half
- AI security The practice of defending an AI system, and the data and tools it can reach, from attackers and deliberate misuse.
How it connects
- Red teaming tests AI safety
- AI safety defended by Guardrail
- Alignment underpins AI safety