What is AI Safety?

The work of making AI systems behave according to human intentions, values, and safety constraints.

The broad field of building systems that perform tasks requiring pattern recognition, reasoning, language, or decision-making.

Stress-testing an AI system with adversarial prompts to reveal failures and risks.

The European Union's risk-based regulatory framework for AI systems and providers.

The extra cost in time, compute, or product velocity required to make systems safer and more controllable.

A consistent pattern of error or unfairness in data or model behavior.