AI Robustness

AI Alignment

The research field focused on ensuring AI systems act in accordance with human values, intentions, and ethical principles.

AI Safety

The interdisciplinary field dedicated to making AI systems safe, robust, and beneficial while minimizing risks of unintended consequences.

AI Governance

The frameworks, policies, and regulations that guide the responsible development and deployment of AI technologies.

AI Explainability

The ability to describe AI decision-making processes in human-understandable terms, enabling trust and regulatory compliance.

AI Interpretability

The degree to which humans can understand the internal mechanics and reasoning of an AI model's predictions and decisions.

AI Fairness

The principle of ensuring AI systems make equitable decisions without discriminating against any group based on protected attributes.

AI Transparency

The practice of making AI systems' operations, data usage, and decision processes openly visible to stakeholders.

AI Hallucination

When an AI model generates plausible-sounding but factually incorrect or fabricated information with high confidence.

AI Red Teaming

The systematic adversarial testing of AI systems to identify vulnerabilities, failure modes, harmful outputs, and safety risks before deployment.

AI Watermarking

Techniques for embedding imperceptible statistical patterns in AI-generated content to enable reliable detection and provenance tracking of synthetic outputs.

AI Guardrails

Safety mechanisms and constraints implemented around AI systems to prevent harmful, biased, or policy-violating outputs while preserving useful functionality.

AI Model Card

A documentation framework that provides standardised information about an AI model's intended use, performance characteristics, limitations, and ethical considerations.

A theoretical level of AI that surpasses human cognitive abilities across all domains, including creativity and social intelligence.

AI designed to handle specific tasks without possessing self-awareness, consciousness, or true understanding of the task domain.

The simulation of human intelligence processes by computer systems, including learning, reasoning, and self-correction.

A training paradigm where AI models are refined using human preference signals, aligning model outputs with human values and quality expectations through reward modelling.

Google's custom-designed application-specific integrated circuit for accelerating machine learning workloads.

The ratio of true positive predictions to all actual positive instances, measuring completeness of positive identification.

Architectures that enable AI agents to store, retrieve, and reason over information from past interactions, providing continuity and personalisation across conversations.

Techniques for combining the weights and capabilities of multiple fine-tuned models into a single model without additional training, creating versatile multi-capability systems.