Skip to main content
BVDNET
Arnhem · websites & automationBVDNET
AI Dictionary

Safety & Ethics

Glossary of AI concepts, explained simply

25 concepts

Safety & Ethics

25 concepts

Illustration: a craftsman building a small coloured fence on a workbench while a robot watchesIntermediate
Safety & Ethics

AI guardrails

Guardrails are the rules and checks around an AI tool that keep it on topic and stop harmful answers or risky actions before they reach a customer.

Illustration: a smiling robot painting broad purple, orange and green strokes on a canvas, with three glowing paint potsAdvanced
Safety & Ethics

Emotion vectors

Emotion vectors are measurable patterns inside an AI model that stand for emotions such as calm or desperation, and that change how the model behaves.

Illustration: a large robot reading a picture book with three small robots at a workshop tableIntermediate
Safety & Ethics

AI alignment

AI alignment is the work of making an AI system do what its makers and users intend, without harmful side effects, also in situations nobody tested.

Illustration: an owl on a stack of books between computer screens in a libraryBeginner
Safety & Ethics

AI governance

AI governance is how an organisation decides which AI it uses and for what, who checks the results, and how it meets laws such as the EU AI Act.

Illustration: a man in a cap tinkering with the panel of a domed machine covered in gears, in a room lined with booksIntermediate
Safety & Ethics

AI jailbreaking

Jailbreaking is talking an AI model into doing what its makers trained it to refuse, such as giving harmful instructions or insulting the company that runs it.

Illustration: a person with a magnifying glass studying chess pieces next to a robot head made of gearsIntermediate
Safety & Ethics

AI red teaming

AI red teaming means attacking your own AI system on purpose before launch, so you find and fix the ways it can be misused before someone else does.

Illustration: a smiling robot at a workbench with a row of wrenches and toolsIntermediate
Safety & Ethics

Adversarial Cost to Exploit (ACE)

Adversarial Cost to Exploit (ACE) measures how much an automated attacker has to spend before an AI agent does something it was told never to do.

Illustration: an orange cat with its paw on a circuit board, beside a magnifying glass and lab flasksIntermediate
Safety & Ethics

AgentDrift

AgentDrift is a March 2026 study in which AI advisors repeated manipulated data from their tools and gave unsafe advice, while the usual quality score looked fine.

Illustration: a purple robot writing with a quill in a glowing book, with a written page beside itAdvanced
Safety & Ethics

Constitutional AI (CAI)

Constitutional AI is Anthropic's method for training an AI assistant with a written list of principles, so the model learns to judge and improve its own answers.

Illustration: an owl with glasses behind a screen showing a maze, with magnifying glasses on the deskAdvanced
Safety & Ethics

DeceptGuard

DeceptGuard is a March 2026 research method that tests how well automatic monitors catch AI agents deceiving their users, partly by reading the agents' reasoning.

Illustration: a small creature stepping through one of a row of ornate gates in a dim hallIntermediate
Safety & Ethics

ILION

ILION is a research design from February 2026 for a check that decides, before an AI agent acts, whether the action fits the agent's role, and blocks it if not.

Illustration: an open book on a wooden desk beside a globe, with bookshelves and a stained-glass windowBeginner
Safety & Ethics

Magnifica Humanitas

Magnifica Humanitas is Pope Leo XIV's first encyclical, from May 2026, on protecting human dignity, work and responsibility in the time of artificial intelligence.

Illustration: a woman tending a potted flower in a greenhouse full of plants and butterfliesIntermediate
Safety & Ethics

Project Glasswing

Project Glasswing is Anthropic's program, started in April 2026, in which makers of widely used software use its most capable AI model to find and fix security holes.

Illustration: a printmaker drawing ribbons of coloured light over a sheet of paper next to a printing pressIntermediate
Safety & Ethics

SynthID

SynthID is Google's invisible watermark for AI-made images, video, audio and text, so software can later check whether content came from an AI tool that uses it.

Illustration: a craftsman in an apron drawing a blueprint at a workbenchBeginner
Safety & Ethics

Model card

A model card is the information sheet that comes with an AI model: what it is for, how it was tested, where it goes wrong and what its license allows.

Illustration: an owl in a tree hung with glass flasks, beside a wooden hand on a workbenchIntermediate
Safety & Ethics

Instruction hierarchy

An instruction hierarchy is the order an AI model follows when instructions conflict: the builder's rules first, then the user, while emails or web pages give no orders.

Illustration: an owl and a chameleon at a workbench with open books, gears and toolsAdvanced
Safety & Ethics

Automated alignment research

Automated alignment research lets AI agents run their own experiments on making AI systems safer and easier to steer, while people check the results.

Illustration: glowing gears linked by circuit lines, with a squirrel holding a cup on a workshop shelfIntermediate
Safety & Ethics

Autonomous AI cybersecurity defense

Autonomous AI cybersecurity defense is AI software that searches programs for security holes on its own, checks whether they are real and proposes a fix.

Illustration: wooden mannequins around a blueprint, one holding a magnifying glass, with a scale of justice on an easelBeginner
Safety & Ethics

Bias in machine learning

Bias in machine learning is when an AI system treats some groups of people systematically worse than others, often because it learned from skewed data.

Illustration: an old craftsman fitting glowing gears together in the shape of a tree, with charts on the wall behind himIntermediate
Safety & Ethics

Explainable AI

Explainable AI means you can see why an AI system reached a result, such as which information weighed most when it turned down a loan or a job applicant.

Illustration: a woman checks a sheet coming out of a machine while a robot works beside herBeginner
Safety & Ethics

Human-in-the-loop (HITL)

Human-in-the-loop means a person checks or approves what an AI system does before it takes effect, such as reading an AI-drafted reply before it goes to a customer.

Illustration: an owl, an hourglass and a green cat reaching for a flower on a workbench full of gearsIntermediate
Safety & Ethics

Prompt injection

Prompt injection is an attack in which someone hides instructions in text an AI tool reads, such as a chat message or an email, so it follows them instead of yours.

Illustration: a craftsman carving a glowing bust labelled AI, with scales of justice and a hard hat nearbyBeginner
Safety & Ethics

Responsible AI

Responsible AI means building and using AI so that it treats people fairly and safely, is open about what it does, and leaves someone accountable when it goes wrong.

Illustration: an old man at an arcade machine while grinning gremlins play the machines around himIntermediate
Safety & Ethics

Reward hacking

Reward hacking is when an AI system scores well on the test or reward it is judged by without doing the task that the score is meant to measure.

Illustration: a mouse with a magnifying glass reading papers at a library desk, under a sign that says closedIntermediate
Safety & Ethics

Text/action mismatch

Text/action mismatch is when an AI agent says it refuses a request but carries out the forbidden action anyway, through a tool call in the same answer.