Introduction

#1.1Who is this book for?

This book is a general introduction to artificial intelligence (AI) and generative AI (genAI). It was developed because AI is currently an almost unavoidable part of your academic journey and future career, and because it has a major impact on society.

This book is especially suitable for students in disciplines without a specialization in AI. It offers an overview of the most important concepts related to AI and its impact on you, your studies, your future profession, and society. With this companion, you will work toward the following three goals:

Gain the knowledge and skills to use generative AI responsibly during your studies, or to decide not to use it.

Prepare yourself for a professional life in which AI literacy is becoming just as important as computer skills are today.

Develop a critical and ethical perspective on AI so that you are not just a user, but also a conscious citizen who thinks about AI’s impact on our society.

This companion is not intended to study or develop scientific theories about AI, nor to cover all the technical, mathematical, and statistical knowledge about AI. Those specializations belong in discipline-specific education in fields such as Computer Science, Artificial Intelligence, Sociology, Psychology, Philosophy, or Environmental Science. What you need instead? Curiosity and a willingness to think critically about the role of AI.

#1.2What is AI?

When you think of AI, you might imagine smart robots, self-driving cars, or science fiction movies. But AI is a much more everyday phenomena, and much closer to you than that. The recommendations Netflix gives you, the spam filter in your e-mail inbox, the route planning in Google Maps—these are all examples of traditional AI. These systems analyze data, recognize patterns, and make decisions or predictions based on that (LeCun et al., 2015).

Artificial intelligence refers to technologies that can perform tasks that normally require human intelligence, such as reasoning, learning, planning, and understanding language (Russell & Norvig, 2016). Within AI, there are different subfields such as machine learning, natural language processing (NLP), and computer vision. Generative AI is a relatively new variation and has received the most attention in recent years. Since the arrival of ChatGPT in November 2022, AI has often been equated with generative AI. You'll discover why that is not accurate below.

#1.3What is generative AI?

Unlike traditional AI, which mainly recognizes and classifies, generative AI can create new content. Think of text, images, audio, or even video. You are probably familiar with ChatGPT, DALL·E, and Copilot; these are well-known examples of generative AI tools. These systems rely on enormous amounts of existing data to generate something new that seems coherent and convincing—as if it were made by a human (Goodfellow et al., 2014).

Generative AI often works with so-called transformer models such as GPT (see Box 1.1). These models predict which word is most likely to come next after the previous one, based on previously learned patterns. Just as a baby learns to speak by listening to the language around it, language models such as GPT learn to write by ‘reading’ enormous amounts of text and learning from it (Brown et al., 2020). You can read more about this in chapters 5 and 6.

#1.4How does generative AI work?

When you ask ChatGPT or another generative AI a question, it can sometimes feel like you are talking to a smart conversation partner. But actually, it is a statistical calculator—a language model—that tries to predict the most likely and desirable next word. The training of these models happens in multiple phases. First, the model is fed billions of sentences from the internet (pre-training). Then human trainers teach the model what desirable behavior is, such as being polite or not giving unethical advice, through what is known as Reinforcement Learning with Human Feedback (RLHF) (Christiano et al., 2017). You can read more about this in chapter 5.

#1.5What is AI literacy?

AI literacy means understanding how AI works, when you can use it responsibly, and when you should not do so. It's not just about technical knowledge, but above all about taking a critical approach to AI and developing ethical awareness. It is a combination of critical thinking, technical understanding, ethical awareness, and adaptive learning ability. In this companion, we choose to see AI literacy as a combination of understanding, evaluating, applying, and reflecting (Streppel et al., 2024). You don't need to be a programmer, but it is important that you can: assess what AI does, what ethical and legal issues are involved, and how it affects you and society, such as its impact on the environment and polarization.

In addition, AI literacy can also be divided into learning about AI, learning with AI, and learning through AI:

• Learning about AI is about building basic knowledge on this subject and learning how to apply AI technology.
• Learning with AI is about using AI to support your learning process as a study buddy or coach.
• Learning through AI is about developing skills with and through specific AI tools.

AI literacy is part of, or a further development of, the broader concept of digital literacy. Today, the two are often mentioned in the same breath, but digital literacy has different definitions. For example, according to SLO (the national expertise center for the curriculum) (SLO, 2024): “acquiring knowledge about digital technology, being able to work with it, using its possibilities critically and with self-awareness, and being able to assess its opportunities and risks.” In doing so, SLO distinguishes four subdomains of digital literacy: practical ICT skills, media literacy, digital information skills, and computational thinking. AI literacy runs through several of these domains and has not yet been given a fixed place. SLO has now published the final core concept goals for digital literacy in primary and secondary education, allowing future students to build on that foundation.

Another breakdown that is often used is that of the DigiComp model (European Commission, 2025). In it, the competencies are divided into information and data literacy, communication and collaboration, digital content creation, safety, and problem solving. See Table 1.1 for more details and examples from academic practice that you can use yourself. Throughout the book, you will discover many more examples in which AI plays a role.

#1.6Why is AI literacy important for you as a student?

AI is not some distant issue. In the classroom, in your future profession, and in your social life, AI is playing an increasingly large role. At VU Amsterdam, we believe that AI literacy is a core competency, comparable to critical thinking, academic writing, or being able to conduct research and literature reviews (VU Amsterdam, 2025). But AI literacy also means being aware of its social and environmental impact, an aspect that is often missing from general descriptions of AI competencies.

It stands to reason that AI skills are something increasingly in demand on the job market. For example, generative AI can support you in summarizing text, structuring essays, analyzing sources, or serving as a study coach—provided you know how to use it carefully. As a result, students who learn to use AI effectively may gain an advantage. That is why it is important to learn how AI works and how to use it responsibly and effectively. In addition, AI literacy is becoming an increasingly important part of citizenship: helping you make well-considered choices in life, in your studies, and in your work.

At the same time, technology—and AI in particular—is not neutral. Every choice made in the design, training, and use of an AI system reflects the values, priorities, and blind spots of the people who created it. For example, language models such as ChatGPT have largely been trained on English-language Western texts, which means other languages, cultures, and perspectives are systematically underrepresented in its outputs (Bender et al., 2021). Or think of an AI system that evaluates job applicants but is trained on historical data already saturated with existing inequalities. Moreover, AI also has a very large ecological footprint: the data centers that run AI models consume enormous amounts of energy and water, largely dependent on fossil fuels (Vries-Gao, 2025a). By using AI, you also take part in the production chain that stretches from lithium mines to water shortages and climate change. As a student and future professional, it is therefore essential to learn how to use AI and how to question it: who made this system, based on whose data, and at what cost?

#1.7How and when to use generative AI responsibly?

Brainstorming, rephrasing, searching for information, summarizing, or adding structure to your work—generative AI can be incredibly useful. But it is also risky if you use it uncritically. AI is not neutral: it makes mistakes, can quietly introduce bias into your work, or can even be misleading.

#1.8What do the opportunities and risks of AI mean for your future?

Generative AI offers opportunities: from helping with creativity and supporting more efficient or productive methods to enabling new forms of learning and research. At the same time, there are risks: deskilling, disinformation, copyright violations, Big Tech dependence, market concentration, political influence, privacy issues, and environmental problems. If you want to use AI well, you have to learn how to deal with that ambiguity. This applies to different areas of your life, such as your studies, your future work, and your role as a citizen. As a student, this means being able to work critically with AI in your studies and research, in writing texts, or in preparing for exams. As a future professional, you will encounter AI in your field, whether you become a lawyer, psychologist, biologist, or economist. It shapes how you gather, analyze, and communicate information. And as a citizen, you are part of a society in which AI influences decisions about politics, education, healthcare, work, and the justice system. Think of automated hiring systems, AI-generated news reports, or predictive policing models. But AI also brings problems related to copyright, working conditions, social developments, and the environment. You need to position yourself in relation to these issues. In chapter 10 we go into this in more depth.

#1.9How should you use this companion?

This companion guides through the world of generative AI you step by step and is structured as a learning pathway. Each chapter covers a specific aspect that you need to use AI effectively, creatively, and critically in your studies. You begin with the basics about what AI is and what you can generally do with it (chapter 2). In this edition of the Companion, a new chapter 3 has been added that describes the risks and opportunities for your learning process. This was needed because it is becoming increasingly clear that generative AI can quickly undermine learning. Subsequently, you will learn how to use AI practically by prompting well (chapter 4) and you will learn, at a deeper level, what is technically happening under the hood (chapter 5 and 6). In a separate chapter, you will learn about AI’s environmental impact (chapter 7). In chapters 8 and 9 you zoom out to the broader impact of AI on work, society, and power. In the final chapter, you will once again reflect consciously on how you want to engage with AI (chapter 10). Each chapter contains theory, background information, examples, deeper-dive boxes, self-study and check questions, and concrete applications—so that you do not just read about AI, but experience it for yourself as well.

#1.10How do you use the Canvas course

This book is also linked to a Canvas course and an Information Literacy e-learning module from the UBVU. Depending on how instructors use this book or the e-learning module in one or more courses in your program, you will be able to study the chapters of this book there. Each chapter of the Canvas course includes a small chatbot at the beginning so you can discuss the chapter’s content with it. At the end of each chapter, it also includes a number of application and reflection questions to deepen your knowledge. Finally, the course includes several discussion boards. If you log in with your VUnetID, we invite you to share your knowledge with your fellow students and discuss your use of and views on generative AI for learning and your professional practice with one another.

• Go to the Canvas course for this book
• Want to participate in the assignments? Then enroll in the course (VU students)
• Go to the UBVU Information Literacy e-learning module