Definition
Could you now explain to a friend how a chatbot writes, why it can be wrong, and how to use it well?
This review brings together the key ideas of Generative AI and Conversational Assistants: the types of generative AI, how it creates content, what a large language model is, how to prompt and follow up, how to use it for learning, hallucinations and fact-checking, spotting generated content, and questions of ownership and credit, followed by a scored quiz.
In simple words
Read the recap table, try the matching activity, then take the quiz. Each answer comes with an explanation. If you miss one, go back to that topic and read it again.
Why it matters
Generative AI is the kind of AI you are most likely to use directly, every day. The habits from this module, clear prompts, careful checking and honest credit, are what separate a skilled user from a careless one.
How it works
| Idea | In one line |
|---|---|
| Types | Text, images, audio, video and programs; multimodal tools combine them |
| How it creates | Learns patterns in training, then builds new content step by step |
| Language models | Predict the next piece of text; fluent, and not a fact-checker |
| Prompts | Role, context, task, format and limits |
| Follow-up | Improve answers through specific requests; ask for evidence, not agreement |
| Learning with AI | Try first; use it for hints, quizzes and feedback |
| Hallucinations | Confident, fluent and false; commonest with exact details and sources |
| Fact-checking | SIFT: stop, investigate, find better coverage, trace |
| Generated content | Clues are fading; check the origin |
| Thinking partner | Think with it, not through it |
| Ownership and credit | The law is unsettled; honesty is always required |
Try it yourself
Match each problem to its remedy
What should you do in each situation?
- The answer is too general
- The chatbot cites a book you cannot find
- A shocking photo arrives with no source
- You must write an essay to learn a topic
- You used AI to help with a project
Common mistakes
- Treating a chatbot as a search engine that returns checked facts.
- Believing content because it is fluent, detailed or realistic.
- Letting the tool do the thinking that you needed to do yourself.
Check yourself
Summary
- Generative AI builds new content from learned patterns and does not check for truth.
- Clear prompts and specific follow-ups get better results; verification stays your job.
- Use it to think better, give honest credit, and check before you believe or share.
Finished reading?
Sources: UNESCO: Guidance for generative AI in education and research · AI4K12: Five Big Ideas in AI