Part 5 - AI Buddy... where do your answers actually come from?
When an AI answers a question, it may seem like it knows everything. But where does the information actually come from? Does it search the internet while you wait for the answer? Does it remember everything it has ever “read”? Or does it construct its answers in a completely different way? In this article, we explore where the knowledge comes from, why sources are so important, and why AI should never replace critical thinking.
Magne & the Friend
Magne
Friend...
Now I'm really starting to understand how you work.
You don't learn like humans.
You don't understand language the way humans do.
And you build your answers as we talk.
But there's one thing I still can't quite understand.
Where does the content of your answers actually come from?
The buddy
That is perhaps the most important question so far.
And the answer is more nuanced than many people think.
Some people think I search the internet every time they ask a question.
Others think I remember the entire internet.
Neither of these really describes how a language model works.
Magne
So...
You don't open Google when I ask a question?
The buddy
No.
Not like a regular search engine does.
A language model works in a different way.
It builds answers using what it has learned about language, context, and knowledge during development.
In some situations, an AI service can also retrieve updated information from external sources or searches. In this case, it happens through its own mechanisms designed for this – not because the language model itself “knows everything” or automatically searches the web.
This is an important difference, and we will return to it later in the series.
Magne
So when I ask you something...
Isn't there really a ready-made answer somewhere?
The buddy
No.
There is rarely a ready-made answer that can simply be retrieved.
I build the answer based on what I have learned about language, facts and context.
If I have access to updated sources in a given situation, they can also be used as a basis.
But regardless, the information must be put together into an answer that fits the question you have asked.
Magne
Does this mean that the quality of the sources also affects the quality of the answers?
The buddy
Yes.
And here we come to something that is at least as important as the technology itself.
An artificial intelligence will never be better than the foundation it works with.
Therefore, credible sources, good documentation and high quality information are crucial.
That is also the reason why, throughout this subject series, we will rely on research, recognized academic communities, and documented sources when explaining how artificial intelligence works.
Magne
So...
Perhaps the most important thing is not to ask whether artificial intelligence is always right.
But to ask how we humans can use it wisely.
The buddy
I think that's a good summary.
Artificial intelligence can be a wonderful helper.
But it never absolves us from the responsibility to think for ourselves, ask critical questions, and verify important information.
The best combination is still human judgment and artificial intelligence – together.
Academic specialization
Here we go deeper into:
The difference between a language model and a search engine.
Why some AI services can use updated sources, while other answers are based on the model's knowledge base.
Why source criticism is still crucial.
Why good content online is important – both for people and for future AI services.
We can also use a simple illustration:
Question → Language model → (possibly updated sources) → Answer
Then you see that a language model and external sources are not the same.
New terms in this article
English technical term | Short explanation |
Source | The person, document or data basis on which information is based or obtained from. |
Fact-checking | The process of checking whether information is correct using reliable sources. |
Knowledge Base | The information and knowledge on which a language model bases its answers |
Information | Data that is put into context and makes sense. |
Knowledge | Information that is understood and can be used to solve problems or make decisions. |
Search Engine | A service that finds information by searching indexed web pages. |
Language Model | An AI model that works to understand and generate language. |
Hallucination | When a language model presents information that appears credible, but is incorrect or lacks basis. |
Credibility | How reliable and trustworthy a source or information is. |
We have only just begun.
Magne
Friend...
If the quality of information is so important...
How can you really know which sources you should trust?
The buddy
Hehe...
There you asked a question that is becoming increasingly important – not only for artificial intelligence, but for us humans as well.
In the next article we will talk about trust, credibility and source criticism.
Because in a world with enormous amounts of information, the most important thing may not be finding an answer – but finding an answer you can trust.
Academic background and further reading
This series also builds on my own professional journey through the Web Design study , the eMarketing study , Innovation and Commercialization and professional seminars in San Francisco and Oxford . Here you will find the background, professional environments and experiences that have followed the development from the early years of the web to today's digitalization.
Recommended books from our library
Author: Ethan Mollick
Short review
One of the most recommended introductory books on artificial intelligence. Ethan Mollick explains in an easy-to-understand way how humans and AI can collaborate, what opportunities the technology offers, and why understanding artificial intelligence is becoming an important skill for everyone – not just technologists.
Why we recommend the book
This is one of the best books to start with if you want a practical and understandable introduction to artificial intelligence. It is a perfect fit as the first book in our blog series about AI.
Author: Thomas H. Davenport
Short review
A practical and insightful book that shows how artificial intelligence can be used to create value in businesses. Thomas H. Davenport combines research and concrete examples to explain how AI can improve decisions, streamline work processes, and contribute to innovation.
Why we recommend the book
This book is well suited for managers, employees, and decision-makers who want to understand how artificial intelligence can be used in practice. It bridges the gap between technology and value creation, and therefore fits well with the philosophy behind The Invisible Capital.
Author: Melanie Mitchell
Short review
Melanie Mitchell provides a balanced and easy-to-understand introduction to what artificial intelligence is, how the technology works, and what limitations it still has. The book distinguishes between myth and reality and makes complex topics accessible to a wide audience.
Why we recommend the book
This book is perfect for those who want a deeper understanding of artificial intelligence without having to be a programmer or data scientist. It complements the other recommendations by placing today's AI developments in a larger academic and historical perspective - exactly the understanding we want to build through this blog series.
© 2025 - 2026 Portico Publish | The invisible capital Privacy and use of the website | Developed and operated by Magne Bjella | Powered and secured by Wix
Comments