Level 1· Lektion 1 von 10
What AI really is
No hype, no magic. What LLMs do and what they don't.
What is an LLM?
A Large Language Model is statistics. No soul, no understanding, no consciousness. It calculates which word is most likely to come next, based on the billions of texts it was trained on.
So why does it sound so good?
Because the training data is so large that the model picks up patterns in language, logic, and facts. It imitates intelligence very well. That's impressive, but it's important to know where the line is.
What it is NOT
- It is not a search engine
- It is not "on", it has no state between questions
- It has no memory (which is why we need memory systems, see Level 4)
- It doesn't automatically know what day it is, what's happening on the internet right now, or what you talked about with it yesterday
What you'll be able to do at the end of Level 1
- Spot when AI is the right tool
- Identify typical hallucinations
- Build a prompt so the model can give a useful answer
On to Lesson 2. Spotting hallucinations.
You're reading without an account. Login saves your progress so you can pick up where you left off. Log in →