Episode 2 of 10
Why AI sounds so sure
When a model is missing the facts, it still writes a fluent, confident answer.
Check yourself
A chatbot tells a customer, calmly and firmly, that a spare part is in stock. What does that tone tell you?
A model writes fluently whether or not it has the facts. Only a source you can check tells you more.
Show text
01 · Basic
How AI really works
From 'what is a language model' to 'why our ChatGPT pilot did not stick', in ten 40-second episodes. No hype, one idea each.
0:37Ep. 1What is a language model?
0:37Ep. 2Why AI sounds so sure
0:41Ep. 3What is RAG?
0:38Ep. 4Searching by meaning
0:41Ep. 5Ask your own documents
0:38Ep. 6Chatbot or agent?
0:39Ep. 7A human at the controls
0:39Ep. 8Fine-tuning or your own documents?
0:36Ep. 9Where does your model run?
0:38Ep. 10Why the ChatGPT pilot did not stick
After this series you can:
- You recognise an answer without a source as a guess, and ask for the source.
- You choose per task whether lookup, fine-tuning or an agent fits, and where the approval sits.
- You ask a supplier pointed questions about access rights, location and oversight.