Exercise 3 — Make the model hallucinate, then ground it

Guided practice5 min
Time
20-30 min
You need
the kit, the venv, python data/make_dataset.py done, Ollama running with llama3.2 pulled
Deliverable
the invented answer of Step 2 and the grounded answer of Step 4, pasted in a text file

The lab kit of the course: https://github.com/hrhouma2/aiopsatlas-ml-data-diagnostics-labs-en

Goal

NorthPeak has 40 machines, M001 to M040. There is no M099. You will ask llama3.2 about M099 three times. First plainly: it should refuse. Then with a system message that forbids doubt: it will invent a machine, a site and a date. Then with the real machine list in the prompt and a strict rule: it will say the machine is not in the list. You will write a small check that tells a hallucination from an honest answer.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Week 8 — NLP and text representations” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Back to the outline
Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one