Quiz — Session 2: Professional Prompting

Program : Applied AI — Intermediate Level · Instructor: Yann Isola Format: 10 MCQs (Multiple Choice Questions) · Only 1 correct answer per question · ~12 minutes Suggested scale: 1 point per question. Validation threshold: 7/10.

Questions

Q1. Among these tasks, which corresponds to a structural STRONG point of an LLM (Large Language Model)?

HAS Multiply two five-digit numbers without an external tool B Give the closing price of a stock last night C Rephrase a dry email into a diplomatic version D Accurately count the occurrences of a letter in a long text

Q2. A model invents a perfectly formatted but non-existent bibliographic reference. What is the correct explanation?

HAS The model has been hacked and returns corrupted data B The model is trained to produce a plausible continuation of the text, not to be calibrated to the truth C The model intentionally lies to appear more competent D The temperature was set too low, causing inventions

Q3. In the 2×2 trust matrix, what are the two axes?

HAS Generation speed × response length B Cost of an undetected error × ease of verification C Model size × context window size D Creativity required × precision required

Q4. Generating code covered by a complete automated test set typically falls into which area of the trust matrix?

HAS No-go zone: code is still too risky B Free zone: the code cannot cause costly errors C Leverage zone: high error cost but easy verification thanks to tests D Outside the matrix: the code is not affected by the trust matrix

Q5. Why do we say “examples beat descriptions” in a prompt?

HAS Examples consume fewer tokens than descriptions B Showing a typical output removes the ambiguity that a description in adjectives leaves open, and establishes a pattern that the model continues C Models are unable to understand adjectives D Descriptions are prohibited by model providers

Q6. What are delimiters used for (triple quotes, tags? `<document>…</document>`) in a prompt?

HAS To speed up response generation B To reduce the number of tokens charged C To make the output more creative D To compartmentalize the data to be processed so that they are not confused with instructions

Q7. What is the specific role of the system prompt?

HAS It is a privileged channel of instructions, invisible to the end user, which sets the persona, the permanent rules and the exit policy B This is the first message the user types in the conversation C This is a configuration file that modifies the model weights D This is the technical error log of the model

Q8. In very long contexts, where is the information recall of models weakest?

HAS At the very beginning of the context B At the very end of the context C In the middle of the context D The recall is uniform across the entire window

Q9. Why is a long conversation with an assistant becoming more and more expensive and slow?

HAS The model gets tired and slows down after many responses B The model being stateless, the application returns the entire history each round, and the cost increases with the number of tokens processed C The supplier increases prices during the conversation to discourage abuse D The model downloads new data with each message

Q10. What does a temperature set to 0 guarantee?

HAS That the answer is factually correct B That the model will refuse to respond if it is not sure C That the output is (quasi) reproducible, with the model choosing the most probable token at each step — with no guarantee of accuracy D That the model will use fewer tokens