Quiz collegato alla guida · Medio Livello
Quiz sull'ingegneria del contesto
Verifica in che modo l'ingegneria del contesto differisce dal prompt, perché il contesto è un budget simbolico e tecniche come il caricamento just-in-time e la memorizzazione nella cache dei prompt.
Domanda 1 di 8
Cosa distingue meglio l’ingegneria del contesto dall’ingegneria immediata?
Anteprima di ogni domanda8 domande
Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.
- Cosa distingue meglio l’ingegneria del contesto dall’ingegneria immediata?
- It only concerns the wording of the user's question
- It covers everything the model sees, including retrieved data, tool results and memory, not just the wording
- It requires fine-tuning the model's weights
- It applies only to image-generation models
- Cosa ha suggerito la ricerca "perso nel mezzo" sugli input lunghi?
- Models read every part of a long input equally well
- Models ignore the beginning of their input
- Models often use information at the start and end of a long input better than information in the middle
- Models cannot process more than about 1,000 tokens
- Perché la guida descrive il contesto come un budget?
- Every token costs money and latency, and irrelevant material can distract the model
- Providers charge a flat monthly fee for context
- Models refuse inputs above a certain dollar amount
- The word refers only to the compute used in training
- Cos'è il caricamento just-in-time?
- Loading the entire codebase into the window at the start of a session
- Retraining the model whenever new data arrives
- Caching every model output permanently
- Giving the agent lightweight references, such as file names, and letting it fetch full content with tools when needed
- Perché è utile mettere i contenuti stabili, come le istruzioni di sistema e le definizioni degli strumenti, all'inizio in un ordine fisso?
- Rende il modello più creativo
- Every API requires this order
- An identical prefix can be reused through prompt caching, which lowers cost and latency
- It hides the instructions from the user
- Which approach to tool design does the guide recommend?
- Tools should return all raw data so nothing is missed
- Tools should return concise, high-signal output and support filtering or pagination
- Many tools with overlapping descriptions give the model more choice
- Tool descriptions should be left empty to save tokens
- Which statement is a misconception the guide warns about?
- Large context windows increase cost per request
- Tool definitions take up tokens on every turn
- Retrieval can reduce how much text goes into the window
- A bigger context window removes the need to curate what goes in
- What role do sub-agents play in context engineering?
- They explore in their own separate context and return condensed findings to the main agent
- They double the context window of the main agent
- They replace the system prompt
- They store user passwords between sessions