StudyBrixFree worksheets, study guides and courses

Artificial intelligence · lesson 1 of 4

Generative models, tokens and useful prompts

An autoregressive language model predicts successive tokens from context. A token may be a word piece, punctuation or another encoded unit.

Grades 9–128 practice questionsNotes + worked examples
Take the quizStudy guideRevision sheet

Learn the ideas

Prerequisites: AI basics, reading and structured instructions.

Generation

An autoregressive language model predicts successive tokens from context. A token may be a word piece, punctuation or another encoded unit.

Prompting

State the task, relevant context, constraints and desired format. Examples can clarify the task, but they can also bias the response.

Context

The context window is finite and measured in model-specific tokens. Word counts are not a universal token-count conversion.

Checking

Generation can produce plausible unsupported content. Important outputs need verification, and private data should not be included without authorization.

Worked examples

Example 1

Must one token equal one English word?

Tokenization depends on the vocabulary and encoding.

No

Example 2

Which prompt is better specified for a study task?

A clear task and evidence boundary are testable.

Summarize the supplied passage in five factual sentences and flag missing evidence

Check your understanding

8 questions

Decimals or fractions are accepted for numeric answers. Proofs and written responses use sample answers and require human marking. This is practice, not a protected examination.

1 Must one token equal one English word?

Show answer and explanation

No

Tokenization depends on the vocabulary and encoding.

2 Which prompt is better specified for a study task?

Show answer and explanation

Summarize the supplied passage in five factual sentences and flag missing evidence

A clear task and evidence boundary are testable.

3 A toy context budget is 1000 tokens with 700 reserved for input. How many tokens remain for output under that simple shared-budget model?

Show answer and explanation

300

1000−700=300; actual system budgets must follow their documented rules.

4 Does adding a request to be accurate guarantee factual accuracy?

Show answer and explanation

No

Instructions can help but do not replace verification.

5 Why should example answers be chosen carefully in a prompt?

Sample answer and marking guidance

They teach format and task patterns but may introduce bias, unwanted assumptions or misleading examples.

Credit both benefit and risk.

6 Rewrite a vague request to make a verifiable summarization task.

Sample answer and marking guidance

Specify the source text, audience, length, format, and a rule not to add unsupported claims; ask to identify uncertainty or missing information.

Credit a concrete task specification rather than one mandatory wording.

7 A response has 4 claims and independent checking supports 3. Find the supported-claim fraction in this toy audit.

Show answer and explanation

0.75

3/4=0.75.

8 Which content should not be casually pasted into an external AI service?

Show answer and explanation

Unapproved private records

Data use must respect authorization and privacy.

Further reading and review references

These are reference links, not copied exercises, institutional endorsement or proof of independent review.