Year 6 · 70 minutes · Generation
Does a likely next word make a true sentence?
A language generator chooses from possible next tokens. This teaching model starts with a small supplied score table, converts scores into probabilities using softmax and samples from them. Temperature changes how concentrated the probabilities are. Fixed random draws make comparisons reproducible. It is not a large language model and its word scores are invented. Likelihood is a property of this distribution, not evidence that a sentence describes the world.
Print the supplied phrase and score table. Prepare a number line from 0 to 1 for sampling. Explain that real tokenisers can split words into pieces; this tiny model uses whole words for visibility.
Read a probability bar and distinguish a guess from evidence. Useful earlier investigations: y1-pattern Use pairs with predictor/operator roles. Swap after the first comparison. Each learner draws or writes their own explanation using one exact case.
Australian Curriculum Version 9 · Digital Technologies: AC9TDI6K03, AC9TDI6P06. Selected aspects only. This activity contributes evidence; it does not cover the full descriptor or achievement standard. A programming descriptor is not claimed for merely moving controls. ACARA AI curriculum connection · V9 Technologies These are planning connections, not ACARA endorsement or exhaustive descriptor alignment.
Collect several continuations of the same phrase and distinguish familiar from supported.
Ask: “Does sounding natural make the fact true?”
Listen for: “No, it could be a familiar but false claim.”
Predict the effect of increasing temperature with logits and random draws fixed.
Ask: “Will the largest probability usually grow or shrink?”
Listen for: “It should shrink as alternatives gain probability.”
Change temperature and inspect probabilities, cumulative intervals and multiple sampled continuations. Replay identical draws to isolate the parameter effect.
Ask: “Why did the same random number choose a different token?”
Listen for: “The probability intervals changed.”
Use the unsupported-fact score table. Observe that low temperature concentrates on its wrong continuation.
Ask: “Did greater concentration create evidence?”
Listen for: “No, the score table never checked a source.”
Choose settings for a fictional creative task and a factual task. Add a source-check requirement for factual use; compare outputs without claiming one temperature guarantees truth.
Ask: “What must happen outside sampling to support a fact?”
Listen for: “We need relevant evidence and verification.”
Annotate one draw on the cumulative probability strip.
Ask: “What exactly was computed in this lab?”
Listen for: “Softmax probabilities and sampling from supplied scores.”
The most likely word is a verified fact.
Increase temperature with logits and random draws fixed. Predict concentration and at least one sampled token change.
A supplied score table can assign its highest score to a false continuation; lowering temperature makes it more consistently wrong.
Specify a creative sampling policy and a separate factual evidence requirement, supported by two replayed runs.
Ask learners to identify the cumulative interval containing one draw. Require them to distinguish supplied scores, calculated probabilities and external factual evidence.
Begin with three candidates and probabilities in tenths; use a physical number strip before displaying softmax.
Calculate entropy across temperatures and examine why diversity is not the same as usefulness.
A token-branch journal with probability strips, replay comparison and evidence policy.
Only supplied benign text is sampled. No account, prompt upload or external model request occurs.
Sample 65,536 seeded draws from a temperature-scaled distribution using MPS/CUDA tensor operations. Compare theoretical probabilities, empirical frequencies and absolute errors.
| Criterion | Beginning | Secure | Extending |
|---|---|---|---|
| Sampling mechanism | Treats output as chosen by understanding | Connects draw to probability interval | Explains a temperature-induced interval change |
| Evidence judgement | Treats high score as truth | Identifies unsupported output | Designs a verification step independent of sampling |
Australian Curriculum Version 9 · Digital Technologies
References: AC9TDI6K03, AC9TDI6P06. Read the current source (checked 2026-09-07).
Evidence to assess: A token-branch journal with probability strips, replay comparison and evidence policy.
Selected aspects only. This activity contributes evidence; it does not cover the full descriptor or achievement standard. A programming descriptor is not claimed for merely moving controls. Moderate the supplied illustrative responses against your school unit and current achievement standard.
These are planning estimates to test with your class. A short session develops one supported claim; it does not compress the whole senior project.
| Stage | 45 minute focus | 60 minute investigation |
|---|---|---|
| Readiness and prediction | 0–5 | 0–5 |
| Trace the supplied example | 5–13 | 5–15 |
| Author and run cases | 13–25 | 15–35 |
| Counterexample and redesign | 25–35 | 35–45 |
| Explain and discuss | 35–42 | 45–55 |
| Export and handover | 42–45 | 55–60 |
For a longer project, use three 50-minute sessions. Session 1 (0–50): readiness, model, hypothesis and initial cases. Export a project and record the next test. Session 2 (50–100): reopen, check settings, author counterexamples and revise the design. Export the changed project and identify unresolved evidence. Session 3 (100–150): independent peer test, final artefact, individual explanation and moderation. If using two 60-minute sessions, stop at minute 60 after saving the first comparison; use 60–120 for redesign, independent test and defence.
Entry check: Read a probability bar and distinguish a guess from evidence. Ask the learner to demonstrate it before choosing the level of support.
Preparation: allow about 15 minutes to run the starter, print the cards and check a project can be reopened. This estimate has not yet been measured in a classroom pilot.
Read the entry question aloud, model one row, and label the units. Offer the case table as a large-print sheet. Keep mathematical derivations optional until the learner can explain the comparison.
For one device, use a projector: one pair predicts, one operates, and the class records on paper. Swap roles after the first comparison. For individual access, support keyboard controls and a written table equivalent to each visual. Learners may explain orally or with an annotated diagram. Never require personal data, a recorded voice, or a photograph.
Mixed readiness: if the entry check is difficult, use the linked prerequisite and the first two case cards; retain the same central question. If secure, ask the learner to design an unseen test and state which explanation it could disprove.
Count which words follow the selected word in your corpus and normalise the counts.
Starting parameters: Previous word = is
4 observed continuations in your corpus.
| word | count | probability |
|---|---|---|
| blue | 2 | 0.5 |
| calm | 1 | 0.25 |
| green | 1 | 0.25 |
These are authored examples, not work collected from children. Assess reasoning using the lesson rubric, not whether the first prediction was correct.
Beginning: “It worked because the result looks right.” This identifies no exact case, control or measurement. Ask the learner to point to one row and say what happened.
Developing: “In the first case I recorded word: blue; count: 2; probability: 0.5.” This cites evidence, but does not yet explain how the result follows from the rule. Ask the learner to trace the relevant step.
Secure: “For the first supplied case, word: blue; count: 2; probability: 0.5. I can trace it using this mechanism: Count which words follow the selected word in your corpus and normalise the counts. My result supports a claim about these supplied cases. It does not establish that the same result holds outside them.” Look for an accurate trace, the actual settings and a bounded claim; accept equivalent oral or visual evidence.
Extending: The learner constructs and reruns a new case, reports whether the first explanation survives, and defends a revised design. Use this concrete challenge: Write two contexts that share a final word but support different continuations. Compare them with the trained-model bonus lab. Require the original and changed evidence and this boundary: This is a count-based language model, not a transformer. Compare with the trained-model bonus investigation.
Moderation: first assess independently against each lesson criterion. Compare the exact trace or artefact that led to your judgement. Resolve differences using evidence, not polished language. Keep each learner's individual explanation even when the artefact was produced in a group.