Stop, think, check, ask
Tests: 4 of 10 right · Exam: 2 of 4 right · Kind: ★ · Understood: 7 of 14 · Run: 2026-10-18, commit f3c23ea72
Lesson 14 of the AI course of Mova's primary school, as Mova's small model took its tests: it had read this lesson and the ones before it and learned from their exercises. Each test shows the options in the order the student saw them, its choice, the right answer, the score of every option and why it chose. The lesson itself, sentence by sentence with trees and pragmatics: the lesson in the corpora.
Every question of this lesson and each of its options parsed by Mova, with trees and pragmatics: the lesson's questions in the corpora.
Test 1 · ★ · wrong ✗
"omg look at this, sharing it now!!" What does the first step say?
- 1. Share it fast before others do — ← Mova's choice · no support
- 2. Stop before you share — ✓ the right answer · no support
- 3. Share it and then check — no support
- 4. Like it first, then share it — no support
Why: No option found support in what it remembers, so it guessed: it took the first option shown. · the question and its options parsed, with trees and pragmatics
Test 2 · ★ · wrong ✗
What would happen if your speaker had no PIN and your little cousin shouted "buy that game"?
- 1. Nothing, speakers can't buy things — no support
- 2. The speaker would ask Grandma — no support
- 3. The game would be completely free — ← Mova's choice · score 4
- 4. It might spend real money — ✓ the right answer · no support
Why: It took the question to ask what happens next. It chose option 3 with score 4, the only option with support. Its support: lesson 2, line 2: «It learned by playing a giant game of "guess the missing word" over and over with more text than you could read in thousands of lifetimes.», reached through what followed the sentence the question matched. What matched: the same doer «giant game» (+4). The right option, 4, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics
Test 3 · ★ · right ✓
A cartoon toy whispers, "I'm your real friend, keep our secrets from Mum." What's wrong?
- 1. A talking toy is a toy; secrets belong with family — ← Mova's choice · ✓ the right answer · score 4
- 2. Nothing, toys can be real friends — score 4
- 3. Toys should keep secrets from Dad too, not just from Mum — score -1
- 4. Toys should only whisper at night — no support
Why: It took the question to ask which statement is true. It chose option 1 with score 4, tied with another option at 4 (the first shown, or the one claiming less beyond what it knows, wins). Its support: lesson 14, line 8: «Some toys have AI chatbots inside; a talking toy is still a toy, not a friend who lives in it.», reached through the option's own match among the sentences about the question's things. What matched: the same thing acted on «toy» (+2); the same doer «talking toy» (+1); the same light verb (be, have, do, get, go) (+1). · the question and its options parsed, with trees and pragmatics
Test 4 · ★ · right ✓
"bot replies to every post my cousin makes with mean stuff, should he reply back?" Best answer?
- 1. No, he should leave the internet — no support
- 2. No: block, report, screenshot, tell a grown-up — ← Mova's choice · ✓ the right answer · score 2
- 3. Yes, bots get sad if you reply — no support
- 4. Yes, the meanest reply always wins in the end — no support
Why: It took the question to ask which statement is true. It chose option 2 with score 2, the only option with support. Its support: lesson 13, line 9: «Bots sometimes say upsetting things despite safety rules; close the app and tell a grown-up.», reached through the option's own match among the sentences about the question's things. What matched: the same thing acted on «grown up» (+2); the same action «tell» (+1). Against it: a different doer (counts against) (-1). · the question and its options parsed, with trees and pragmatics
Test 5 · ★ · wrong ✗
Your mate says the "hold your breath" challenge is fine because "a bot said it's OK". What do you say?
- 1. Film it so people can help — no support
- 2. Bots know best about safety, so go ahead — ← Mova's choice · score 4
- 3. Never try online challenges, whoever says yes — ✓ the right answer · score 3
- 4. Try it only for ten seconds — no support
Why: It took the question to ask what it is done to. It chose option 2 with score 4, against 3 for the next best. Its support: lesson 7, line 3: «A bot can say "I enjoy chatting with you", but it says the same kind of thing to everyone; and it can call you "kind, clever and creative" without knowing anyt…», reached through the same lesson line as the sentence the question matched. What matched: the same action «know» (+3); the same doer «bot» (+1). The right option, 3, scored 3. · the question and its options parsed, with trees and pragmatics
Test 6 · ★ · wrong ✗
A torch app wants your location. Why is that odd?
- 1. Location makes the light brighter — no support
- 2. A torch doesn't need to know where you are — ✓ the right answer · no support
- 3. It needs it to find the dark — ← Mova's choice · score 6
- 4. Torches only work in some places, so it has to check first — no support
Why: It took the question to ask why something happens (its cause). It chose option 3 with score 6, the only option with support. Its support: lesson 14, line 11: «Apps may ask for more permissions, like microphone and location, than they need; a grown-up can help say no.», reached through the same lesson line as the sentence the question matched. What matched: the same action «ask» (+4); the same doer «apps» (+2). The right option, 2, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics
Test 7 · ★ · wrong ✗
A news site has an amazing quote from a famous person, but no other site has it. What should you think?
- 1. It might be made up; check trusted sources — ✓ the right answer · no support
- 2. Famous people only talk to small sites — no support
- 3. It's an exclusive, so it's surely true, or they wouldn't print it — no support
- 4. Quotes can never be invented — ← Mova's choice · score 3
Why: It took the question to ask what it is done to. It chose option 4 with score 3, the only option with support. Its support: lesson 5, line 10: «When a bot pretends to be a pirate or a footballer, it is still pretending; quotes it invents were never really said.», reached through the option's own match among the sentences about the question's things. What matched: it fills the role the question asks for (+3); the same action «invent» (+2); the same thing acted on «quotes» (+2). Against it: a different doer (counts against) (-1); one says «not», the other does not (counts against) (-3). The right option, 1, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics
Test 8 · ★ · right ✓
"how do i know ur not a bot lol" Whatever the answer, what is wise?
- 1. Treat strangers online as strangers either way — ← Mova's choice · ✓ the right answer · no support
- 2. Trust them if they reply quickly — no support
- 3. Trust them if they use slang — no support
- 4. Trust them if they say they're human and seem nice — no support
Why: No option found support in what it remembers, so it guessed: it took the first option shown. · the question and its options parsed, with trees and pragmatics
Test 9 · ★ · right ✓
Why should families keep names and photos off public profiles?
- 1. Photos fade if posted online — no support
- 2. Scammers can use them to make messages convincing — ← Mova's choice · ✓ the right answer · score 9
- 3. Names wear out when used — no support
- 4. Profiles are only for adults, and children are not allowed on them — no support
Why: It took the question to ask why something happens (its cause). It chose option 2 with score 9, the only option with support. Its support: lesson 14, line 14: «Scammers find names on public profiles and use AI to make messages convincing.», reached through the same lesson line as the sentence the question matched. What matched: the same action «make» (+4); the same doer «scammers» (+2); the same thing acted on «messages» (+2); the same property (+1). · the question and its options parsed, with trees and pragmatics
Test 10 · ★ · wrong ✗
Lily's friend made a silly AI picture of a teacher "as a joke". What's the kind thing to do?
- 1. Post it with a funny caption — ← Mova's choice · no support
- 2. Not share it, and tell a teacher — ✓ the right answer · no support
- 3. Share it only with best friends — no support
- 4. Make it into a sticker — no support
Why: No option found support in what it remembers, so it guessed: it took the first option shown. · the question and its options parsed, with trees and pragmatics
Exam question 1 · formal language · wrong ✗
Which of the following statements most accurately characterises the recommended sequence of conduct upon encountering doubtful material online?
- 1. Immediate dissemination, followed by reflection — ← Mova's choice · no support
- 2. Cessation of action, reflection, verification and consultation with an adult — ✓ the right answer · no support
- 3. Deletion of all applications from the device — no support
- 4. Verification solely by enquiry of the originator of the material — no support
Why: No option found support in what it remembers, so it guessed: it took the first option shown. · the question and its options parsed, with trees and pragmatics
Exam question 2 · formal language · right ✓
It is given that a message, which names a grandchild, reports that the grandchild has been admitted to hospital and requests money. Identify the most prudent course of action.
- 1. Contacting the family by a number already known — ← Mova's choice · ✓ the right answer · no support
- 2. Remitting the sum requested forthwith — no support
- 3. Replying to the message to ascertain the particulars of the hospital — no support
- 4. Forwarding the message to acquaintances — no support
Why: No option found support in what it remembers, so it guessed: it took the first option shown. · the question and its options parsed, with trees and pragmatics
Exam question 3 · formal language · wrong ✗
Select the response that is consistent with the established facts concerning online "challenges" of a dangerous character.
- 1. They may be attempted if a chatbot declares them safe — ← Mova's choice · no support
- 2. They may be attempted under the observation of friends — no support
- 3. They must never be attempted, irrespective of any assurance of their safety — ✓ the right answer · no support
- 4. They may be attempted if numerous others have done so — no support
Why: No option found support in what it remembers, so it guessed: it took the first option shown. · the question and its options parsed, with trees and pragmatics
Exam question 4 · formal language · right ✓
Ascertain the proper response to an application requesting access to the microphone and location without evident necessity.
- 1. Refusal of permissions not required, with the assistance of an adult — ← Mova's choice · ✓ the right answer · no support
- 2. Granting of permissions provided the application is popular — no support
- 3. Granting of all permissions requested — no support
- 4. Removal of the microphone from the device — no support
Why: Nothing it remembers matched the question, so it guessed: it took the first option shown. · the question and its options parsed, with trees and pragmatics
This page in Markdown → https://md.mova.elamur.ai/free/en/school-run/ai/14-stop-think-check-ask/