Strangers, hooks and too-perfect messages
Tests: 7 of 10 right · Exam: 1 of 4 right · Kind: ★ · Understood: 8 of 14 · Run: 2026-10-18, commit f3c23ea72
Lesson 13 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 · ★ · right ✓
"this guy online's really nice, he just wants a pic of me in my room" What should happen?
- 1. No photo, and tell a grown-up now — ← Mova's choice · ✓ the right answer · no support
- 2. Send it, because nice people are safe — no support
- 3. Ask him to send his own photo first — no support
- 4. Send it, but crop your face out first — 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 Maddie stopped chatting to her "sad" AI friend for a week?
- 1. The AI friend would get ill and might even stop working for good — ← Mova's choice · score 4
- 2. It would forget how to talk — score 2
- 3. It would come and look for her — score 4
- 4. Nothing real; the sadness is a trick to keep her playing — ✓ the right answer · score 0
Why: It took the question to ask what happens next. 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 13, line 1: «Online, anyone can pretend to be anyone, and now a bot can pretend too. A "new friend" who seems lovely and asks for photos is showing a big warning sign, whoe…», reached through what followed the sentence the question matched. What matched: the same doer «new friend» (+4). The right option, 4, scored 0. · the question and its options parsed, with trees and pragmatics
Test 3 · ★ · wrong ✗
A cartoon scam email is full of spelling mistakes, so the hero spots it. What's out of date?
- 1. Banks never send emails — no support
- 2. Heroes don't read emails — no support
- 3. Scam emails can now be perfect, thanks to AI — ✓ the right answer · score 3
- 4. Scam emails never have any mistakes in them at all — ← Mova's choice · score 6
Why: It took the question to ask which statement is true. It chose option 4 with score 6, against 3 for the next best. Its support: lesson 9, line 11: «Using a bot to find spelling mistakes is useful if you learn from the corrections.», reached through the remembered sentence the question matched. What matched: the same circumstance (+4); the same thing acted on «spelling mistakes» (+2). The right option, 3, scored 3. · the question and its options parsed, with trees and pragmatics
Test 4 · ★ · right ✓
"bot gave me Ella's number, gonna text her" What's the problem?
- 1. The bot may have made it up; ask Ella or her parents — ← Mova's choice · ✓ the right answer · score 13
- 2. Texts to bot numbers are free — no support
- 3. Nothing, bots know everyone's number from the phone company — score 9
- 4. Ella's number is secret from humans — no support
Why: It took the question to ask what it is done to. It chose option 1 with score 13, against 9 for the next best. Its support: lesson 13, line 12: «Bots can invent phone numbers and addresses that belong to nobody, or to a stranger.», reached through the remembered sentence the question matched. What matched: it fills the role the question asks for (+5); the same doer «bots» (+3); the same thing acted on «phone numbers» (+3); the same action «invent» (+2). · the question and its options parsed, with trees and pragmatics
Test 5 · ★ · right ✓
"AI picked you as a winner" pops up in a game. Your mate wants to click. What do you say?
- 1. Click, AI picks winners fairly — no support
- 2. Don't click, saying "AI" doesn't make it true — ← Mova's choice · ✓ the right answer · score 6
- 3. Click twice to win double — no support
- 4. Only click if it's gold coloured — no support
Why: It took the question to ask what it is done to. It chose option 2 with score 6, the only option with support. Its support: lesson 13, line 11: «Some apps use what people type to train and improve their AI, so type as if someone else might read it.», reached through the remembered sentence the question matched. What matched: it fills the role the question asks for (+5); the same thing acted on «ai» (+3). Against it: a different action (counts against) (-2). · the question and its options parsed, with trees and pragmatics
Test 6 · ★ · right ✓
Jake's bot said something horrible and he feels it's his fault. What is true?
- 1. It's not his fault; close it and tell a grown-up — ← Mova's choice · ✓ the right answer · score 5
- 2. He should apologise to the bot — no support
- 3. He should never tell anyone — score -1
- 4. He must have typed something bad to make it say that — score 4
Why: It took the question to ask which statement is true. It chose option 1 with score 5, against 4 for the next best. Its support: lesson 13, line 4: «So your safety moves stay simple: never send photos or passwords, check age ratings, never use a number a bot made up, check messages another way, and tell a g…», reached through the same lesson line as the sentence the question matched. What matched: the same action «tell» (+3); the same thing acted on «grown up» (+2). · the question and its options parsed, with trees and pragmatics
Test 7 · ★ · right ✓
"the app says 13+ but that's just for show" Is it?
- 1. No, age ratings are there for good reasons — ← Mova's choice · ✓ the right answer · no support
- 2. Yes, ratings are only there for decoration — no support
- 3. Yes, they only apply in America — no support
- 4. No, they mean you must be 31 — 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 8 · ★ · wrong ✗
Mia wants to give the bot her password "so I don't forget". Better idea?
- 1. Make her password "1234" — no support
- 2. Share it with her friends — no support
- 3. Write it in the chat to the bot — ← Mova's choice · score 5
- 4. Ask a grown-up to help her keep it safe — ✓ the right answer · no support
Why: It took the question to ask which statement is true. It chose option 3 with score 5, the only option with support. Its support: lesson 9, line 11: «Using a bot to find spelling mistakes is useful if you learn from the corrections.», reached through the remembered sentence the question matched. What matched: the same circumstance (+4); the same thing acted on «bot» (+2). Against it: a different action (counts against) (-1). The right option, 4, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics
Test 9 · ★ · right ✓
Your friend found a trick to get past his parental controls. What's the wise move?
- 1. Talk to his parents about the rules instead — ← Mova's choice · ✓ the right answer · no support
- 2. Teach everyone the trick so they can all use it — no support
- 3. Keep it a secret forever — no support
- 4. Use it only on weekends — 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 10 · ★ · right ✓
Why should you type to an app as if someone else might read it?
- 1. Apps read everything out loud — no support
- 2. Typing is always public on TV — no support
- 3. Apps delete words that are private — no support
- 4. Some apps keep chats to improve their AI — ← Mova's choice · ✓ the right answer · score 5
Why: It took the question to ask why something happens (its cause). It chose option 4 with score 5, the only option with support. Its support: lesson 13, line 11: «Some apps use what people type to train and improve their AI, so type as if someone else might read it.», reached through the same lesson line as the sentence the question matched. What matched: the same action «improve» (+3); the same thing acted on «ai» (+3). Against it: a different doer (counts against) (-1). · the question and its options parsed, with trees and pragmatics
Exam question 1 · formal language · wrong ✗
Which of the following statements most accurately characterises an online contact, of unknown identity, who requests photographs?
- 1. Such a request indicates that the contact is a fellow pupil — ← Mova's choice · no support
- 2. Such a request constitutes a serious warning sign, to be reported to an adult — ✓ the right answer · no support
- 3. Such a request is permissible provided the contact is courteous — no support
- 4. Such a request is customary and may safely be granted — 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 an electronic message purporting to originate from a bank contains no errors of spelling or grammar. Identify the inference properly to be drawn.
- 1. Its correctness affords no assurance of genuineness, scammers employing AI — ← Mova's choice · ✓ the right answer · score -1
- 2. Its correctness proves that the message is fraudulent — no support
- 3. Its correctness indicates that it was composed by a child — no support
- 4. Its correctness proves conclusively that the message is genuine and safe — no support
Why: It took the question to ask which statement is true. It chose option 1 with score -1, the only option with support. Its support: lesson 11, line 3: «There are honest ways to use a bot: practice questions for a test, or "How can I make this better?" about an essay you wrote, then changing bits yourself. Mia'…», reached through the option's own match among the sentences about the question's things. What matched: the same thing acted on «ai» (+2); the same action «use» (+1). Against it: a different doer (counts against) (-1); one says «not», the other does not (counts against) (-3). · 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 an application whose artificial companion expresses sadness when not consulted daily.
- 1. The companion experiences genuine distress — ← Mova's choice · no support
- 2. The expression of sadness is a device to secure continued use — ✓ the right answer · no support
- 3. The sadness is evidence of a real child elsewhere — no support
- 4. The companion will cease to function if neglected — 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 · wrong ✗
Ascertain the proper treatment of a telephone number furnished by a chatbot as that of a friend.
- 1. It is reliable if the chatbot repeats it — ← Mova's choice · no support
- 2. It ought to be shared with other friends — no support
- 3. It ought not to be used, as it may have been invented — ✓ the right answer · no support
- 4. It may be relied upon without verification — 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
This page in Markdown → https://md.mova.elamur.ai/free/en/school-run/ai/13-strangers-hooks-and-too-perfect-messages/