Mova0.5 pre-release⌕
☰
home / at school / AI / 15

Bots are not doctors, helplines are people

Tests: 3 of 10 right · Exam: 1 of 4 right · Kind: ★★ · Understood: 7 of 14 · Run: 2026-10-18, commit f3c23ea72

Lesson 15 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 ✗

"bot told me to skip breakfast to lose weight, i'm 10" What is the right reply?

  • 1. Kids don't diet unless a doctor says; talk to a grown-up — ✓ the right answer · no support
  • 2. Skip lunch too to be quicker — no support
  • 3. Do it, because the bot knows best about food and it's only breakfast — ← Mova's choice · score 5
  • 4. Ask a second bot first — score 3

Why: It took the question to ask which statement is true. It chose option 3 with score 5, 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» (+2). The right option, 1, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics

Test 2 · ★★ · wrong ✗

What would happen if Maddie sent her address to the fake voice?

  • 1. She'd get a party invitation in the post — no support
  • 2. Nothing, because voices can't use addresses for anything — ← Mova's choice · score 0
  • 3. A stranger might know where she lives — ✓ the right answer · no support
  • 4. The voice would forget it the moment she said it — score 0

Why: It took the question to ask what happens next. It chose option 2 with score 0, tied with another option at 0 (the first shown, or the one claiming less beyond what it knows, wins). Its support: lesson 13, line 12: «Bots can invent phone numbers and addresses that belong to nobody, or to a stranger.», reached through what followed the sentence the question matched. What matched: the same thing acted on «addresses» (+4). Against it: a different action (counts against) (-2); a different doer (counts against) (-2). The right option, 3, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics

Test 3 · ★★ · wrong ✗

A cartoon kid in a smoky kitchen types "what do i do" into a chatbot. What should happen instead?

  • 1. Keep typing more questions into the chat box — ← Mova's choice · no support
  • 2. Ask the bot to call the fire brigade — no support
  • 3. Get out and call the emergency number — ✓ the right answer · no support
  • 4. Wait for the bot's full answer, then follow 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 4 · ★★ · right ✓

"this app lets me talk to my dead hero, it's really him" Is it?

  • 1. No, it's a bot copying his style — ← Mova's choice · ✓ the right answer · score 7
  • 2. Yes, if it knows his birthday too — no support
  • 3. Partly, it has half of his memories — no support
  • 4. Yes, it has his real voice and mind — no support

Why: It took the question to ask which statement is true. It chose option 1 with score 7, the only option with support. Its support: lesson 15, line 11: «An app that imitates a famous person who has died is a bot copying a style; the person is not there.», reached through the same lesson line as the sentence the question matched. What matched: the same action «copy» (+3); the same doer «bot» (+2); the same thing acted on «style» (+2). · the question and its options parsed, with trees and pragmatics

Test 5 · ★★ · right ✓

"ur account will be deleted in 24h, log in here!!" What does Chloe do?

  • 1. Send her password to be safe — no support
  • 2. Reply to ask if it's real — score 4
  • 3. Not click; open the app herself and tell a grown-up — ← Mova's choice · ✓ the right answer · score 7
  • 4. Click and log in quickly before it's too late and everything is lost — score 2

Why: It took the question to ask what is done. It chose option 3 with score 7, against 4 for the next best. Its support: lesson 15, line 14: «To log in safely, open the app or website yourself instead of using a link in a message.», 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 «open» (+2); the same thing acted on «app» (+2). · the question and its options parsed, with trees and pragmatics

Test 6 · ★★ · right ✓

"the AI said the world ends tuesday, i can't sleep" How can a grown-up help?

  • 1. Tell him to ask the AI again — no support
  • 2. Explain that scary online predictions are nonsense made for attention — ← Mova's choice · ✓ the right answer · score 3
  • 3. Agree and help him pack his bags, just in case it's true — no support
  • 4. Say it's true but far away — no support

Why: It took the question to ask what something is like. It chose option 2 with score 3, the only option with support. Its support: lesson 2, line 15: «Picture-making AI learned from millions of pictures with descriptions and builds new pictures that fit the words.», reached through the option's own match among the sentences about the question's things. What matched: the same action «build» (+2); the same doer «making ai» (+2). Against it: a different thing acted on (counts against) (-1). · the question and its options parsed, with trees and pragmatics

Test 7 · ★★ · wrong ✗

Mia worries a helpline will get her in trouble. What is true?

  • 1. Helplines report children to the police and to their school — ← Mova's choice · no support
  • 2. Trained people answer and are there to help — ✓ the right answer · no support
  • 3. Helplines only help adults — no support
  • 4. Helplines are run by bots — 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 ✗

Your friend says, "I can always tell AI pictures, easy." What's a humble reply?

  • 1. You're right, they always look fake if you look — ← Mova's choice · score 2
  • 2. AI pictures have watermarks always — no support
  • 3. Even grown-ups get it wrong, so check sources — ✓ the right answer · no support
  • 4. Only experts can see pictures — no support

Why: It took the question to ask which statement is true. It chose option 1 with score 2, the only option with support. Its support: lesson 12, line 15: «Many viral pictures are fake or edited, so check who posted them first before sharing.», reached through the option's own match among the sentences about the question's things. What matched: the same doer «many viral pictures» (+1); the same property (+1). The right option, 3, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics

Test 9 · ★★ · wrong ✗

Jake's mum says AI can copy faces. What can Jake ask her?

  • 1. To post his photos only on Mondays — ← Mova's choice · no support
  • 2. To delete every photo ever taken of him — no support
  • 3. Not to post his photos publicly — ✓ the right answer · no support
  • 4. To post more photos so fakes don't work — 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 · ★★ · wrong ✗

Safe search is on, but something upsetting still appears. What now?

  • 1. Keep scrolling, it's the filter's fault — ← Mova's choice · no support
  • 2. Tell a grown-up straight away — ✓ the right answer · no support
  • 3. Hide it so the tablet isn't taken — no support
  • 4. Turn safe search off — 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 provision of dietary advice to a child by a chatbot?

  • 1. Such advice is equivalent to that of a qualified dietician — ← Mova's choice · no support
  • 2. Such advice is reliable provided it is courteously expressed — no support
  • 3. Such advice ought to be followed without consultation — no support
  • 4. Such advice may be unsuitable, children not requiring diets save on medical instruction — ✓ the right answer · 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 · wrong ✗

It is given that a message threatens the deletion of an account unless the recipient authenticates through an enclosed link. Identify the nature of such a message.

  • 1. A reward offered for prompt authentication — ← Mova's choice · no support
  • 2. An examination administered by the school — no support
  • 3. A genuine notice issued by the provider in accordance with its terms of service — no support
  • 4. An attempt at phishing, intended to obtain the recipient's credentials — ✓ the right answer · 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 · right ✓

Select the response that is consistent with the established facts concerning conduct in the event of fire.

  • 1. The premises are to be vacated and the emergency number telephoned without delay — ← Mova's choice · ✓ the right answer · score 3
  • 2. The occupant is to remain concealed within the premises — no support
  • 3. A chatbot is to be consulted before any action is taken — no support
  • 4. A friend is to be informed by text message in the first instance — no support

Why: It took the question to ask which statement is true. It chose option 1 with score 3, the only option with support. Its support: lesson 15, line 10: «In an emergency, call the emergency number straight away instead of asking a bot.», reached through the option's own match among the sentences about the question's things. What matched: the same thing acted on «emergency number» (+2); the same action «call» (+1). · the question and its options parsed, with trees and pragmatics

Exam question 4 · formal language · wrong ✗

Ascertain the proper characterisation of an application purporting to permit conversation with a deceased celebrity.

  • 1. A recording of answers prepared by the person in life — ← Mova's choice · no support
  • 2. A repository of the person's actual memories — no support
  • 3. A means of genuine communication with the deceased — no support
  • 4. A program imitating the manner of that person, who is in no sense present — ✓ the right answer · 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/15-bots-are-not-doctors-helplines-are-people/