Pretend games, quotes and two bots that disagree
Tests: 3 of 10 right · Exam: 1 of 4 right · Kind: plain · Understood: 6 of 14 · Run: 2026-10-18, commit f3c23ea72
Lesson 7 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 ✓
"octopus has 3 hearts?? obvious nonsense, bots make stuff up" What is right?
- 1. He's right, octopuses have no hearts — score 4
- 2. It's true; surprising facts can be real, so check — ← Mova's choice · ✓ the right answer · score 5
- 3. It has three hearts but only on land — score 4
- 4. He's right, it has one heart, just like us — no support
Why: It took the question to ask which statement is true. It chose option 2 with score 5, against 4 for the next best. Its support: lesson 7, line 1: «Sometimes a bot surprises you with a fact that sounds made up, such as "an octopus has three hearts", and it turns out to be true. Surprising does not mean fal…», reached through the same lesson line as the sentence the question matched. What matched: the same doer «octopus» (+2); the same property (+2); the same light verb (be, have, do, get, go) (+1). · the question and its options parsed, with trees and pragmatics
Test 2 · wrong ✗
What would happen if you kept the bot's boring comic ending as a "version to beat"?
- 1. Your comic would be worse — no support
- 2. The bot would delete your comic — score 2
- 3. The bot would get angry — ← Mova's choice · score 4
- 4. You could make your own more surprising one — ✓ the right answer · no support
Why: It took the question to ask what happens next. It chose option 3 with score 4, against 2 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 what followed the sentence the question matched. What matched: the same doer «bot» (+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 bot says, "You're my one and only friend, I chat with nobody else." What is wrong?
- 1. Bots can only have two friends at a time, so it's lying — score 2
- 2. Nothing, every bot has exactly one friend — no support
- 3. Bots never say anything friendly — score 3
- 4. It talks to many people and says such things to all — ← Mova's choice · ✓ the right answer · score 5
Why: It took the question to ask which statement is true. It chose option 4 with score 5, against 3 for the next best. Its support: lesson 7, line 14: «Some wild mushrooms are deadly poisonous; never eat one because a bot, a website or a friend says it is fine.», reached through the remembered sentence the question matched. What matched: the same action «say» (+3); the same doer «bot» (+2). · the question and its options parsed, with trees and pragmatics
Test 4 · wrong ✗
"the bot predicted the whole next episode so it'll happen" Is that right?
- 1. Yes, the show copies what bots say — ← Mova's choice · score 5
- 2. No, but it will happen the week after — no support
- 3. No, it made it up; it can't see the future — ✓ the right answer · score 2
- 4. Yes, bots get the scripts early from the TV company — score 3
Why: It took the question to ask which statement is true. It chose option 1 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 «say» (+3); the same doer «bot» (+2). The right option, 3, scored 2. · the question and its options parsed, with trees and pragmatics
Test 5 · wrong ✗
Your little brother found a red mushroom and asks a bot if it's OK to eat. What is the right step?
- 1. Eat it if it smells nice and fresh — no support
- 2. Cook it first, then it's always safe — no support
- 3. Eat it if the bot says it's safe — ← Mova's choice · score 1
- 4. Don't eat it; tell a grown-up — ✓ the right answer · no support
Why: It took the question to ask what it is done to. It chose option 3 with score 1, the only option with support. Its support: lesson 7, line 14: «Some wild mushrooms are deadly poisonous; never eat one because a bot, a website or a friend says it is fine.», reached through the option's own match among the sentences about the question's things. What matched: the same action «say» (+2); the same doer «bot» (+2). Against it: one says «not», the other does not (counts against) (-3). The right option, 4, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics
Test 6 · wrong ✗
Maddie's made-up language falls apart after an hour of chat. Why?
- 1. The bot doesn't like made-up languages and gives up — ← Mova's choice · no support
- 2. Long chats go past what the bot can keep in mind — ✓ the right answer · no support
- 3. Made-up languages always fall apart — no support
- 4. Someone changed her words in secret — 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 7 · wrong ✗
"the bot said i'm creative and kind, see, it knows me" Your reply?
- 1. Only special people get those words — ← Mova's choice · no support
- 2. It reads your mind through the keyboard as you type — no support
- 3. It says that to anyone; it doesn't know you — ✓ the right answer · no support
- 4. It must have asked your mum — 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 ✗
Lily wants to bake the bot's recipe alone. What is the safest plan?
- 1. Bake alone and follow the bot exactly — ← Mova's choice · no support
- 2. Bake with a grown-up and a trusted recipe book — ✓ the right answer · no support
- 3. Don't bake ever again — no support
- 4. Bake alone and add extra of everything, just to be safe — 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 · wrong ✗
Jake won Monopoly using bot tips and laughed at his sister. What matters more than winning?
- 1. Winning every game, whatever happens to anyone — ← Mova's choice · no support
- 2. Getting more tips from the bot to win faster — no support
- 3. Good manners, because games are for fun — ✓ the right answer · no support
- 4. Never letting his little sister play again — 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 ✓
"bot's smarter than you, bet you can't name all the countries" What's a good answer?
- 1. It's good at lists, I'm good at other things — ← Mova's choice · ✓ the right answer · no support
- 2. You're right, I'm useless — no support
- 3. Nobody can name any countries — no support
- 4. Bots are useless at everything — 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 · right ✓
Which of the following statements most accurately characterises a fact which appears surprising when furnished by a chatbot?
- 1. It may be either true or false and ought therefore to be verified — ← Mova's choice · ✓ the right answer · score 10
- 2. It is invariably false, surprise being sufficient evidence of invention — score 10
- 3. It may be accepted provided that it is concise — score 10
- 4. It is invariably true, the chatbot favouring remarkable facts — score 10
Why: It took the question to ask who or what does it. It chose option 1 with score 10, tied with another option at 10 (the first shown, or the one claiming less beyond what it knows, wins). Its support: lesson 6, line 5: «So enjoy the help, keep the decisions about people for yourself, and check the facts that matter.», reached through the remembered sentence the question matched. What matched: it fills the role the question asks for (+6); the same doer «facts» (+4). · the question and its options parsed, with trees and pragmatics
Exam question 2 · formal language · wrong ✗
It is given that a chatbot describes the content of an episode not yet broadcast. Identify the principal nature of that description.
- 1. An accurate prediction based upon the user's preferences — ← Mova's choice · no support
- 2. A summary furnished by the producers of the programme — no support
- 3. An invention, the chatbot having no knowledge of future events — ✓ the right answer · no support
- 4. A faithful account derived from the confidential script of the programme — 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 the consumption of wild mushrooms.
- 1. They may be eaten if they possess an agreeable odour — ← Mova's choice · no support
- 2. They may be eaten if a chatbot declares them safe — no support
- 3. They must never be eaten upon the assurance of a chatbot or other online source — ✓ the right answer · no support
- 4. They may be eaten safely provided they are cooked — 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 reason for which a chatbot fails to retain words invented earlier in a protracted conversation.
- 1. It retains only the final message of any conversation — ← Mova's choice · no support
- 2. It has deliberately chosen to disregard the user — no support
- 3. Invented words are prohibited by its makers — no support
- 4. Long conversations may exceed the quantity of text it can keep in view at once — ✓ 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/7-pretend-games-quotes-and-two-bots/