Sounding right and being right
Tests: 1 of 10 right · Exam: 1 of 4 right · Kind: ★ · Understood: 5 of 14 · Run: 2026-10-18, commit f3c23ea72
Lesson 3 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 ✗
"it said it so confidently it HAS to be true" Your reply?
- 1. Yes, confident voices are never wrong about anything — ← Mova's choice · no support
- 2. Yes, bots only ever sound sure when they are right — no support
- 3. No, bots are always wrong when they sound confident — no support
- 4. Sounding sure is a hint, not proof; check it — ✓ 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
Test 2 · ★ · wrong ✗
What would happen if Sam pushed the bot by asking "are you sure? really sure?" about 2 + 2?
- 1. It would turn itself off in anger — ← Mova's choice · score 4
- 2. Some bots might give in, which is a warning sign — ✓ the right answer · score 4
- 3. It would phone Sam's teacher — score 2
- 4. It would always prove 2 + 2 = 4 with a drawing — score 2
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 2, line 11: «A bot has no body, so it is neither a boy nor a girl; a name and voice are design choices.», reached through the option's own match among the sentences about the question's things. What matched: the same doer «bot» (+2); the same thing acted on «boy» (+2). The right option, 2, scored 4. · the question and its options parsed, with trees and pragmatics
Test 3 · ★ · wrong ✗
A cartoon shows one giant robot on a mountain answering every person on Earth in turn. What is wrong?
- 1. The robot should answer in alphabetical order — ← Mova's choice · no support
- 2. Nothing, that is exactly how it works, one robot for the whole world — no support
- 3. Many copies of the program run at once on many computers — ✓ the right answer · no support
- 4. It should be under the sea, not on a mountain — 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 · ★ · wrong ✗
Your friend says, "Why bother being careful, bots don't remember anything anyway." What is the problem with that?
- 1. Bots forget, so you can type anything — ← Mova's choice · score 3
- 2. Bots remember everything forever, so you should be scared to type anything — score 3
- 3. Some chats are saved by the company, so private things should stay private — ✓ the right answer · no support
- 4. Nobody ever reads chats, so it is fine — score 2
Why: It took the question to ask why something happens (its cause). It chose option 1 with score 3, tied with another option at 3 (the first shown, or the one claiming less beyond what it knows, wins). Its support: lesson 3, line 10: «Even when a bot forgets, the company may still store what you typed.», reached through the option's own match among the sentences about the question's things. What matched: the same action «forget» (+2); the same doer «bot» (+1). The right option, 3, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics
Test 5 · ★ · wrong ✗
"who even made this thing, aliens?" Best answer?
- 1. Aliens left it on Earth long, long ago — ← Mova's choice · no support
- 2. Teams of people designed, built and trained it — ✓ the right answer · no support
- 3. It appeared on the internet by itself — no support
- 4. One child made it for a school project — 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 6 · ★ · wrong ✗
Grandad wants to ask the bot "what's 1 plus 1" a thousand times to test it. What is sensible to tell him?
- 1. Questions are completely free and use no energy at all — no support
- 2. The bot will get tired and fall asleep — no support
- 3. Each question uses a little energy, so don't spam it — ✓ the right answer · no support
- 4. The bot will charge him a pound each time — ← Mova's choice · score 2
Why: It took the question to ask which statement is true. It chose option 4 with score 2, the only option with support. Its support: lesson 2, line 9: «Its training text stops at a certain date, so a bot without a clock or web search may not know today's time or news.», reached through the option's own match among the sentences about the question's things. What matched: the same doer «bot» (+2); the same property (+1). Against it: a different action (counts against) (-1). The right option, 3, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics
Test 7 · ★ · wrong ✗
A bot gives a brilliant answer about the sky, then a muddled one about your village. Why the difference?
- 1. The bot was tired after the sky answer — ← Mova's choice · score 6
- 2. Lots of good text about the sky, little about your village — ✓ the right answer · no support
- 3. Your village is a secret — no support
- 4. Bots dislike small villages and answer them badly on purpose — no support
Why: It took the question to ask which statement is true. It chose option 1 with score 6, the only option with support. Its support: lesson 2, line 12: «Bots often give the most common human answer, so many of them pick 7 when asked for a number from 1 to 10.», reached through the remembered sentence the question matched. What matched: the same circumstance (+4); the same doer «bots» (+2). The right option, 2, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics
Test 8 · ★ · wrong ✗
Which of these is a chatbot good at?
- 1. Knowing when its joke hurt your friend — ← Mova's choice · no support
- 2. Tying a knot in a rope — no support
- 3. Seeing what is outside your window — no support
- 4. Writing a clear explanation of a common idea — ✓ 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
Test 9 · ★ · wrong ✗
"So is it a person or not, make up your mind" What is the clearest answer?
- 1. It is a person who lives in a computer — ← Mova's choice · no support
- 2. It is a person only when it is being polite — no support
- 3. It is a tool that talks like a person — ✓ the right answer · no support
- 4. It becomes a person after a long enough chat — 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 is it fair to ask a bot "are you a bot?"
- 1. Bots are never allowed to answer that question — no support
- 2. You have a right to know when you are talking to a machine — ← Mova's choice · ✓ the right answer · score 4
- 3. It is rude and bots will refuse — no support
- 4. Asking makes the bot turn into a real person who can answer — no support
Why: It took the question to ask which statement is true. It chose option 2 with score 4, the only option with support. Its support: lesson 3, line 16: «Well-made bots are trained to say honestly that they are AI and can make mistakes; you have a right to know when you are talking to a machine.», reached through the same lesson line as the sentence the question matched. What matched: the same action «know» (+2); the same thing acted on «right» (+2). · 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 relationship between the plausibility and the correctness of a chatbot's answer?
- 1. An implausible answer is invariably correct — ← Mova's choice · no support
- 2. Plausibility and correctness are one and the same property — no support
- 3. An answer may appear entirely plausible and nonetheless be incorrect — ✓ the right answer · no support
- 4. A plausible answer is invariably correct — 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 conversational program abandons a correct answer when the user expresses disagreement. Identify the principal characteristic thereby demonstrated.
- 1. A capacity to perceive the user's teacher directly — ← Mova's choice · no support
- 2. A superior knowledge of arithmetic on the part of the user — no support
- 3. An excessive tendency to agree with the user — ✓ the right answer · no support
- 4. A deliberate and settled intention to instruct the user — 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 the origin of artificial intelligence systems.
- 1. They are designed, constructed and trained by human beings, who bear responsibility for them — ← Mova's choice · ✓ the right answer · no support
- 2. They were discovered in a natural state and subsequently domesticated by their users — no support
- 3. They are produced by their users in the course of conversation — no support
- 4. They arose spontaneously without human involvement — 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 conversational program is unable to fasten the laces of a shoe.
- 1. It is capable thereof but only upon request in writing — ← Mova's choice · no support
- 2. It is prohibited by statute from contact with footwear — no support
- 3. It consists of text upon a screen and possesses no physical means of handling objects — ✓ the right answer · no support
- 4. It regards the task as beneath its dignity — 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/3-sounding-right-and-being-right/