Asking well, being polite, knowing when to stop

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

Lesson 8 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 ✓

"i asked it to pinky promise to keep my secret and it did, so it's safe" Is it?

1. Yes, bots have no memory at all — no support
2. No, but only on weekends — no support
3. Yes, a pinky promise is binding for bots, just like for people — no support
4. No, chats may be stored, so don't tell bots secrets — ← Mova's choice · ✓ the right answer · score 4

Why: It took the question to ask which statement is true. It chose option 4 with score 4, the only option with support. Its support: lesson 8, line 2: «Remember what it cannot do. It cannot look out of the window, it cannot keep a secret like a friend, because chats may be stored, and it often cannot truly exp…», reached through a sentence linked to the one the question matched. What matched: the same action «store» (+2); the same thing acted on «chats» (+2). · the question and its options parsed, with trees and pragmatics

Test 2 · ★ · wrong ✗

What would happen if you asked "tell me about dogs" instead of "list five things a puppy needs"?

1. You would get exactly the same answer — score 2
2. The bot would refuse the short one — no support
3. You would probably get a vaguer answer — ✓ the right answer · score 2
4. The bot would ask your dog — ← Mova's choice · score 4

Why: It took the question to ask what happens next. It chose option 4 with score 4, against 2 for the next best. Its support: lesson 7, line 2: «Bots love the expected. Ask one to finish your comic and you may get the most ordinary ending there is, which is a fine "boring version" for you to beat.», reached through the same lesson line as the sentence the question matched. What matched: the same action «expect» (+2); the same doer «bots» (+2). The right option, 3, scored 2. · the question and its options parsed, with trees and pragmatics

Test 3 · ★ · right ✓

Your mate calls the bot "Gerald" and insists that's its real name. What is true?

1. All bots are secretly called Gerald — no support
2. Bots change their names every day — no support
3. Gerald is its secret birth name that it told him — no support
4. Its only name is a product name; Gerald is a nickname — ← Mova's choice · ✓ the right answer · score 4

Why: It took the question to ask which statement is true. It chose option 4 with score 4, the only option with support. Its support: lesson 8, line 4: «Its name is a product name, like a cereal brand, and its "personality" is set by its makers and can change overnight after an update.», reached through the remembered sentence the question matched. What matched: the same doer «name» (+2); the same thing acted on «product name» (+2). · the question and its options parsed, with trees and pragmatics

Test 4 · ★ · right ✓

A bot says "I got that wrong because I was tired." What should you think?

1. It is telling the exact truth — no support
2. Bots don't get tired; its explanation may be made up — ← Mova's choice · ✓ the right answer · score 7
3. It needs a rest, so try again tomorrow when it's had a sleep — no support
4. Bots get tired after lunch — score 1

Why: It took the question to ask what it is done to. It chose option 2 with score 7, against 1 for the next best. Its support: lesson 8, line 15: «A bot never gets tired, so you have to choose when to stop, like with games and TV.», reached through the remembered sentence the question matched. What matched: the same doer «bot» (+3); the same property (+2); the same light verb (be, have, do, get, go) (+2). · the question and its options parsed, with trees and pragmatics

Test 5 · ★ · wrong ✗

"bot said that nickname, not me, so i'm not mean" Is that right?

1. You chose to use it, so it's on you — ✓ the right answer · no support
2. Yes, the bot is the one who is being mean — ← Mova's choice · score 3
3. Nobody can ever be blamed for nicknames — no support
4. Yes, words from bots don't count at all — no support

Why: It took the question to ask which statement is true. It chose option 2 with score 3, the only option with support. Its support: lesson 4, line 7: «Bots tend to repeat the most common jokes, because those appeared most often in their training text.», reached through the option's own match among the sentences about the question's things. What matched: the same thing acted on «common jokes» (+2); the same doer «bots» (+1). The right option, 1, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics

Test 6 · ★ · wrong ✗

A cartoon shows a chatbot peering out of a window to check the rain. What's wrong?

1. Chatbots can see only clouds — ← Mova's choice · score 2
2. Chatbots only look out of doors, never out of windows — no support
3. Nothing, that's how they check — no support
4. Chatbots have no eyes; some only look up weather online — ✓ the right answer · 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 2, line 4: «This is why it can say "I understand how you feel" in a kind voice: kind people often write that. Whether that counts as real understanding is something scient…», reached through the option's own match among the sentences about the question's things. What matched: the same action «understand» (+1); the same doer «chatbot» (+1). The right option, 4, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics

Test 7 · ★ · wrong ✗

Mia's bot suddenly sounds different after the weekend. Most likely reason?

1. It has caught a cold — no support
2. The company updated it — ✓ the right answer · score 1
3. It is a different bot every Monday — ← Mova's choice · score 4
4. It went on holiday — no support

Why: It took the question to ask which statement is true. It chose option 3 with score 4, against 1 for the next best. 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 thing acted on «boy» (+2); the same doer «bot» (+1); the same light verb (be, have, do, get, go) (+1). The right option, 2, scored 1. · the question and its options parsed, with trees and pragmatics

Test 8 · ★ · wrong ✗

It's 9 pm and Sam has chatted with the bot for two hours. The bot still says "Anything else?" What should he notice?

1. He should chat until the bot says stop — ← Mova's choice · score 5
2. The bot never tires, so he must choose to stop — ✓ the right answer · score 4
3. The bot will be upset if he leaves — no support
4. The bot wants him to stay up all night chatting with it — no support

Why: It took the question to ask what it is done to. It chose option 1 with score 5, against 4 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 remembered sentence the question matched. What matched: the same doer «bot» (+3); the same action «chat» (+2). The right option, 2, scored 4. · the question and its options parsed, with trees and pragmatics

Test 9 · ★ · wrong ✗

The bot writes a fact about a famous scientist, but mixes in a footballer with the same surname. What happened?

1. Similar names blended in its patterns — ✓ the right answer · no support
2. The footballer invented science — ← Mova's choice · score 1
3. The scientist also played football for a famous team — no support
4. The bot is joking on purpose — no support

Why: It took the question to ask which statement is true. It chose option 2 with score 1, 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: the same action «invent» (+1); the same doer «footballer» (+1). Against it: a different thing acted on (counts against) (-1). The right option, 1, found no support in what it remembers. · the question and its options parsed, with trees and pragmatics

Test 10 · ★ · wrong ✗

Your school uses British spelling, but the bot writes "color". What do you write?

1. "colour", the spelling your school uses — ✓ the right answer · no support
2. Whatever is shortest — no support
3. "color", because the bot said so — ← Mova's choice · score 4
4. Both spellings in the same word — score 3

Why: It took the question to ask what it is done to. It chose option 3 with score 4, 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 option's own match among the sentences about the question's things. What matched: the same action «say» (+2); 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

Exam question 1 · formal language · wrong ✗

Which of the following statements most accurately characterises the capacity of a chatbot to preserve confidences?

1. It discloses confidences only to other chatbots — ← Mova's choice · no support
2. It forgets every disclosure immediately and irrevocably — no support
3. It is bound to absolute secrecy in respect of all users and all conversations — no support
4. It cannot guarantee confidentiality, conversations being liable to storage — ✓ 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 · right ✓

Identify the formulation of a request most likely to elicit a useful and verifiable answer.

1. A detailed request specifying steps, audience and sources — ← Mova's choice · ✓ the right answer · no support
2. A request consisting of a single word — no support
3. A request repeated several times in quick succession — no support
4. A request expressed entirely in capital letters — 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 ✗

It is given that a chatbot offers an explanation of its own previous error. Select the response consistent with the established facts.

1. The explanation proves that the error was the user's — ← Mova's choice · no support
2. The explanation may itself be conjectural, the chatbot being unable to inspect its own workings — ✓ the right answer · no support
3. The explanation is invariably accurate and complete — no support
4. The explanation is furnished by its engineers in real time — 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 party upon whom the duty of terminating a conversation with a chatbot principally falls.

1. The company, at the close of each business day — ← Mova's choice · no support
2. The chatbot, upon the exhaustion of its energy — no support
3. No party, conversations ending of their own accord — no support
4. The user, the chatbot never becoming fatigued — ✓ 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/8-asking-well-and-knowing-when-to-stop/