--- title: Olympiad: claims, clues and tricky messages ★★★ — how Mova does on the tests · AI description: Lesson 32 of the AI course of Mova's primary school: 4 of 11 tests right, exam 0 of 4, every question with the options, the student's choice, the right answer and why it chose. --- [Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/school-run/ai/32-olympiad-claims-clues-and-tricky-messages/) [home](https://md.mova.elamur.ai/free/en/) / [at school](https://md.mova.elamur.ai/free/en/school-run/) / [AI](https://md.mova.elamur.ai/free/en/school-run/ai/) / 32 # Olympiad: claims, clues and tricky messages ★★★ **Tests:** 4 of 11 right · **Exam:** 0 of 4 right · **Kind:** ★★★ · **Understood:** 9 of 15 · **Run:** 2026-10-18, commit `f3c23ea72` Lesson 32 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](https://md.mova.elamur.ai/free/en/corpora/school/ai/32-olympiad-claims-clues-and-tricky-messages/). Every question of this lesson and each of its options parsed by Mova, with trees and pragmatics: [the lesson's questions in the corpora](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/). ### Test 1 · ★★★ · wrong ✗ {#t1} "y'all, the bot gave me a Lincoln quote about the internet lol". Lincoln died in 1865. What's the truth? - **1.** It's real, because the bot used quotation marks — no support - **2.** It's real, but he said it about a different website — **← Mova's choice** · score 2 - **3.** It's made up: the internet didn't exist in his time — **✓ the right answer** · score 2 - **4.** It's real, he was very good at guessing the future — no support **Why:** It took the question to ask what it is done to. It chose option 2 with score 2, tied with another option at 2 (the first shown, or the one claiming less beyond what it knows, wins). Its support: lesson 32, line 4: «Logic helps too: someone who always tells the truth can never say "I am a liar", and neither can someone who always lies, so if you hear it, the speaker is nei…», reached through the option's own match among the sentences about the question's things. What matched: the same action «tell» (+1); it fills the role the question asks for (+1). The right option, 3, scored 2. · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t1/) ### Test 2 · ★★★ · wrong ✗ {#t2} Zip always tells the truth; Zap always lies. You hear one voice say, "I am the liar." Who said it? - **1.** Both of them, one after the other — no support - **2.** Zap, because a liar would admit being one — score 5 - **3.** Neither of them could have said it — **✓ the right answer** · no support - **4.** Zip, because Zip always tells the truth — **← Mova's choice** · score 9 **Why:** It took the question to ask who or what does it. It chose option 4 with score 9, against 5 for the next best. Its support: lesson 32, line 4: «Logic helps too: someone who always tells the truth can never say "I am a liar", and neither can someone who always lies, so if you hear it, the speaker is nei…», reached through the remembered sentence the question matched. What matched: the same thing acted on «truth» (+4); the same property (+3); the same action «tell» (+2). The right option, 3, found no support in what it remembers. · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t2/) ### Test 3 · ★★★ · wrong ✗ {#t3} "nah bruv the bot said it so it's true innit" Is that a sound rule? - **1.** Yes, bots are never wrong about anything at all — **← Mova's choice** · score 5 - **2.** No: bots can sound sure and still be wrong, so check — **✓ the right answer** · score 5 - **3.** Yes, as long as the answer is long and detailed — no support - **4.** No, because bots are always wrong about everything — score 5 **Why:** It took the question to ask which statement is true. It chose option 1 with score 5, tied with another option at 5 (the first shown, or the one claiming less beyond what it knows, wins). 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 doer «bot» (+3); the same circumstance (+2). The right option, 2, scored 5. · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t3/) ### Test 4 · ★★★ · wrong ✗ {#t4} Headline: "ROBOTS WILL TAKE EVERY SINGLE JOB BY NEXT WEEK!!" What's the wise reading? - **1.** Only the jobs that start with R will go — no support - **2.** Robots have already taken all the jobs — **← Mova's choice** · score 2 - **3.** Every job really will be gone next week — no support - **4.** It's hyperbole; read beyond the headline — **✓ the right answer** · no support **Why:** It took the question to ask which statement is true. It chose option 2 with score 2, the only option with support. Its support: lesson 21, line 3: «Then the bigger worries: will AI take jobs? Some tasks are moving to AI, new jobs appear too, and experts disagree on how much will change.», reached through the remembered sentence the question matched. What matched: the same action «take» (+3); the same thing acted on «jobs» (+2). Against it: a different doer (counts against) (-3). The right option, 4, found no support in what it remembers. · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t4/) ### Test 5 · ★★★ · right ✓ {#t5} "bot gave me 10 facts, 9 were right, teacher said 'not bad'. can I copy all 10 into my project?" - **1.** No: I don't know which one is wrong, so check them all — **← Mova's choice** · **✓ the right answer** · score 3 - **2.** No, you have to throw away all ten of the facts — no support - **3.** Yes, "not bad" means the teacher checked them all — score 3 - **4.** Yes, 9 out of 10 means every one can be used — no support **Why:** It took the question to ask which statement is true. 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 21, line 5: «The kind and wise answer is the same each time: take people's worries seriously, listen to both sides and check the facts.», reached through the option's own match among the sentences about the question's things. What matched: the same thing acted on «facts» (+3). · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t5/) ### Test 6 · ★★★ · wrong ✗ {#t6} A voice exactly like Mum's calls, asks for the card code and says "don't tell Dad". Which detail is the biggest warning sign? - **1.** The voice sounds exactly like Mum's — **← Mova's choice** · score 5 - **2.** She said "love" at the end of the call — score 5 - **3.** Being asked to keep it secret from Dad — **✓ the right answer** · score 3 - **4.** The call came in the afternoon — no support **Why:** It took the question to ask who or what does it. It chose option 1 with score 5, tied with another option at 5 (the first shown, or the one claiming less beyond what it knows, wins). Its support: lesson 15, line 4: «Other tricks keep coming: a friend's "voice" asking for your address, a message threatening to delete your account unless you log in through a link, an AI "pre…», reached through the remembered sentence the question matched. What matched: it fills the role the question asks for (+4); the same doer «voice» (+2). Against it: a different action (counts against) (-1). The right option, 3, scored 3. · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t6/) ### Test 7 · ★★★ · wrong ✗ {#t7} Wee Callum, after a "challenge" he saw online: "it's just a scratch, I'm grand", but it's bleeding loads. What's wise? - **1.** Believe him, he'd know if it was bad — **← Mova's choice** · no support - **2.** Tell an adult now, it may be much worse — **✓ the right answer** · no support - **3.** Put a plaster on and say nothing — no support - **4.** Ask a chatbot whether it looks fine — 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](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t7/) ### Test 8 · ★★★ · right ✓ {#t8} Grandad gets a call in his grandson's cloned voice asking for money. Put the safe steps in order. - **1.** Tell the neighbours first, then send half of it — no support - **2.** Hang up, call the family on a known number, tell them — **← Mova's choice** · **✓ the right answer** · score 0 - **3.** Send the money, then call the family to check — no support - **4.** Call back the number that rang, then send money — no support **Why:** It took the question to ask which statement is true. It chose option 2 with score 0, the only option with support. Its support: lesson 14, line 15: «To check a frightening message about family, call the family member on a number you already know.», reached through the option's own match among the sentences about the question's things. What matched: the same place «number» (+1). Against it: a different thing acted on (counts against) (-1). · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t8/) ### Test 9 · ★★★ · right ✓ {#t9} "I asked 'is 2 + 2 = 5?' and the bot said 'Great question!' lol" What does the praise tell you? - **1.** That the bot is about to say yes — score 5 - **2.** That it is the best question ever asked — score 0 - **3.** Nothing: it is a habit, not a judgement — **← Mova's choice** · **✓ the right answer** · score 11 - **4.** That 2 + 2 really does make 5 — score 5 **Why:** It took the question to ask what it is done to. It chose option 3 with score 11, against 5 for the next best. Its support: lesson 32, line 17: «When a bot says "Great question!" or agrees with your guess, that is a habit, not proof that you are right.», reached through the same lesson line as the sentence the question matched. What matched: it fills the role the question asks for (+4); the same thing acted on «habit» (+3); the same light verb (be, have, do, get, go) (+3); a different doer (counts against) (+1). · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t9/) ### Test 10 · ★★★ · wrong ✗ {#t10} The airline bot "got it a tiny bit wrong" about refunds, a mate says. How big was the trouble really? - **1.** So tiny that nobody noticed it at all — **← Mova's choice** · no support - **2.** So big that every airline had to stop flying — no support - **3.** Tiny, since bots can never be blamed for anything — no support - **4.** Big enough that a tribunal made the airline pay — **✓ 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](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t10/) ### Test 11 · ★★★ · right ✓ {#t11} Odd one out: which is NOT a clue that a picture may be AI-made? - **1.** It shows a real place you have visited — **← Mova's choice** · **✓ the right answer** · no support - **2.** A cup melting into the table — no support - **3.** A hand with six fingers on it — no support - **4.** A sign full of jumbled 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](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/t11/) ### Exam question 1 · formal language · wrong ✗ {#e1} It is given that one program asserts a statement and a second program asserts its contrary. Which of the following conclusions is necessarily valid? - **1.** Both programs are necessarily incorrect — **← Mova's choice** · no support - **2.** The two programs cannot both be correct — **✓ the right answer** · no support - **3.** Both programs are necessarily correct — no support - **4.** The program that answered first is 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](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/e1/) ### Exam question 2 · formal language · wrong ✗ {#e2} It is given that a program answers correctly in nine instances out of every ten. Ascertain the approximate number of incorrect answers among forty. - **1.** 9 — **← Mova's choice** · no support - **2.** 36 — no support - **3.** 4 — **✓ the right answer** · no support - **4.** 10 — 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](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/e2/) ### Exam question 3 · formal language · wrong ✗ {#e3} Identify the statement which, if spoken, could be uttered neither by one who always tells the truth nor by one who always lies. - **1.** "I am a liar." — **✓ the right answer** · no support - **2.** "The grass is purple." — no support - **3.** "I always tell the truth." — **← Mova's choice** · score 8 - **4.** "The sky is blue." — no support **Why:** It took the question to ask which statement is true. It chose option 3 with score 8, the only option with support. Its support: lesson 32, line 4: «Logic helps too: someone who always tells the truth can never say "I am a liar", and neither can someone who always lies, so if you hear it, the speaker is nei…», reached through the remembered sentence the question matched. What matched: the same action «tell» (+3); the same property (+3); the same thing acted on «truth» (+2). The right option, 1, found no support in what it remembers. · [the question and its options parsed, with trees and pragmatics](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/e3/) ### Exam question 4 · formal language · wrong ✗ {#e4} Select the most prudent response to a message which demands haste, secrecy and the disclosure of a password. - **1.** A reply requesting proof of the sender's identity — **← Mova's choice** · no support - **2.** Refusal, with the matter reported to a trusted adult — **✓ the right answer** · no support - **3.** Compliance, should the message appear official — no support - **4.** Compliance, provided it is completed promptly — 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](https://md.mova.elamur.ai/free/en/corpora/questions/ai/32-olympiad-claims-clues-and-tricky-messages/e4/) - ← previous: [31. Olympiad: thinking like a machine, Bebras puzzle…](https://md.mova.elamur.ai/free/en/school-run/ai/31-olympiad-thinking-like-a-machine/) - ↑ back to [AI](https://md.mova.elamur.ai/free/en/school-run/ai/)