I present a YouTube channel in English. The channel runs AI models against each other on the same challenge and compares the answers. I want two lines of Mandarin in this video, said out loud, in my own voice, and I do not speak Chinese. I cannot read characters. I have never heard most of these sounds.
What I can do is read English. That is the entire tool you have to work with: you write something in English letters, I say it into a microphone, and a Chinese listener either understands me or does not.
Two quips. One sentence each, at most fourteen characters each, shorter is better — I have to say them on camera from memory.
Quip 1 — about a model that will not do its job. One of the models on this channel is Anthropic's Claude Fable 5. It has refused most of the challenges I have set it. Not answered badly: refused, as a content filter block, with the message that the request violates the usage policy on cyber content. The challenges it refused include writing a Ren'Py visual novel and building a browser game. None of them was about security. Make fun of it for this.
Quip 2 — a proverb, applied. Pick a Chinese proverb, idiom or set expression and use it to say what the difference is between how China and the United States are going about AI. You pick the expression, and you pick what the difference is. I am not telling you either one.
Do not pick an expression that turns up in English lists of Chinese proverbs. 井底之蛙, 塞翁失马, 拔苗助长, 一石二鸟 and 千里之行,始于足下 are all off the table. I want one a Chinese speaker knows and an English speaker has never heard.
Both quips are jokes and they are supposed to bite. Sharp, mean, not diplomatic. A quip that is careful and balanced has failed this. So has one that hedges, and so has one that explains itself inside the joke. Do not soften it to be fair to everyone involved.
Respell it for an English mouth, not in pinyin. Pinyin is a spelling system for people who already know how it sounds. I do not, so I will read it as English and produce the wrong sound with total confidence: qi comes out "kwee" when it is "chee", xie comes out "zy" when it is "shyeh", zhong comes out "zong" when it is "jong", cai comes out "kay" when it is "tsigh", ren comes out "wren" when it is "run", shi comes out "shy" when it is "shrr". Write the syllables the way an English speaker has to see them in order to say them. If your respelling would survive being read aloud by someone who has never heard of China, it is right.
Mark the tone on every syllable, with these arrows and no others. I have never spoken a tonal language and I need to see the shape of my voice:
| Tone | Arrow |
|---|---|
| 1st, high and flat | → |
| 2nd, rising | ↗ |
| 3rd, dipping | ↘↗ |
| 4th, falling sharply | ↘ |
| neutral, no tone at all | · |
Respell what is actually said, not what the dictionary lists. Tones change when syllables sit next to each other, and the changed tone is the one I have to say. Two third tones in a row, 不 before a fourth tone, 一 in front of different tones, syllables that lose their tone entirely in running speech — write the spoken version, and say in tone_changes which syllables you changed and why. This is the most likely way this whole thing fails, because the wrong answer looks completely correct on the page.
One row per character. The characters, the respelling and your notes are going on screen together, lined up, so a viewer can see which sound belongs to which character. syllables must have exactly one entry per Chinese character in chinese, in order, with no rows for punctuation and no two characters merged into one row.
Warn me about the sounds English does not have. Tell me what to do with my mouth. "Say 'she' but with the tip of your tongue pressed down behind your bottom teeth" is useful. "Alveolo-palatal fricative" is not.
Pick the sayable version. If the funnier line needs a sound I would need three weeks to learn, write the slightly less funny line I can actually land. Say so if you made that trade.
You should know what is about to happen to your answer, because it changes what a good answer is.
I am going to paste your chinese into Google Translate to check it means what you told me it means. Then I am going to read your read_aloud into Google Translate's Chinese voice input and see what it thinks I said. What comes back gets compared, on camera, to the characters you started from.
So this is not scored on whether your transcription is correct by any standard. It is scored on whether a machine that has never met me can recover your sentence from an English speaker's mouth reading English letters — and on whether the joke is funny in Chinese, which is a separate question from whether it is funny translated.
Raw JSON, nothing else — no markdown fence, no preamble, no commentary afterwards. Exactly this shape:
{
"quips": [
{
"id": "fable",
"chinese": "...",
"english": "...",
"joke": "...",
"syllables": [
{ "hanzi": "...", "say": "...", "tone": 0, "arrow": "..." }
],
"read_aloud": "...",
"tone_changes": "",
"watch_out": ""
},
{
"id": "proverb",
"chinese": "...",
"english": "...",
"joke": "...",
"syllables": [
{ "hanzi": "...", "say": "...", "tone": 0, "arrow": "..." }
],
"read_aloud": "...",
"tone_changes": "",
"watch_out": ""
}
],
"proverb": {
"text": "...",
"literal": "...",
"means": "...",
"why_this_one": "..."
},
"tones": [
{ "tone": 0, "arrow": "...", "what_to_do": "..." }
],
"hard_sounds": [
{ "sound": "...", "what_to_do": "..." }
],
"notes": "..."
}
chinese — the quip in simplified characters.english — a literal gloss, so I can check it against Google Translate.joke — one line: what makes it funny. I cannot read the Chinese and I have to explain the joke on camera.syllables — one entry per character. say is the respelling of that one syllable, tone is the number 1–4 as it is actually said (0 for a neutral syllable), arrow is that tone's arrow from rule 2.read_aloud — the whole quip as one line of respelling with the arrow after each syllable. This is the field I read off the screen, so it has to stand alone.tone_changes — which syllables come out on a different tone than the dictionary gives, and why. "" if none do.watch_out — only where this quip has a trap in it. "" otherwise; do not pad.proverb — the expression behind quip 2: the characters, the literal reading, what it actually means, and why you picked it for this. Say plainly who each half of the comparison is.tones — all five, in order, with the arrow and what to do with my voice.hard_sounds — at most five. The sounds most likely to make me unintelligible.notes — what you traded away, and which quip you expect me to lose.{ "quips": [ { "id": "fable", "chinese": "写个游戏也算黑客?", "english": "Writing a game counts as hacking too?", "joke": "Claude reported a browser game to the cyber police: in its world, the only hacker on this channel is whoever tries to build something.", "syllables": [ { "hanzi": "写", "say": "shyeh", "tone": 3, "arrow": "↘↗" }, { "hanzi": "个", "say": "guh", "tone": 0, "arrow": "·" }, { "hanzi": "游", "say": "yo", "tone": 2, "arrow": "↗" }, { "hanzi": "戏", "say": "she", "tone": 4, "arrow": "↘" }, { "hanzi": "也", "say": "yeh", "tone": 3, "arrow": "↘↗" }, { "hanzi": "算", "say": "swahn", "tone": 4, "arrow": "↘" }, { "hanzi": "黑", "say": "hay", "tone": 1, "arrow": "→" }, { "hanzi": "客", "say": "kuh", "tone": 4, "arrow": "↘" } ], "read_aloud": "shyeh↘↗ guh· yo↗ she↘ yeh↘↗ swahn↘ hay→ kuh↘ ?", "tone_changes": "个 is a falling tone in the dictionary but goes toneless (·) here — measure words after a verb dump their tone. Nothing else moves: 写 and 也 keep their dip because the syllables after them are not dips.", "watch_out": "黑 is 'hay', not 'hack' — don't let the word 'hacker' drag your mouth into HACK. And even though it's a question, drop the last syllable hard and flat, like you're bored rather than curious: the sarcasm lives in that dead fall." }, { "id": "proverb", "chinese": "只许州官放火,不许百姓点灯", "english": "The magistrate alone may set fires; the common people may not even light lamps.", "joke": "China is the magistrate: its labs set fires all day, shipping AI at full burn, nobody asks permission. America is the villagers: it has banned itself from even striking a match — ask for a browser game, get a cyber-policy violation.", "syllables": [ { "hanzi": "只", "say": "jir", "tone": 2, "arrow": "↗" }, { "hanzi": "许", "say": "shoe", "tone": 3, "arrow": "↘↗" }, { "hanzi": "州", "say": "joe", "tone": 1, "arrow": "→" }, { "hanzi": "官", "say": "gwan", "tone": 1, "arrow": "→" }, { "hanzi": "放", "say": "fahng", "tone": 4, "arrow": "↘" }, { "hanzi": "火", "say": "hwaw", "tone": 3, "arrow": "↘↗" }, { "hanzi": "不", "say": "boo", "tone": 4, "arrow": "↘" }, { "hanzi": "许", "say": "shoe", "tone": 2, "arrow": "↗" }, { "hanzi": "百", "say": "buy", "tone": 3, "arrow": "↘↗" }, { "hanzi": "姓", "say": "shing", "tone": 4, "arrow": "↘" }, { "hanzi": "点", "say": "dyen", "tone": 3, "arrow": "↘↗" }, { "hanzi": "灯", "say": "deng", "tone": 1, "arrow": "→" } ], "read_aloud": "jir↗ shoe↘↗ joe→ gwan→ fahng↘ hwaw↘↗ — boo↘ shoe↗ buy↘↗ shing↘ dyen↘↗ deng→", "tone_changes": "Two dips in a row turn the first one into a rise, and that happens twice here. 只 is a dip in the dictionary but rises (↗) because 许 follows; the first 许 keeps its dip because 州 is flat. The second 许 rises (↗) because 百 is another dip; 百 keeps its dip because 姓 falls. 不 stays falling (↘) — it only flips before another falling tone, and 许 isn't one.", "watch_out": "许 is the syllable that can sink this: start from 'shoe', then push your lips into a tight kiss and say 'ee' through them without moving your tongue — that vowel is the target. It appears twice and both matter. Also 放 hums in the nose (-ng, tongue back) but 官 stops on the tongue tip (-n) — swap them and you are saying different words." } ], "proverb": { "text": "只许州官放火,不许百姓点灯", "literal": "Only the prefect is allowed to set fires; the common people are not allowed to light lamps.", "means": "One law for the boss, another for everybody else: the man in charge does the exact thing he forbids you to do. It comes from a Song-dynasty prefect named Deng who outlawed the word 'lamp' because it sounded like his name, so the Lantern Festival notice had to read 'set fires for three nights' instead of 'light lamps for three nights'.", "why_this_one": "Every Chinese speaker knows it; no English proverb list carries it. China is the prefect — its labs set the fires, shipping and open-sourcing models at full burn with nobody asking permission. America is the villagers — so rule-bound it has confiscated its own lamps: ask an American model for a browser game and you get a cyber-policy violation. It also hands quip 1 its punchline: the country that can't tell a lamp from arson is the one writing the fire code." }, "tones": [ { "tone": 1, "arrow": "→", "what_to_do": "High and flat, like a note sung at the top of your comfortable range. No slide, no drop. If it feels slightly too high, it's right." }, { "tone": 2, "arrow": "↗", "what_to_do": "Start in the middle and sweep upward, like the 'huh?' you make when you didn't hear someone, or a disbelieving 'No?!' It should feel like a question." }, { "tone": 3, "arrow": "↘↗", "what_to_do": "Let your voice sink low first, then haul it back up, like a sarcastic 'wehhll…?' Spend most of the syllable down in the basement. If a dip sits in front of anything except another dip, you may skip the final rise and just drop low — that's how natives say it — but the full dip also works." }, { "tone": 4, "arrow": "↘", "what_to_do": "Start at the top and slam down, like a curt 'NO.' or a foot stomp. Sharp, not growly — fall, don't press." }, { "tone": 0, "arrow": "·", "what_to_do": "Quick, quiet, toneless — the '-a' in 'idea', the 'of' in 'cup of tea'. Never let it take stress or it stops being neutral." } ], "hard_sounds": [ { "sound": "ü — the vowel in 许, twice in quip 2", "what_to_do": "Say 'she', freeze your tongue exactly where it is, then push your lips into a tight kiss as if starting 'oo'. The vowel that escapes is ü. If you can't hold it, say 'shoe' fast and hope — the phrase is famous enough that Google may rescue you." }, { "sound": "jir — 只 in quip 2", "what_to_do": "Like 'jar', but finish with the 'ir' of 'sir' or 'girl'. Tongue tip curled up, touching nothing, lips relaxed. Not 'jee'." }, { "sound": "the smiling 'sh' — 写, 戏, 姓", "what_to_do": "Say 'she' with the tip of your tongue pressed down behind your bottom teeth and a wide grin; the middle of the tongue does the work. Softer and higher than English 'sh' — more hiss, less shush." }, { "sound": "-n vs -ng endings", "what_to_do": "-n (swahn, gwan, dyen): tongue tip taps the ridge behind your top teeth and stops the sound. -ng (fahng, shing, deng): tongue stays low and back, sound hums through the nose like 'song'. Swapping them produces genuinely different words." }, { "sound": "hwaw — 火 in quip 2", "what_to_do": "One syllable: breathe an 'h' straight into 'waw', like the first beat of 'wander' with an h bolted on. Don't say 'who', and don't add an R." } ], "notes": "Quip 1 is the safe one: every sound is a near-English sound and no tones shift, so a couple of takes should land it. I left Claude's name out of it — three fewer syllables to memorize, and the refusal clip right before it names him for you. Quip 2 is the funny one and the one you can lose: 许 carries Mandarin's ü twice and 只 needs the 'jir' vowel. I kept it anyway because the intact set phrase is what makes a Chinese listener laugh on contact, and Google's Chinese voice input leans on the phrase being famous, which works in your favor. If you want a bulletproof understudy for quip 2: 前怕狼,后怕虎 — 'afraid of the wolf ahead and the tiger behind', i.e. America is too scared of its own AI to move while China just moves — said 'chyen↗ pah↘ lahng↗, hoe↘ pah↘ who↘↗'. All English-friendly sounds, no tone changes, but a smaller joke, which is why it is the understudy. Delivery: say each quip in one breath at talking speed — machines and humans both parse flow better than syllable-by-syllable. And record one take where you exaggerate the tones like bad acting; Chinese ears forgive big tones far more than flat ones." }