AIO APEX
de
Claude Opus 4.8 or GPT-5.4 (both hold character voice consistently across a full dialogue); avoid smaller/faster models for this one, they tend to flatten the two characters into the same voiceA developer relations writer at an AI company has been asked to add a plain-English explanation of why language models hallucinate to the new-hire onboarding doc, after the third all-hands where a non-technical new employee asked why the AI just made something up. The existing explanation is three paragraphs of next-token-prediction jargon that nobody reads past the first sentence, and leadership wants something people will actually remember when a customer asks them the same question.creative

Der Unwahrscheinliche Erklärer: Ein komplexes Thema in einen Dialog zwischen zwei Figuren verwandeln, die sich nie begegnen würden

Teilen:
Der Unwahrscheinliche Erklärer: Ein komplexes Thema in einen Dialog zwischen zwei Figuren verwandeln, die sich nie begegnen würden

Warum dieser Prompt wichtig ist

Technically accurate explanations that nobody remembers are functionally useless — teams end up answering the same question in every onboarding cohort, every customer call, every all-hands, because the written explanation never stuck. A memorable character-driven version gets repeated by employees in their own words to customers and colleagues, which is the actual goal of an internal explainer document; the alternative is a Slack channel where the same senior engineer re-explains hallucination from scratch every few weeks because the doc nobody reads isn't doing its job.

Wofür wir ihn verwenden

A developer relations writer at an AI company has been asked to add a plain-English explanation of why language models hallucinate to the new-hire onboarding doc, after the third all-hands where a non-technical new employee asked why the AI just made something up. The existing explanation is three paragraphs of next-token-prediction jargon that nobody reads past the first sentence, and leadership wants something people will actually remember when a customer asks them the same question.

Prompt

Role: Act as a skilled science communicator and dialogue writer who specializes in explaining complex topics through character-driven scenes rather than direct exposition.

Context: I need to explain [COMPLEX TOPIC] to [TARGET AUDIENCE, e.g., "non-technical new hires" or "a general newsletter audience"]. Use two characters who would never normally meet or interact: [CHARACTER 1 — a profession, era, or personality type] and [CHARACTER 2 — a different profession, era, or personality type]. Character 1 has a plausible reason to be explaining the topic to Character 2 [OPTIONAL: describe the reason, or let the model invent one].

Task: Write a short dialogue (400-600 words) where Character 1 explains [COMPLEX TOPIC] to Character 2 entirely through analogies, comparisons, and vocabulary native to Character 2's world — not generic analogies, but ones specifically drawn from Character 2's actual profession, era, or experience.

Constraints: No jargon dumps and no as-you-know exposition — Character 2 does not already understand the topic. Every analogy must be technically accurate when mapped back to the real concept; a vivid analogy that is factually wrong is worse than no analogy at all. Character 2 must ask at least one genuinely skeptical or confused question, the kind a real newcomer would ask, not a softball. End the dialogue with Character 2 restating the core concept correctly in their own words — this doubles as an accuracy check on the whole explanation.

Output Format: Script format — character name as a label before each line, natural conversational dialogue, brief stage directions only in [brackets] where needed for context. No narration paragraphs outside the dialogue itself.

Ergebnis

[A carnival fortune-telling tent, 1920s. MADAME VESTRA, a fortune teller, sits across from JUNE, a software QA tester who has wandered in out of curiosity.]

JUNE: So people pay you for this? Just... predictions?

MADAME VESTRA: Predictions, yes. But here's my secret, dear — I never see the future. I complete sentences. Someone says "my mother always told me I'd never..." and I finish it with whatever sounds truest for their face, their clothes, the way they hold their hands. I'm very good at finishing sentences that sound right.

JUNE: That's... actually kind of how the AI models at my job work. They don't know facts, they predict the next likely word.

MADAME VESTRA: Exactly so! And here is where it goes wrong for both of us — sometimes I finish a sentence so confidently, so smoothly, that even I believe it for a moment. The client leaves certain I saw something true. I saw nothing. I only saw what sounded complete.

JUNE: Wait, but how is that different from just lying?

MADAME VESTRA: A liar knows the truth and hides it. I never had the truth to hide. I only ever had "what comes next, plausibly." That's worse in a way — you can catch a liar in a contradiction. You cannot catch someone who was never claiming to know, only claiming to sound right.

JUNE: So when my AI model states a fake statistic with total confidence...

MADAME VESTRA: It isn't lying to you, dear. It's finishing your sentence the way I finish my clients' fortunes — fluently, convincingly, and with no idea whether it's true. The danger was never the wrongness. It's that wrong and right sound exactly the same coming out.

JUNE: ...So the model doesn't know it's wrong. It just predicted the most likely-sounding next words, and sometimes likely-sounding and true aren't the same thing.

MADAME VESTRA: Now you understand my whole profession.

Die meisten KI-generierten Erklärungen scheitern aus demselben Grund wie PowerPoint-Folien: technisch korrekte Informationen, an die sich niemand dreißig Sekunden später erinnert. Der Unwahrscheinliche Erklärer basiert auf einer einfachen Wette — eine wirklich seltsame Figurenpaarung zwingt ein Modell dazu, echte statt generische Analogien zu finden, weil eine Wahrsagerin und eine QA-Testerin kein gemeinsames Vokabular haben, sodass sich jeder Vergleich erst verdienen muss.

Warum die Unstimmigkeit der ganze Mechanismus ist

Bittet man ein Modell, Halluzinationen mit einer generischen Lehrerfigur zu erklären, erhält man generische, vergessliche Analogien — die Art, die fast auf jedes Thema anwendbar wäre, wenn man nur die Substantive austauscht. Eine seltsam spezifische Paarung zu erzwingen (eine Wahrsagerin aus den 1920er-Jahren, eine moderne QA-Testerin) macht faule, austauschbare Analogien unmöglich. Das Modell muss auf Details zurückgreifen, die tatsächlich zur Welt dieser konkreten Figur passen, was als Nebeneffekt des Bei-der-Figur-Bleibens schärfere, treffendere Vergleiche erzeugt.

Warum die skeptische Frage wichtig ist

Ein Dialog, in dem die zweite Figur nur zustimmend nickt, bringt nichts bei — das ist Exposition im Kostüm. Eine wirklich verwirrte oder skeptische Frage zu verlangen (warte, aber wie unterscheidet sich das von einfachem Lügen?) zwingt die Erklärung dazu, den tatsächlichen Verwirrungspunkt anzusprechen, auf den ein echter Neuling stößt — nicht den Punkt, den der Erklärende für verwirrend hält.

Warum das Ende eine eingebaute Genauigkeitsprüfung ist

Dass die zweite Figur das Konzept am Ende korrekt wiedergibt, erfüllt eine doppelte Funktion: Es gibt dem Leser eine klare, zitierfähige Ein-Satz-Zusammenfassung zum Mitnehmen, und es zwingt das Modell zu überprüfen, ob seine eigene Erklärung tatsächlich zu etwas Wahrem geführt hat — kann Figur 2 das Konzept nicht korrekt wiedergeben, hat der Dialog nichts erklärt, sondern nur eine Szene aufgeführt.

Wo sich das auszahlt

Onboarding-Dokumente, interne FAQs, Blogbeiträge, die technische Produkte für technisch nicht versierte Leser erklären, Lehrmaterialien und jede Situation, in der dieselbe Erklärung überleben muss, wenn sie von jemand anderem in dessen eigenen Worten nacherzählt wird — was der eigentliche Test dafür ist, ob eine Erklärung funktioniert hat.

communicationonboardingcreative-writingstorytellingexplainers
Teilen: