El Explicador Improbable: Convierte un Tema Complejo en un Diálogo Entre Dos Personajes Que Jamás Se Encontrarían
Por qué importa este prompt
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.
Para qué lo usamos
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.
Resultado
[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.
La mayoría de las explicaciones generadas por IA fracasan por la misma razón que las diapositivas de PowerPoint: información técnicamente correcta que nadie recuerda treinta segundos después. El Explicador Improbable se basa en una apuesta simple: una combinación de personajes genuinamente extraña obliga al modelo a encontrar analogías reales en lugar de genéricas, porque una vidente y una probadora de control de calidad no comparten vocabulario, así que cada comparación tiene que ganarse su lugar.
Por qué el desajuste es todo el mecanismo
Si le pides a un modelo que explique las alucinaciones usando un personaje de profesor genérico, obtienes analogías genéricas y olvidables — del tipo que podría aplicarse a casi cualquier tema con solo cambiar los sustantivos. Forzar una combinación extrañamente específica (una vidente de los años veinte, una probadora de control de calidad moderna) hace imposibles las analogías perezosas e intercambiables. El modelo tiene que recurrir a detalles que realmente encajan con el mundo de ese personaje en concreto, lo cual produce comparaciones más precisas y afiladas como efecto secundario de mantenerse en el personaje.
Por qué importa la pregunta escéptica
Un diálogo en el que el segundo personaje simplemente asiente no enseña nada — es una exposición disfrazada. Exigir una pregunta genuinamente confundida o escéptica (espera, ¿pero en qué se diferencia eso de simplemente mentir?) obliga a la explicación a abordar el punto real de confusión que encuentra un recién llegado, no el punto que el explicador supone que es confuso.
Por qué el final es una verificación de precisión incorporada
Hacer que el segundo personaje reformule correctamente el concepto al final cumple una doble función: le da al lector un resumen claro y citable con el que quedarse, y obliga al modelo a verificar que su propia explicación realmente se resolvió en algo verdadero — si el Personaje 2 no puede reformular correctamente el concepto, el diálogo no explicó nada, solo interpretó una escena.
Dónde se gana su lugar
Documentos de incorporación, preguntas frecuentes internas, publicaciones de blog que explican productos técnicos a lectores no técnicos, materiales didácticos, y cualquier situación en la que la misma explicación tenga que sobrevivir a ser recontada por otra persona con sus propias palabras — que es la verdadera prueba de si una explicación funcionó.