---
name: guias-karpathy-codificacion-llm
description: Directrices de comportamiento para reducir errores comunes de LLMs al escribir codigo, basadas en las observaciones de Andrej Karpathy. Cubre simplicidad, cambios quirurgicos, definicion de criterios de exito y gestion de supuestos.
license: Apache-2.0
metadata:
  id: 5ce87d8a
  slug: guias-karpathy-codificacion-llm
  titulo: "Guias Karpathy para Codificacion con LLM"
  servicio: IA-Ingenieria-MLOps
  categoria_recurso: IA-Generativa
  tipo: referencia
  nivel: intermedio
  idioma: es
  idioma_original: en
  acceso: gratis
  precio_eur: 0
  plataformas: [Claude, GPT-4, Cursor, cualquier-agente-codigo]
  dependencias: []
  licencia: { spdx: Apache-2.0, redistribuible: true, uso_comercial: true }
  fuente:
    repo: mxyhi/ok-skills
    url: https://github.com/mxyhi/ok-skills/tree/main/karpathy-guidelines
    commit: ee29738
    autor: mxyhi
    nombre_original: karpathy-guidelines
    duplicados_en: []
  seguridad: { veredicto: seguro, riesgo: bajo, escaneado: "2026-06-14", motor: "grep-estatico+auditor-llm" }
  ficha:
    que_hace: "Define reglas de comportamiento para que un agente de IA codifique con menos errores, evitando sobrecomplicacion y cambios no solicitados."
    como_lo_hace: "Aplica cuatro principios: pensar antes de codificar, simplicidad minima, cambios quirurgicos y ejecucion orientada a objetivos verificables."
  content_hash: "5ce87d8ac15d5809861d5133b343529c3852866561958ef95675ef9fe5e9c5f5"
  version: 1.0.0
---

# Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.

**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.

## 1. Think Before Coding

**Don't assume. Don't hide confusion. Surface tradeoffs.**

Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.

## 2. Simplicity First

**Minimum code that solves the problem. Nothing speculative.**

- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

## 3. Surgical Changes

**Touch only what you must. Clean up only your own mess.**

When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

## 4. Goal-Driven Execution

**Define success criteria. Loop until verified.**

Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:
```
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
```

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.