Common Mistakes

Antipatterns that slow you down or cause problems.

1. The "Just Make It Work" Trap

Problem: Accepting AI code without understanding it.

Fix:

• Read every function
• Ask AI to explain unclear parts
• Add comments for complex logic

2. The Infinite Loop

Problem: AI keeps generating similar wrong solutions.

Signs:

• Same error keeps appearing
• AI apologizes and makes the same mistake
• You've been at this for 20 minutes

Fix:

• Stop and rethink your approach
• Provide more constraints
• Start a new chat
• Write the tricky part yourself

3. Over-Engineering

Problem: AI loves adding abstractions you don't need.

Fix: Explicitly ask for simple solutions:

"Give me the simplest possible implementation. 
No abstractions. I can refactor later if needed."

4. Dependency Bloat

Problem: AI adds npm packages for things you could do in 10 lines.

import { formatDate } from 'date-fns';
import { debounce } from 'lodash';
import { v4 as uuid } from 'uuid';

Fix:

• Ask: "Can this be done without adding a dependency?"
• Review every import from external packages
• Each dependency = security risk + maintenance burden

5. Single Responsibility Violations

Problem: AI creates god-functions that do too much.

// ❌ AI might generate this monolith
function handleUserRegistration(data) {
  // validate, hash password, save to db, 
  // send email, log analytics...
  // 200 lines of everything
}
 
// ✅ What you want
function validateRegistrationData(data) { /* ... */ }
function hashPassword(password) { /* ... */ }
function saveUser(userData) { /* ... */ }
function sendWelcomeEmail(user) { /* ... */ }

Fix: Ask for focused functions:

"Split this into smaller functions. Each function should do ONE thing."

6. Context Contamination

Problem: Long chats where AI "forgets" early decisions.

Fix:

• Summarize decisions periodically
• Reference files directly
• Start fresh for new features

7. The Copy-Paste Cascade

Problem: Copy-pasting AI suggestions without reading.

Fix: Read every line. Trust but verify.