Appendix: Common Traps (Master List)

Chapter 0: What AI Actually Is

• Treating AI outputs as truth
• Assuming AI understands context
• "It works on my test set, ship it!"
• Anthropomorphizing the model

Chapter 1: Python & Data

• Not looking at your data
• Trusting data providers
• Ignoring missing data patterns
• Not versioning data

Chapter 2: Math You Can't Escape

• Memorizing formulas without understanding
• Getting stuck in math rabbit holes
• Skipping linear algebra
• Treating probability as just counting

Chapter 3: Classical ML

• Not using cross-validation
• Tuning hyperparameters on the test set
• Ignoring class imbalance
• Forgetting about feature scaling

Chapter 4: Neural Networks

• Not normalizing inputs
• Using sigmoid for hidden layers
• Not shuffling data
• Forgetting to set model to eval mode
• Not checking for NaNs

Chapter 5: Transformers & LLMs

• Trusting LLM outputs without verification
• Using LLMs for tasks requiring reasoning
• Ignoring cost
• Not handling edge cases

Chapter 6: Modern AI Systems

• Over-relying on LLMs
• Not versioning prompts
• Ignoring latency
• No fallback logic

Chapter 7: Production AI

• Deploying and forgetting
• Optimizing for accuracy alone
• Not planning for retraining
• Adding AI because it's trendy

---