InternshipKey terms and common mistakes
The words you will hear in LLM Engineering & Fine-Tuning work and the mistakes that most often cost interns approvals.
Key terms
| Term | Meaning |
|---|---|
| Token | A small piece of text that a model reads and writes |
| Context window | The most tokens a model can handle in one request |
| Embedding | Numbers that represent the meaning of text |
| RAG | Retrieving relevant documents and adding them to the prompt |
| Fine-tuning | Further training a model on your own examples |
| LoRA | Training small adapter weights instead of the whole model |
| Quantization | Storing weights in fewer bits to save memory |
| Eval set | Fixed test cases used to measure answer quality |
Common mistakes to avoid
- Putting API keys in code or in the frontend.
- Changing prompts or models without re-running the evaluation set.
- Trusting model output without validating JSON or tool arguments.
- Fine-tuning when RAG or a better prompt would solve the problem.
- Leaving personal data in training files.
Want to go deeper? The free Generative AI & Prompt Engineering learning path has short modules, games and a certificate for each module.