Fine-tuning vs. prompting
The idea: Same task via a better prompt vs. a few adapter weights (LoRA intuition).
What you'll be able to do: You can explain when to prompt vs fine-tune (LoRA) and the cost trade-off.
The problem it solves: When do you change the weights vs. change the prompt?
Builds on: Gradient descent: rolling downhill
← RLHF / post-training · Next: Hallucination →
All lessons