Here are some different ways to build applications based on LLMs, in increasing order of cost/complexity:

• Prompting. Giving a pretrained LLM instructions lets you build a prototype in minutes or hours without a training set. Earlier this year, I saw a lot of people start experimenting with prompting, and that momentum continues unabated. Several of our short courses teach best practices for this approach.
• One-shot or few-shot prompting. In addition to a prompt, giving the LLM a handful of examples of how to carry out a task — the input and the desired output — sometimes yields better results. 
• Fine-tuning. An LLM that has been pretrained on a lot of text can be fine-tuned to your task by training it further on a small dataset of your own. The tools for fine-tuning are maturing, making it accessible to more developers.
• Pretraining. Pretraining your own LLM from scratch takes a lot of resources, so very few teams do it. In addition to general-purpose models pretrained on diverse topics, this approach has led to specialized models like BloombergGPT, which knows about finance, and Med-PaLM 2, which is focused on medicine.

Full article here at The Batch