From the course: Prompt Engineering with LangChain
Join today to access over 24,800 courses taught by industry experts.
Prompt basics
From the course: Prompt Engineering with LangChain
Prompt basics
- [Instructor] In the early days of language models, you needed a different model for every language task. Those days are gone. Transformers and transfer learning have made things much simpler. You have one model that is like a Swiss Army knife that can be used for various language tasks. You give this model a prompt, which essentially is just a string of text, and the model will give you a answer. The better your prompt, the better the answer. So what's the big deal with prompts? Well, it is a phenomena called in-context learning. And this refers to methods for steering an LLM's behavior towards your desired outcome without updating the model weights. This approach is rooted in practical testing, and the success of various prompt strategies can differ significantly across models. This means that it's up to you to hack around and play around with prompts to see which one is going to work for your task. As a result, this means that there is extensive trial and error, along with some…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.