Unraveling prompt engineering
Вставка
- Опубліковано 5 лют 2025
- On the face of things, prompting seems intuitive and straightforward. With that said, you'd be hard-pressed to find a developer who'll say that it's easy. This webinar will focus on unraveling the "art" of prompt engineering into best practices and methodologies.
Key topics
LLM compatibility: considerations in use case, task, model, infrastructure, and prompting selection and matching.
The much-overlooked basics of prompting: understanding model tendencies and biases, chaining, mega prompts, and multi-calls, and adhering to prompt formats.
Breakthroughs in prompting techniques: such as Chain-of-Though, Tree-of-Thoughts, Thought frameworks (React), and Chain-of-Density.
Bug-driven development for LLMs + some hands-on examples of prompt engineering best practices
Come with questions! But be advised that this is not an intro session to prompt engineering - we won't be covering basic prompt patterns and concepts such as zero-shot or temperature.
Advised pre-reading
Prompt Engineering Guide
Eight Prompt Engineering Templates
Design Patterns In Prompt Engineering
Presentation
go.superwise.a...
These are some of the best videos I've seen on this topic.
Great talk, your webinars are a wonderful source of information :)
great
Hm… the first speaker made it sound like you couldn’t use context outside of the user input without prompt chaining. This is not true. Otherwise, loved the talk !