What You'll Learn
Prompt Engineering is a cutting-edge course designed for those who wish to master the art of interacting with and manipulating large language models. Through a series of workshops, participants will learn to create complex prompts, develop benchmarks, jailbreak models, automate conversations, and much more. The course emphasizes practical skills alongside theoretical knowledge, preparing students for advanced applications in AI.
Course Schedule
Week 1 2 sessions
Complex Prompts and Benchmarks
Develop a complex prompt and rubric for artifacts you commonly produce with AI. Develop a benchmark to test a prompt or prompt template. Use Self-consistency to improve model performance
Jailbreaks
Jailbreak a large language model out of its alignment guidance. Review jailbreaking techniques, practice them with some jailbreaking games. Add red-team prompts to your benchmark from Workshop 1
Week 2 2 sessions
Thought Architectures and Augmented Skills
Define, Write, and Deploy an entire application with a large language model. Decompose the above process into a Swarm of Agents
Tools
Use (code or) no-code tools to automate actions a large language model can take. Use (code or) no-code tools to trigger a large language model on a schedule
Week 3 2 sessions
Society of Mind
Host a conversation between multiple personas using a large language model. Decompose an agent into a series of smaller agents. Use Autogen to host a conversation between an actor and a critic
Autogen
Automatically host a conversation between multiple personas using a large language model. Re-Implement the SDLC from the third workshop using an agent hierarchy. Implement a multi-agent swarm
Week 4 2 sessions
Swarm Architecture
Implement Actor-Critic using Autogen. Implement a multi-stage swarm using Autogen. Implement Code Execution in Autogen
Alignment
Align a large language model's outputs to human values using prompt engineering techniques according to state-of-the-art research
Week 5 2 sessions
Meta-languages & Meta Narratives
Develop a metalanguage to allow a language model to reason at a symbolic level about a specific problem domain. Develop a metalanguage to allow for narrative design that can be held in available conversational context windows, allowing for the generation of novels and longer-form objects
Final Project
Integration and application of learned skills.
Week 6 1 session
Flexible Session
Flexible session for overflow or additional content.
All times shown in Pacific Time (PT)
Who Is This Course For
Professionals and enthusiasts with a foundational understanding of large language models looking to expand their skill set in prompt engineering and AI interaction.
Join the Course
Pay what you can - accessible learning for all
We use a suggested price to prevent abuse, but if you need a larger discount, email us at liz@themultiverse.school. We offer 100% scholarships - no one is turned away for lack of funds.
Want to schedule this course for your team?
Contact us: liz@themultiverse.school