Highlights
Mastering Prompt Engineering for GPT Training:
- Introducing Prompt Engineering
- Understand the principles of Large Language Models (LLMs),
- Define and design effective prompts using strategies like specificity
- Learn more about chaining prompts for more refined outputs.
- Employ advanced prompt design techniques, including use of delimiters
- Apply techniques to mitigate common LLM issues
- Utilize various prompting methods, including zero-shot, one-shot, and few-shot prompting
- Design and implement complex prompt strategies such as Chain of Thoughts (CoT) and persona-based prompts,
- Expanding the utility and adaptability of LLMs for diverse use-cases.
Course Details
Introducing Prompt Engineering
- What is prompt engineering and why is it important?
- Capabilities of ChatGPT tiers
- Key concepts in prompt engineering
- Core components of a prompt: context, instructions, examples
- Demonstration and discussion of prompt engineering examples
Prompting is Not Search
- Key differences from search queries
- Examples of effective prompts
Overview of Prompting Approaches
- A Taxonomy of Prompting: Reductive, transformative, and generative
Basic Prompt Improvements
- Importance of writing clear and unambiguous prompts
- Providing context and delimiters
- Structuring complex prompts
- Explaining ambiguous concepts and providing definitions
- Breaking complex prompts into simple steps or multiple prompts
- Strategies for prompt improvement: Iterating, refining, and chaining prompts
- Allowing the LLM to demonstrate reasoning and express uncertainty
Limitations of Language Models
- Description, examples, and mitigation strategies for common LLM issues
- Hallucinations and Mitigation Strategies
- Bias and Mitigation Strategies
Understanding Language Models
- Introduction to LLMs: Types and characteristics, including transformer-based neural nets and Reinforcement Learning from Human Feedback (RLHF)
- Attention mechanisms
- Sequence prediction, prompt length, and the context window
- Characteristics and limitations of LLMs: always generates output, tendency to please people, hallucination, mathematical limitations, data training limitations, and conversation isolation
Giving Examples
- When to use zero-shot, one-shot, few-shot prompts
Customising the Output
- Using templates effectively
- Using delimiters to distinguish the data from the prompt
- Asking for Structured Output e.g. JSON, XML, HTML etc
Role-Based Prompting
- Assigning roles for better responses
- Use case examples
Multiple Perspectives
- Simulating different viewpoints
- Improving decision making by taking into account multiple perspectives
- Converging on a concensus
Adding Personality
- Why add personality?
- Defining roles and personality traits
- Including anecdotes
Reasoning
- Improving reasoning capabilities
- Working with maths
Scenarios and Use Cases
- Data analysis example prompt
- Designing prompts for text summarization, question answering, and creative writing
- Writing an Email
- Generating business reports
Additional Topics
- More business use cases
- Leveraging custom GPTs
Conclusions
- Where to go from here
- Further resources
- Course wrap-up
Who should attend
This course is suitable if you have had some exposure to ChatGPT and would like to deepen your skills.
You can gain benefit from the course whether or not you have programming experience.
Feedback
4.8 out of 5 average
"Our tailored course provided a well rounded introduction and also covered some intermediate level topics that we needed to know. Clive gave us some best practice ideas and tips to take away. Fast paced but the instructor never lost any of the delegates"
Brian Leek, Data Analyst, May 2022
“JBI did a great job of customizing their syllabus to suit our business needs and also bringing our team up to speed on the current best practices. Our teams varied widely in terms of experience and the Instructor handled this particularly well - very impressive”
Brian F, Team Lead, RBS, Data Analysis Course, 20 April 2022
