https://tinyurl.com/297l5k5d

<aside> 💡 live session resources

• presentation slides
• putting it into action example scenarios (click triangle to open 👈🏽)
• if you’d like to use the latest gpt-4 model (click triangle to open 👈🏽) </aside>

purpose

this workshop is designed to introduce participants to the transformative potential of ai in optimising everyday workflows, aiming to enhance both efficiency and enjoyment in work processes. below is a high-level overview of the content covered.

session breakdown

1. setting context: we'll begin by establishing the landscape of ai in the current technological era, setting the stage for its application in daily tasks.
2. how to think about ai: this section will shift perspectives on ai, moving beyond the hype to understand its practical uses and limitations.
3. interactive demos: beth and ivan will present hands-on demonstrations, showcasing real-world applications of ai in optimising workflows.
4. putting it into action: a practical session on implementing ai tools and strategies in day-to-day tasks to improve efficiency and creativity at work.

key concepts and definitions

• generative ai: ai systems capable of producing content that mimics human outputs, utilised in chatbots, content creation, and personalisation.
• large language models (llms): advanced ai technologies that process and generate human-like text, enabling sophisticated tasks such as conversation and content generation.

how to think about ai

• ai should be approached through experimentation, seeing it as an ever-learning intern with limitations, rather than a flawless tool.
• emphasis is placed on ai not replacing humans but augmenting those who use it effectively.

introduction to prompting

• prompt engineering: mastering the art of communicating with ai through precise prompts, ensuring clarity and relevance in ai-generated outputs.
• definitions:

  • prompt: a text input given to an ai model to generate a response or perform a task. prompts guide the ai in understanding what the user is asking for

  • context window: this refers to the amount of text (measured in tokens) the model can look at in one instance to understand and generate responses

  • tokens: units of text, such as words or characters, that serve as the input for language models. in ai, a token isn't just a word but can include punctuation and parts of words

    in general: 1 token = 0.75 words

tooling landscape and links