All in One View

Content from Jargon Busting


Last updated on 2026-11-05 | Edit this page

Overview

Questions

  • How do you and other workshop participants feel about AI?
  • What terms, phrases, and concepts are you aware of but wish you understood better?

Objectives

After this episode, learners will be able to:

  • Compare their perspective on artificial intelligence with other participants’ as they begin the workshop.
  • Explain terms, phrases, and concepts associated with artificial intelligence.
  • Differentiate between these terms, phrases, and concepts.
  • Recognise that AI is a label applied to a wide variety of tools, techniques, and technologies.
Discussion

Temperature Check

Gather learners’ anonymous responses to the following questions, using a polling tool or by collecting sticky notes on a whiteboard/wall.

  1. Overall, how do you feel about artificial intelligence and the ways that people are using it? (Choose all that apply.)
    • confused
    • excited
    • frustrated or angry
    • relaxed
    • uninterested
    • worried or scared
    • something else
  2. Which of these statements most closely matches your own view of artificial intelligence right now?
  • it is going to change everything.
  • it is an over-hyped phase that will soon pass.
  • its impact will vary greatly from case to case.
  • I don’t know
  1. On average, how frequently do you use a generative AI chatbot (e.g. ChatGPT, Copilot, Gemini, Claude)?
  • many times per day
  • once per day
  • weekly
  • monthly
  • rarely
  • never
Discussion

Jargon Busting (30 minutes)

This exercise is an opportunity to gain a firmer grasp on some concepts related to (generative) artificial intelligence.

  1. Pair with a neighbor or form a small group. Decide who will take notes.
  2. Spend the first three to five minutes listing any terms, phrases, or ideas related to artificial intelligence that you’ve come across and perhaps feel you should understand better.
  3. Have the note-taker compile your list of terms, phrases, and ideas.
  4. Now in a larger group (or with everyone in the workshop) spend 10 to 15 minutes working together to try to explain what some of those terms, phrases, or ideas on your list mean.
  5. The instructor will collate terms and explanations on a whiteboard or Etherpad and facilitate a discussion about what we will cover today and where you can go for help on things we won’t cover.

We have found that some understanding of the technology behind generative AI tools is helpful when thinking about the ways they could be used. Without dwelling on technical details, the rest of this lesson will explore the central technology of generative AI: the large language model. We will discuss what these models do, how they are produced, and what is happening when you ask one to generate something. With a strengthened understanding of how these tools work, you will be better equipped to judge when and how to use them in your work.

Key Points
  • “AI” is a term people use to refer to a very large variety of different things.
  • Different people have different perspectives on the technology, and these perspectives are sometimes associated with strong feelings.
  • It helps to share what you know and don’t know about.

Content from Large Language Models


Last updated on 2026-11-05 | Edit this page

Overview

Questions

  • What does a large language model do?
  • How is a large language model developed?

Objectives

After this episode, learners will be able to:

  • Summarise how a language model produces output based on its training data and conditioning.

The term “generative AI” refers to a range of artificial intelligence models that produce output similar to the data on which they have been trained, based on some input provided. The category includes many different models that have been trained to produce different kinds of output from different inputs, e.g. text to text, text to image, text to video, image to text. The focus of this workshop will be text-to-text models, since these are the type predominantly used for assistance with programming. The technology at the centre of the most well-known and widely-used text generating AI tools is the Large Language Model (LLM).

Advanced Pattern Matching


Language models encapsulate patterns in data and produce output based on those patterns. What factors influence the output produced by a model?

TODO: a figure summarising the process outlined below.

Model training

Patterns are “learned” by the model through a process of training: a large volume of data is processed to identify the statistical relationships between elements of that data, which are then stored in the model. In language models, these elements of data are tokens: words, parts of words, and other building blocks of text. Patterns are identified in the use of these tokens during the training process, such as which combinations of tokens often appear in sequence.

Callout

Beware of using Human Words for Machine Processes

Words like “learn”, “know”, “understand” and “hallucinate” are everyday human words which we have borrowed to describe LLMs because they are convenient. However, they can suggest that the LLM has more of a human-like conscience than is really the case. For example, when we say a model “learns”, it’s easy to imagine it understanding information as a human does. In reality, a model “learning” instead describes numerical weights being adjusted so that its output better matches patterns in text. Throughout the workshop, pay attention to when the language used to describe AI suggests human-like thinking, and reflect on what the tool is actually doing.

Challenge

Exploring tokens

Use an online tokeniser tool to count the number of tokens in this sentence:

In biology, depolarization or hypopolarization is a change within a cell, during which the cell undergoes a shift in electric charge distribution, resulting in less negative charge inside the cell compared to the outside.

(From Wikipedia: Depolarization)

Scroll down the page to explore the breakdown of tokens from different systems. Try out some other sentences and paragraphs. What do you learn about how text is broken into tokens?

Text is most commonly split into one token per word, with additional tokens for punctuation. Spaces before words are often included in the word’s token, and some words are decomposed into multiple tokens representing common building blocks of the language e.g. suffixes like “ing”, “ize”, and “ed” or prefixes like “pre”, “de”, “uni”, etc.

TODO: add screenshot of tokenizer output

The training process for cutting edge large language model systems involves the processing of colossal and diverse volumes of data. The models themselves must be very large in order to capture the patterns in such a deep and wide range of data. The result is an enormous set of numerical parameters that determine the probability of each possible next token in its output. These are referred to as the model’s weights.

Fine tuning

The initial training is followed by a second process of fine tuning where the model’s weights are further adjusted through testing and feedback. This process involves prompting the model with known examples and comparing outputs to the correct or preferred solutions, and people prompting the model and rating the quality of the output produced. The results of these tests are used to further adjust the weights towards the kinds of responses that are preferred.

The system prompt

A chatbot has an internal prompt containing a fixed set of instructions from its developers. This system prompt is included alongside the user’s prompt whenever the model generates output. It may contain guidance on everything from the tone of the chatbot’s output to how it should avoid infringing copyright in its responses.

The context window

In addition to the inherent weights of the model, the content of the output is influenced by the context of the task at hand. This context includes information about the system prompt, the user’s prompt, the history of the dialogue between the user and the model, and the contents of any files that have been processed so far. It is stored in the context window of the model. Since the training data of a large language model is so diverse and general, the data in the context window is very important for specialising the kind of language that will be included in its responses. The size of the context window varies greatly from model to model, but they all have a limit on how much they can store. The capacity of the context window, and ensuring that the most relevant information remains in the context, become increasingly important considerations as the size of a project grows.

Discussion

How does context influence output?

Your task is to predict the next word in the following sentence:

On the way to the meeting, I picked up a ____

How would your answer change, if you knew that the sentence was part of:

  1. A text message about what the author had for lunch.
  2. A chapter in a novel about secret agents and espionage.
  3. An excuse for being late to a work meeting.

Every time a chatbot is prompted, the entire context is fed into the model, which predicts and returns a new sequence of tokens. The output is a simulation of the language that the model was trained on.

Key Points
  • Large language models generate text output based on patterns in its training data and the context it stores about the task or project.
  • The development of a model includes training on a large volume of data and fine tuning of the resulting weights. The responses produced by a chatbot are also influenced by a fixed system prompt and the contents of the model’s context window.

Content from Output and Uncertainty


Last updated on 2026-11-05 | Edit this page

Overview

Questions

  • What is the role of randomness in the outputs generated by a large language model?
  • Why is it important to be aware of this randomness when working with a chatbot?

Objectives

  • Explain how tokens are selected when model output is generated
  • Identify implications of the unpredictability of LLM output

Random output generation


The previous episode explained that model output is influenced by user and system prompt, other context, and the weights that result from the training process. Output is generated one token at a time.

The Transformer Explainer tool illustrates the process leading to token selection. Each time, a list is produced of most probable next tokens and one token selected from this list. The tokens in that list each have an associated probability of being chosen as the next in the sequence. Sometimes there will be a single token with a very high chance of being selected. Other times the probabilities will be roughly equal between multiple different options. This randomness means that different output can be generated from multiple repeats of the process, even if the starting conditions are the same each time. (There is a way to avoid this, by reducing the value of a setting on the model called its temperature, but that discussion is beyond the scope of this lesson.)

Challenge

Exploring random token selection

Visit the Transformer Explainer page https://poloclub.github.io/transformer-explainer/. Your instructor will provide you with a starting phrase to type into the box at the top of the page or to choose from the Examples dropdown menu beside it. Press the Generate button. After a moment, you will see a list of possible next tokens appear on the right-hand side of the page, accompanied by their relative probabilities of being chosen. One of those tokens (typically a word or punctuation mark) will have been chosen and added to the sentence at the top of the page.

  • Was the token chosen for you the one with the highest probability? If not, how many other tokens had a higher probability of being chosen next?
Challenge

Exploring random token selection (continued)

Press the Generate button again. Consider this next token and the list of other possible options.

  • How do you think these options differ from those produced for people who got a different token in the first iteration?
Discussion

Exploring random token selection (continued)

Now press Generate several more times, until you reach the tool’s length limit (12 words at the time of writing). Copy and paste the sentence you received into the shared notes document.

  • Review the sentences shared by other learners in the workshop. Are there any duplicates? Did anybody else get exactly the same sentence as you?
Discussion

How does this compare to human communication?

How does the way that large language model output is generated compare to the way that people communicate? How does your interpretation of a piece of text change if you know it was AI-generated, vs human-generated?

The randomness in chatbot response generation is intentional. It reduces the predictability of the chatbot’s responses and makes them feel less “robotic”. But the unpredictability also has some disadvantages. Randomness explains why responses vary from one attempt to the next, but it does not account for why LLMs sometimes generate incorrect output. To understand why LLMs can be wrong we need to examine an issue that has been called ‘hallucination’. ## ‘Hallucinations’ The information in large language model output does not always correspond with observable reality: the text might include incorrect information that could be misleading without verification. These non-factual outputs have become known as hallucinations, although some objections have been raised to this terminology. The model itself does not know whether the words and sentences in the output it is generating are factually accurate. Nor can it be held accountable for the consequences of any inaccuracies.

It’s important to remember that an LLM does not understand the content of any text or code it generates.
For example, a model that can write a convincing paragraph about quantum mechanics has not ‘understood’ quantum mechanics. It has learned what such paragraphs tend to look like. Verification is the responsibility of the human on whose behalf the text is being generated.

This responsibility and other risks of using AI-generated outputs are discussed in more detail later in the workshop, in the Considering Implications of GenAI Use lesson.

Challenge

How reliable is model output?

Ask your chatbot to generate the script of a short conference presenter introduction about you. An example prompt:

I am chairing a session at an upcoming [YOUR RESEARCH DOMAIN] conference. One of the presenters is [YOUR NAME]. Please draft the script of a short biography that I can use to introduce the presenter. Maximum four sentences.

Review the response you receive.

  • Is the information accurate?
  • If there are factual inaccuracies, how serious are they?
  • If you were really presenting at a conference, how would you feel if the session chair read this out to introduce you?

As the world’s foremost expert in you (presumably), you are uniquely well positioned to review this output. Reflecting on your assessment of this script, how confident would you feel about using AI to generate the script for an introduction of another researcher in your field?

If you have the option to switch off web searching in your chatbot session, turn it off and try running the prompt again. How does this affect the output?

Discussion

What does this change?

Imagine that you need to cite a key research paper in a grant application that has to be submitted in the next few hours. You accidentally deleted the paper from your reference manager and need to find its details as quickly as possible. There is a good chance that one of the paper’s authors will review your grant proposal so you also need to make sure that those details are correct!

Discuss and compare the relative merits of taking the following approaches to solve your problem:

  1. Ask a colleague with comprehensive knowledge of the research literature and a strong memory for details, but who does not answer their phone and has been known to take days to read and respond to messages.
  2. Search for the paper on the internet.
  3. Ask a chatbot.

Tools and Models are Changing Fast


Chatbots running in a browser or an app have become more sophisticated in recent years. They can search the internet and have access to a computing environment where they can install and run programs and process the results. The core technology is still the large language model, with additional layers constructed around it. The aim of these additional layers is to augment the capabilities of the model and to mitigate the risks of its output not correlating with reality, e.g. by searching the internet for authoritative information rather than relying on the accuracy of the generated output, or triggering a program to run calculations instead of generating the results itself.

Key Points
  • LLM outputs are generated from tokens randomly selected based on probabilities calculated by the model. The same prompt provided multiple times will usually produce different results even if the starting conditions are identical.
  • Bear this randomness in mind as you work with chatbots: responses that appear authoritative, from tools whose responses are often accurate and helpful, can include inaccuracies.