Conversational UX Stack

What is an LLM?

When a new technology really wows and gets us excited it becomes a part of us. We make it ours and we anthropomorphize it. We project human like qualities on it and this can hold us back from really understanding what we are actually dealing it.

So let's consider a few questions. Mainly what is an LLM and what are its limitations?

Perhaps these questions and ideas will illuminate our understanding:

1. Is an LLM a program?

2. Is an LLM a knowledge base?

3. Does an LLM know anything? 

4. If an LLM is a program how does it compute its 70-100 Billion parameters in only a few seconds?

5. If an LLM is a knowledge base, why does it need to predict? 

6. How can an LLM Model with Billions of parameters that has been trained on pretty much the entire internet, fit on a 100GB drive?

7. What are some simple tasks that LLMs can't do?

​

Hopefully these questions dispel some of the mystic around LLMs. There are a number of things that most people believe about them that are contradictory and wrong.

First, LLMS are not knowledge bases and they are not really programs either. What they are is a statistical representation of a knowledge bases.

In other words, an LLM like ChatGPT4 has been trained on hundreds of billions of parameters that it has condensed into statistical patterns. It does't have any knowledge but it has the patters of knowledge. When you ask it a question, it predicts the answer based on its statistical model.

A good way to think about this is that it is basically like a filter. Your question becomes the filter and configures the shape of the model so the right content or words drip out.

​

If you want to learn more about LLMs and how they work check out our LLM Section.

Bias

What is Bias? Is it ever a good thing? It's very important that we are on the same page of what it means so we can understand it better. ​

​

Here is the Webster definition of Bias: 

1. an inclination of temperament or outlook especially : a personal and sometimes unreasoned judgment : PREJUDICE

2. an instance of such prejudice

3. BENT, TENDENCY

4. deviation of the expected value of a statistical estimate from the quantity it estimates And/OR systematic error introduced into sampling or testing by selecting or encouraging one outcome or answer over others

Transitive verb

1. to give a settled and often prejudiced outlook to his background biases him against foreigners

2. to apply a slight negative or positive voltage to (something, such as a transistor)

​

The most important insight here is that, bias has its roots in our preferences. For example, if you prefer coffee over tea, you are more likely to show bias towards coffee. You might believe that more people drink coffee, that coffee increases your mental focus better, even that it is healthier. At the bare minimum, you will have more information about coffee which will skew how you view both coffee and tea.

​

How does Bias Form?

Every interaction has three components. For example, as your reading this sentence, there is the words on the screen, you the reader and the meaning you are gathering form this information.

The first stage is attention, you are paying attention to this instead of something else. The second aspect is your perspective. You are seeing these ideas from a point of view that is limited in time and space. Consider how different this perspective would be if you read this five years ago. Lastly, there is mean making. All of these words will mean something to you. Depending on your background and education, consider how differently an engineer, a linguist and a conversational designer would interpret this paragraph.

Perceptions & Bias:

​

1. Attention: The world has too much information. Based on what we value, we decide where to look and what facts to pay attention to a-priori.

​

BIAS: By doing so, we are implying that some information is more important than other information. We are showing a preference. 

​

2. Perspective: We only see objects from a point of view. Our perspective skews how we see the things we are paying attention to.

BIAS: Seeing a limited perspective or only one side of an object, event, person, topic, etc. leaves us open to confirmation bias, selection bias, sampling bias, reporting bias, volunteer bias, publication bias....

4. Mean Making: We turn limited data on limited things into meaning. Mean making is a process that involves our identities, beliefs, culture, personalities, etc. For example, consider how an adult and a child would interpret a similar event.

​

BIAS: The entire knowledge base is a construct, something we fabricate. It is a useful invention that doesn't exist outside of us.

​

To properly address BIAS, we need to be aware of it at every stage of the process.

Hallucinations & Poor Accuracy

Why do good models do bad things?

​

The answer lies in the models and how they are built.

LLMs are Statistical Representations of Knowledge Bases. They have taken the world's information and knowledge and boiled it down to statistical principles.

These principles are like icons. Icons represent something much more than what they are. They are a low resolution images that represent a much bigger chunk of information. They give you a lot more information than meets the eye.

​

Additionally, LLMs were trained on biased data. We know this because the internet is full of biased data. For example, most the internet is in English and represents Western values, yet the global population doesn't speak mostly english or hold western values.

​

When we combine both low-resolution models and bias we will have a hallucinations and poor accuracy.

​

How does this work and when does it happen?

It happens when you ask a detailed question about something specific. In our example, if you ask detailed questions about the icon, the model might make up those details in a way that conforms to its biases.