Like the rest of the world, we at Whycatcher have been truly fascinated by the explosion of OpenAI. Some of us here had a play around in beta, and as true techheads we knew it was going to be massive. We’re merely stating this to highlight how ahead of the curve we are, but let’s press on.
Now that OpenAI is live, the possibilities really are endless – both within market research, and far wider. Kids are excited by it (for example asking about the Infinite monkey theorem), and the less tech savvy are nervous about it (will it steal my personal data?). No matter who you talk to, we all know that the applications of ChatGPT (a branch of OpenAI) are seemingly endless, and that’s where it gets super interesting. We are clearly on the brink of something huge, even though no-one really knows where it will go.
To explore this mighty piece of kit that everyone’s talking about, we decided to do a little experiment. We asked ChatGPT to write us a blog post and this is how it went.
Whycatcher: Write me a blog post about ChatGPT and its place in market research
ChatGPT: ChatGPT is a powerful language model developed by OpenAI. It has the ability to generate human-like text, making it a valuable tool in a variety of industries. One area where ChatGPT is particularly useful is in market research.
Market research is the process of gathering, analyzing, and interpreting data to better understand the needs, behaviors, and opinions of consumers. It is an essential part of any business strategy, as it helps companies make informed decisions about product development, marketing, and sales.
Traditionally, market research has been conducted through surveys, focus groups, and interviews. These methods can be time-consuming and costly, and they often rely on human interpreters to analyze the data. ChatGPT, on the other hand, can quickly and accurately generate large amounts of data, making it a valuable tool for market researchers.
One of the main advantages of ChatGPT is its ability to generate natural-sounding text. This makes it ideal for simulating conversations between consumers and businesses, allowing researchers to gather valuable insights into consumer behavior and preferences.
Another advantage of ChatGPT is its ability to understand context. This allows it to generate responses that are relevant to the conversation, making the data it generates more accurate and useful.
In addition to these advantages, ChatGPT can be easily integrated into existing market research tools, making it a flexible and versatile tool for researchers.
Overall, ChatGPT is a valuable tool for market researchers. Its ability to generate human-like text and understand context makes it a powerful tool for simulating conversations and gathering data, which can help businesses make more informed decisions. It is a cost-efficient and faster alternative to traditional methods and can be easily integrated into existing market research tools. As the technology continues to improve, we can expect to see ChatGPT playing an even bigger role in market research in the future.
Whycatcher: That’s all well and good, but what about if the blog for six year olds?
ChatGPT: ChatGPT is a special computer program that can talk and write like a person. It’s really good at understanding what people say and responding in a way that makes sense.
In business, people use ChatGPT to help them learn about what other people like and want. This is called “market research.” By using ChatGPT, companies can learn more about what kinds of things kids like you might want to buy, and make new and better products just for you!
ChatGPT is like having a robot friend who can have a conversation with you. It’s faster and easier than asking a lot of people one by one, and it can help companies make better things for you to enjoy.
So next time you see a new toy or video game, remember that ChatGPT might have helped make it happen! It’s like having a super cool helper, working behind the scenes to make sure you have the best stuff to play with.
Whycatcher: That works. Although frankly you sound too good to be true. What are the limitations of chatGPT?
ChatGPT: ChatGPT is a state-of-the-art language model developed by OpenAI, but like any AI model, it has certain limitations. Some of these limitations include:
- Lack of context: ChatGPT can generate human-like responses, but it doesn’t have the ability to understand the context of a conversation or a situation. It generates responses based on the input it receives.
- Limited understanding: ChatGPT is able to understand natural language input, but it doesn’t have a deep understanding of the world like humans do.
- Bias: ChatGPT is trained on a large dataset of text from the internet, which may contain biases. It’s important to be aware of these biases and how they may affect the responses generated by the model.
- Lack of common sense: ChatGPT can answer specific questions or generate responses, but it doesn’t have common sense understanding of the world, so it may struggle to answer questions that require common sense reasoning or understanding.
- Limitations on generating new information: ChatGPT is able to generate text but is not able to generate new information, it can generate text based on the information it has been trained on, but it’s not able to come up with new information.
- Limitations on understanding sarcasm, irony, and other forms of figurative language.
- Limitations on understanding and generating emotions, it may generate text with emotional words but it doesn’t have the ability to understand and generate emotions like humans do.
It’s important to keep these limitations in mind when using ChatGPT and to supplement its output with human judgement and knowledge.
Whycatcher: Thanks! Onto more pressing matters then – how long would it take a monkey to randomly type ‘Bob’ on a typewriter?
ChatGPT: The “Infinite monkey theorem” states that given an infinite amount of time, a monkey randomly hitting keys on a typewriter will almost surely type a given text, such as the complete works of William Shakespeare. However, the time it would take for this to happen is astronomical and practically impossible.
It is impossible to determine how long it would take for a monkey to randomly type the word “Bob” on a typewriter as it would depend on a number of factors such as the number of keys on the typewriter, the typing speed of the monkey, and the likelihood of the monkey hitting the correct keys in the correct order to spell “Bob.” Additionally, monkeys do not have the cognitive ability or fine motor skills to type on a typewriter, and would not have the interest to do so.
It’s important to remember that the “Infinite monkey theorem” is just a thought experiment and it’s not meant to be taken as a serious prediction of how long it would take for monkeys to type a specific word like “Bob”. The real time frame for this would be impossible to predict and it would not be ethical to test it out on animals.
Whycatcher: Ok – thanks for putting me back in my place (and spoiling my sons’ fun). One final thing then – would you ever steal my anyone’s bank details?
ChatGPT: As an AI, I am not capable of stealing or committing any illegal or unethical actions. My purpose is to assist users with providing helpful and accurate information, and I don’t have access to any personal information or the ability to steal or manipulate it. I am a program, and my actions are limited to the parameters and instructions given to me by the engineers who created me. It is not ethical for me or anyone else to steal personal information like bank details, and it is illegal in most countries. If you suspect any illegal or unethical activities, you should contact the appropriate authorities and seek professional help.
Whycatcher: Lovely, thanks for that – I had a great time with you today!
ChatGPT: I’m glad I could help. If you have any other questions or need further assistance, feel free to ask. I am here to help you with any information or clarification you need. Have a great day!
So there you have it, ChatCPG in a nutshell. Sure, it might be a bit formulaic in places and lacking in emotion, but the content is all there. Ultimately that’s what OpenAI is all about – analysing huge amounts of data to succinctly return an intelligent response to the user. It is absolutely not a human though, and therefore it shouldn’t be treated as such. ChatGPT will see everything in black and white, so subtleties that you or I would pick up may be completely missed. It can’t make inferences and recommendations in the same way that a researcher would. So it turns out that even with all those millions of data points, there is no replacement for human understanding.
The onward journey for OpenAI remains unclear, but one thing is for sure – this has blown the AI game right out of the water and we’re all super excited to see where it goes.
Maria Colarusso is Digital Lead at Whycatcher. She loves tech and wrote this blog with a bit of help from her son (and ChatGPT).