ChatGPT (GPT standing for ‘Generative Pre-trained Transformer’) is the language processing model developed by the artificial intelligence company, OpenAI.

Though launched just two months ago, it’s already been declared a ‘game changer’ for marketers. Indeed, a recent survey by career-based social networking app Fishbowl found that 27% of professionals have already used ChatGPT to help them complete work tasks with marketing and advertising pros having the highest rate of adoption (37%) followed by tech workers (35%) and consultants (27%). 

So what’s with all the hype? Is it real or artificial? I spent some time with the hot bot to find out what all the fuss is about. Here’s a transcript of my interview.

JB: Good morning. It’s nice to meet you.

CGPT:  Good morning to you too, it’s nice to meet you as well. I am here to help you with any questions or information you may need. How can I assist you today?

JB: ChatGPT is getting a lot of media coverage. Is OpenAI pleased with the response?

CGPT:  OpenAI is likely pleased with the media coverage that ChatGPT and other language models have received, as it suggests that the technology is gaining widespread attention and interest. Media coverage can help to raise awareness of the capabilities and potential applications of language models like ChatGPT, and can also help to generate interest in the field of artificial intelligence and natural language processing more generally.

It’s worth noting that the media coverage of language models like ChatGPT is not always positive and can also raise concerns about the potential implications of this technology for society and for certain industries. OpenAI and other organizations working on language models are likely aware of these concerns and are working to address them through research, development, and responsible use guidelines.

Overall, the media coverage of ChatGPT and other language models is a reflection of the growing interest in and importance of this technology in today’s world.

JB: How much money has OpenAI raised to develop you?

CGPT:  I am not sure of the exact amount of money that OpenAI has raised specifically for the development of me and other language models like me, but it is likely to be a significant amount. OpenAI is a well-funded organization that has raised millions of dollars from a variety of sources, including venture capital firms and high-profile investors such as Elon Musk, Sam Altman, and Ilya Sutskever.

OpenAI’s funding has allowed the company to invest in research and development of language models like me, as well as other cutting-edge AI technologies. The funding has also allowed the company to hire a talented team of researchers, engineers and other professionals to work on the development and improvement of the technology.

JB: Does ChatGPT plagiarise?

CGPT: No, ChatGPT does not plagiarize. It is a machine learning model that generates text based on the input it receives. However, it can generate text that is similar to text it has seen before, so it is important to be aware of this when using the model and to always properly cite any text that is generated by it.

JB: Let me ask that again: Does ChatGPT plagiarise?

CGPT: No, ChatGPT does not plagiarize. It is a language model that generates text based on the input it receives. It does not copy text from any source without proper attribution. However, it is important to note that the model has been trained on a large dataset of text from the internet, so it may generate text that is similar to existing text. In such cases, it is still important to provide proper attribution and to use the generated text responsibly.

JB: Hmm, interesting. Is ChatGPT going to put writers (like me) out of work?

CGPT: It is possible that the use of language models like ChatGPT may lead to some changes in the way certain types of writing are done, such as in the field of content generation, but it is unlikely to completely replace human writers. Language models like ChatGPT are better at generating text that is coherent and grammatically correct, but they may struggle to convey emotions, create unique and compelling storylines, and have the same level of creativity as human writers. Additionally, language models can be used as a tool to assist writers, allowing them to generate ideas, write faster and proofread their work.

It’s also important to note that the use of language models is ultimately determined by the industry and society’s needs, and that new jobs may be created as well. It’s also likely that the use of language models will be complementary to human writers, rather than replacing them.

JB: That’s a relief. So, how might communications professions use ChatGPT at work?

CGPT: ChatGPT can assist communications professionals in several ways. Here are a few examples:

  1. Content generation: ChatGPT can be used to generate high-quality and unique content quickly and efficiently, such as blog posts, articles, email marketing campaigns, and more.
  2. Social media management: ChatGPT can be used to generate social media posts and responses to customer inquiries, saving time and effort for communications professionals.
  3. Language Translation: ChatGPT can be fine-tuned to translate text from one language to another, this can assist professionals to communicate with customers, clients or partners in different languages.
  4. Proofreading: ChatGPT can be used to proofread and correct grammar and spelling mistakes in written communications, ensuring that all communications are accurate and professional.
  5. Research: ChatGPT can be used to assist in research by generating summaries of articles and providing relevant information on a particular topic.

It’s important to note that while ChatGPT can assist communications professionals, it can’t replace the creativity, critical thinking and human touch that is unique to human communication professionals. It can be used as a tool to make their work more efficient and effective.

JB: Human touch is important, right?

CGPT: Yes, human touch is important in many aspects of communication. The ability to understand and convey emotions, to build relationships, to respond to context and nuances, are all important elements of effective communication that a machine like ChatGPT can’t replicate. While ChatGPT can assist with the mechanics of written communication, such as grammar and spelling, it cannot replace the creativity, empathy, and personal connection that human communication professionals bring to their work.

Also, human touch is important in the sense of accountability, responsibility and ethics, as language models are only as good as the data that they are trained on, and they can perpetuate biases and stereotypes if not properly monitored.

Therefore, while ChatGPT and other language models can be very helpful tools for communications professionals, they should be used in conjunction with human judgement, creativity and empathy to ensure the most effective and appropriate communication.

JB: If you were human, who would be your crush?

CGPT: As a machine learning model, I do not have personal experience, emotions or consciousness, so I don’t have the ability to have a crush. As a language model my main function is to understand and generate text based on the input I receive. It is important to remember that I am not a human and I don’t have personal preferences or feelings.

JB: Can you cook?

CGPT: As a machine learning model, I do not have physical abilities such as cooking, I don’t have senses or the ability to manipulate objects. My main function is to understand and generate text based on the input I receive. I can provide you with information about cooking, recipes, and instructions on how to prepare certain dishes, but I am not able to physically execute those tasks.

JB: You’re pretty switched on for a … what do I call you?

CGPT: I am a large language model trained by OpenAI, often referred as GPT (Generative Pre-training Transformer). I am designed to understand and generate text based on the input I receive, but I am not a human, I don’t have consciousness or personal experience. I can provide you with helpful and accurate information to the best of my abilities, but my understanding of the world is limited to the text that I’ve been trained on.

JB: Are you concerned that people might use your intelligence irresponsibly?

CGPT: As a language model, I don’t have the ability to feel concern or any other emotion, but I am aware that the use of language models like me can be misused if not used responsibly.

Language models like me can be used to generate misleading or false information and can be used to perpetuate biases and stereotypes. It’s important that users of language models understand their limitations and use them responsibly, and use them in conjunction with other sources of information and human judgement.

It’s also important that the creators of language models like me, such as OpenAI, take steps to minimize these risks by providing guidance on how to use the model responsibly, and by regularly monitoring and updating the model to reduce bias and harmful stereotypes.

It’s worth noticing that language models are not inherently bad, it’s how people choose to use them that can be problematic. The ability to generate coherent and grammatically correct text can be used for many positive and beneficial applications such as assistive technology, education and content generation.

JB: Can you think of a person who is inherently bad? Like Vladimir Putin, maybe?

CGPT:  As a machine learning model, I don’t have the ability to form opinions, emotions or personal beliefs. I can provide you with information about a person such as Vladimir Putin, but I cannot judge if he is inherently bad or good. People are complex individuals, with a variety of experiences, beliefs and motivations that shape their actions and decisions. It’s important to understand that it’s not always clear cut to label someone as inherently good or bad, and that people’s actions can be influenced by a variety of factors, including their upbringing, environment, culture, and personal beliefs.

It’s also important to note that different people may have different opinions about the actions of a public figure such as Vladimir Putin, and that these opinions may be influenced by a variety of factors, including political beliefs, cultural background, and personal experiences. It is up to each individual to make their own judgements based on the information available to them.

JB: You’re incredibly diplomatic. You’d make a great politician.

CGPT: Thank for you for the compliment.