Taming the new AI hero in TechTown: OpenAI’s ChatGPT; Discussing the chatbot’s use, why and where to draw the line.

By Abharan Yadavalli

2/23/2023

What is ChatGPT?

ChatGPT is an artificial intelligence-based chatbot that uses a deep learning algorithm called a transformer to generate responses to text-based inputs. It is trained on a massive corpus of text data to understand the patterns and structures of language. Where GPT stands for Generative Pre-Trained Transformer, which means that it generates new text rather than selecting pre-existing responses from a database. This makes it highly versatile and able to generate responses to a wide range of inputs, including those it has never encountered before.

So, at this point there might have been a glaring question in front of us: “Why am I writing this article, when an AI could write essays in seconds?”

Let’s take a look at the result of asking ChatGPT to generate an article that outlines the following:
1. What is ChatGPT?
2. How is it different from other AI tools?
3. What are its use cases?

The following response was generated:

“Artificial intelligence has come a long way, and ChatGPT is at the forefront of this progress. ChatGPT is a deep learning language model that uses the transformer architecture to generate human-like responses to text-based inputs. Developed by OpenAI, it has garnered significant attention due to its impressive capabilities.

So, what sets ChatGPT apart from other AI text tools?

One of the most significant differences is its generative nature. ChatGPT does not rely on pre-programmed responses or keyword matching like rule-based systems or chatbots. Instead, it uses deep learning to analyze the context of a user’s input and generate a response based on its understanding of language patterns. This allows ChatGPT to create unique and personalized responses, making it a more natural and engaging conversational partner.

ChatGPT’s architecture also enables it to learn from vast amounts of text data, making it highly adaptable to new inputs. It can understand the meaning of words and phrases in context, making it better equipped to handle complex and ambiguous queries.

The result is a highly sophisticated AI text tool that can be used in various industries and applications. Some of the use cases of ChatGPT include:

Customer service – ChatGPT can handle simple and complex customer queries, reducing the need for human intervention and speeding up response times.

Language translation – With its deep understanding of language patterns, ChatGPT can provide accurate translations for different languages.

Personalized content creation – ChatGPT can generate unique and engaging content for social media, email marketing, and other digital channels.

Education – ChatGPT can act as a tutor, helping students with questions and providing explanations for complex concepts.

Healthcare – ChatGPT can be used to create chatbots that assist patients in booking appointments, answering health-related queries, and more.

In conclusion, ChatGPT’s innovative approach to language processing has made it a game-changer in the AI text tool space. Its generative nature and ability to learn from vast amounts of text data make it highly versatile and adaptable to various industries and applications. As AI continues to evolve, ChatGPT will undoubtedly play a significant role in shaping the future of conversational interfaces.”

Great! I could not have given a better introduction. That is a well written concise piece of writing(more like a concise piece of algorithmic generation). It has summarised what it does, how it operates and a few of its uses. Clearly, ChatGPT is helping write the article, doing a pretty decent job, lets see which other fields where one can gain professional content using ChatGPT, in an instant!

So, I asked ChatGPT to list out 45 use cases in professional fields and here is the response: (feel free to skim to the end of the list)

“Content creation: Assist with generating written content such as articles, social media posts, and blog posts.
Chatbots: Create automated chatbots to handle customer queries and support.
Customer support: Provide real-time assistance and support to customers.
Language translation: Translate written text in real-time between multiple languages.
Personalized content: Create personalized content for individual users based on their interests and preferences.
Virtual assistants: Assist with scheduling, reminders, and other tasks to help with productivity.
Creative writing: Assist with generating creative content such as poetry and short stories.
Academic research: Assist with generating research papers and analyzing data.
Marketing: Assist with generating marketing content such as ad copy and email campaigns.
Gaming: Assist with generating dialogue and narrative for video games.
Chat-based learning: Assist with language learning and educational material delivery.
Text summarization: Summarize lengthy text into shorter and more manageable pieces of information.
Speech recognition: Recognize and transcribe spoken words into written text.
Sentiment analysis: Analyze and understand the sentiment and emotion of written text.
Content moderation: Identify and remove inappropriate or offensive content from online platforms.
Resume screening: Screen job applications and identify qualified candidates based on job requirements.
Personal finance management: Assist with managing finances and tracking spending.
Legal document analysis: Analyze legal documents and contracts.
News aggregation: Collect and organize news articles from various sources.
Chat-based therapy: Provide therapy and mental health support through chat.
Knowledge management: Store and retrieve knowledge and information within an organization.
HR management: Assist with recruiting, hiring, and managing employees.
Sales support: Assist with generating leads and closing sales.
Project management: Assist with managing projects and tasks.
Virtual event assistants: Assist with organizing and managing virtual events.
Social media management: Assist with managing and scheduling social media posts.
Content curation: Collect and organize relevant content for users.
Restaurant menu recommendation: Recommend menu items based on user preferences.
Personalized fitness coaching: Create personalized fitness plans for individual users.
Financial forecasting: Analyze financial data to make predictions about future trends.
Data analysis: Analyze and interpret large amounts of data.
Fraud detection: Identify and prevent fraudulent activity.
Investment analysis: Analyze and make predictions about investment opportunities.
Cybersecurity: Identify and prevent cyber threats and attacks.
Natural language database querying: Query databases using natural language instead of programming languages.
Chat-based health assessments: Conduct health assessments and provide medical advice through chat.
Real-time language translation: Translate spoken language in real-time between multiple languages.
Personal shopping assistants: Assist with online shopping and finding the right products.
Voice-controlled smart home automation: Control smart home devices through voice commands.
Mood tracking and emotional support: Provide emotional support and help users track their mood.
Personalized travel recommendations: Recommend travel destinations and activities based on user preferences.
Storytelling: Assist with generating engaging stories for various purposes.
Technical support: Provide technical support for software and hardware issues.
Legal advice: Provide legal advice and guidance.
Financial planning: Assist with financial planning and budgeting.”

Good job!

ChatGPT may not pass the Turing test, but definitely can pass an interview with its “tell me about yourself” section. Now we have a long list of fields (non-exhaustive), which we can use ChatGPT in order to automate, research, or assist us with tasks. So, does it mean that now we can be reliably good at carrying out tasks of the above mentioned fields?

The answer is a big ‘No’.

Breaking down few of the use cases mentioned above:

Most of the use cases in the list that are listed up-to item No.30, is definitely an advantage that is provided by ChatGPT, but soon after that the list goes down-hill. For example, No. 44: Legal advice and guidance; is safe to say that it is rather a dangerous proposition to follow for a person who lacks subject matter expertise. Legal advice needs to incorporate factors that might or might not be considered while merely scratching the surface; especially in cases of Civil law, that are heavily based on considering the society, its individuals, its workings, geographically differing laws and their treatments. In a similar way, chat-based health assessment and therapy is equally harmful, because the chatbot’s bank of knowledge is too huge: “enables it to learn from vast amounts of text data”.

Why is the extensive amount of ‘text data’ a downside? (More the better right?). Sadly, it’s a ‘No’ again, because the vast amounts of text data are scoured from databases that present everything in their entirety, which includes a huge amount of generalized and inaccurate information. Human beings, on the other hand, require specialized assessments that cater to their individual factors with a great amount of careful filtering of information. Hence chatbots are not the solution for health advice either.

“But wait, facts are facts.. Right?”. To answer this, we need to understand how ChatGPT generates its content. ChatGPT “uses deep learning to analyze the context of a user’s input and generate a response based on its understanding of language patterns”. The key phrase here, being “its understanding of language patterns” is crucial! ChatGPT being a language model, is limited when it comes to functioning capabilities, since it generates responses based on past language trends and patterns, and does not possess the critical thinking and decision making capabilities(unlike actual intelligence). Pre-trained language models like ChatGPT, suggest answers only based on the language-based pattern recognition algorithm. And with the internet being home to a handful of misleading information (ex. blogs that suggest unregulated health and medication recommendations etc.), including it in the information pool can lead to great amounts of inaccuracy.

So, always take a chatbot’s recommendations with a grain of salt.

Learn more about AI language models: C. Montemayor, (2020), Language and Intelligence (https://doi.org/10.1007/s11023-021-09568-5)

There are numerous sources showcasing the advantages of using a chat-based AI’s fetching capabilities, which are very handy. So let’s skip to the part which addresses an ongoing concern of using not just AI but goes all the way back to the boom in importance that technology suddenly received. Diminishing critical thinking skills!. Reliance on technology, in the manner that we have collectively evolved into, will potentially altered our learning, and how we receive information. This will likely raise questions about our critical thinking and decision-making skills and if they are enhanced or are adversely affected by AI.

Is technology bad? Should we stop using it?

Absolutely “Not”! Technology has existed from when the wheel was invented, and technology drove great historical leaps such as the industrial revolution. The question is not about the existence of technology around us, but the manner in which we use it.

When performing your tasks, “leverage” technology, as a catalyst to stepping closer to your goals.

AI is smart, but not actually intelligent, as it only fetches what seems to be an intelligent answer. Artificial Smartness (AS) might be a more apt acronym for it.

in·tel·li·gence: /inˈteləj(ə)ns/

noun. /ɪnˈtɛlədʒəns/ [uncountable] 1the ability to learn, understand and think in a logical way about things;

P.S:

A screenshot of what could contain information that can be misleading or problematic:

Recommending any kind of medications/names of medications has the ability to pose a great risk to potential individuals with lack of knowledge.