ChatGPT Use Cases ~2 Months In

, , , , , Leave a comment

It has been just over two months since the release of ChatGPT. During this time, I have explored various use cases and compared different tools. In this post, I would like to share the two uses for ChatGPT that have proven to be the most valuable so far. Of course, it can be used for a thousand other things, but these two have personally stood out to me as the most consistently useful.

Use Cases

I have found that ChatGPT is most consistently useful in the role of an expert, tutor, and editor.

1. Expert and Tutor

When: I want to learn X.

Expertise vs Tutoring

These are very similar conceptually, but I would make a small distinction:

  • Expertise. At times, I may want to get a brief overview (tldr) of a topic. This could be viewed as a quick chat with an expert. For example, if I wanted a brief summary of the life extension industry, but didn’t want to dive too deep, I could think of it as a quick chat with a friend who works in the industry.
  • Tutoring: In other instances, I may want to dive deeper into a specific topic and ask a series of questions. For instance, while I was learning about machine learning with PyTorch, I found ChatGPT to be very helpful as a tutor.”

How

  • Know Where to Start. If I don’t know where to begin, a general introductory question might be helpful, such as “What are the most important topics to master in order to learn X?”
  • Troubleshoot. If I encounter a specific problem or question, it’s best to address it directly. I’ve found that this approach works particularly well with programming questions, at least at a basic level.

Best Practices

  • Creative Prompting: Sometimes, getting creative with prompts can help. For example, instead of asking, “Explain general relativity as if I’m five years old,” it may be helpful to try, “Explain general relativity as if I’m five years old. Please respond as a physics professor at MIT who is good at communicating complex ideas without dumbing them down.”
  • Follow-up: In my experience, one of the main advantages of ChatGPT over traditional search engines and previous-generation AI assistants or chatbots is its interactivity and ability to maintain the thread of the conversation. So, just like with a real tutor, it may be helpful to ask for explanations in a different way, provide an example, elaborate on a particular point, or step back and explain how a certain concept fits into the big picture.

3. Editor

When: I want to change anything about a text.

How

Some examples include:

  • Checking grammar
  • Summarizing or rephrasing the text
  • Getting ideas on what else to consider and think about
  • Analyzing the argument. For example, “What are the likely influences behind this text?” or “What are the strongest counter-arguments to this?”

Context

Lessons and Challenges

  1. Hallucinations and Validation. Of course, one must watch out for hallucinations. That’s why I find that using ChatGPT in combination with Google may work best. The first step may be asking ChatGPT to provide an initial overview of a topic to save time reading long articles from the Google’s organic results that have been SEO’d in and out. And the next step may be to search for specific sub-topics — sometimes using search syntax/operators to find exact matches or limit the search to certain websites.
  2. Common Knowledge vs. Advanced/Niche Topics: I’ve found that ChatGPT is very good at summarizing and explaining common non-controversial knowledge, but is more likely to hallucinate or struggle when dealing with advanced or niche topics that may only be covered by a just few papers or blog posts. Another way to think about this is to consider how likely it is that this topic was prominent in the training dataset.

What I’ve Tested

Despite still relying on Google for the majority of my searches, I have come to the conclusion that ChatGPT — especially when combined with Google — is better or comparable for a specific subset of my use cases and queries. Depending on the question or query, I have also found Perplexity.ai, Neeva, You.com/chat, and Elicit.org to be worth trying out.

What’s Next

I am looking forward to trying Microsoft’s integration of ChatGPT with Bing and Google’s integration of Bard with Google Search. I find the intersection of search and conversational AI to be particularly intriguing, as these two tools are some of the best resources for organizing and retrieving information that we have today.

Examples

Please see — or skip — the three examples of actual “conversations” below:

Conversation 1. Expert: Industry Overview

– Me:

Can you give an overview of the life extension industry? I’m interested in understanding the structure of the ecosystem, encompassing both research and business aspects, as well as the major players, trends, and challenges.

– ChatGPT:

Sure! The life extension industry, also known as the anti-aging or longevity industry, is a relatively new and rapidly growing field that aims to extend the human lifespan and improve the health and well-being of individuals as they age.

The life extension industry encompasses a wide range of areas including pharmaceuticals, biotechnology, gerontology, and nutrition. Some of the key players in the industry include pharmaceutical companies, biotech firms, research institutions, and anti-aging clinics.

In terms of research, the focus is mainly on developing drugs, treatments, and interventions that can target the biological mechanisms of aging and reduce the risk of age-related diseases. This includes researching senolytics (drugs that can target and eliminate senescent cells), nutraceuticals (nutritional supplements that can help improve health), and gene therapy (using genetic manipulations to extend lifespan).

The business aspect of the industry involves the development, marketing, and sale of products and services aimed at the anti-aging and longevity market. This includes cosmetics, dietary supplements, and fitness equipment, as well as more cutting-edge technologies such as wearable health monitors and bioregenerative devices.

There are also a growing number of anti-aging clinics and spas that offer personalized health and wellness plans, and some also offer anti-aging treatments such as hormone therapy and intravenous infusions of nutrients.

The life extension industry is still in its infancy and faces many challenges, including regulatory hurdles, scientific skepticism, and public perception. Additionally, the high cost of many anti-aging treatments and lack of long-term data on their safety and efficacy can make it difficult for individuals to make informed decisions about whether to invest in these products and services.

Despite these challenges, the life extension industry is growing rapidly and attracting a lot of investment and attention. With advances in technology and an aging global population, it’s likely that the industry will continue to evolve and expand in the coming years.

– Me:
Can you name the most well-regarded, prominent, and promising players?

– ChatGPT:

Sure! Here are some of the most well-regarded, prominent, and promising players in the life extension industry:

  1. Calico: Calico is a research-focused subsidiary of Alphabet Inc. (Google’s parent company) that is focused on the biology of aging and age-related diseases. Calico is one of the largest and most well-funded players in the life extension industry, and it has partnerships with a number of top biotech and pharmaceutical companies.
  2. Unity Biotechnology: Unity Biotechnology is a biotech company that is focused on developing drugs that can target and eliminate senescent cells, which are thought to contribute to aging and age-related diseases.
  3. Juvenescence: Juvenescence is a biotech company that is focused on developing drugs to extend lifespan and improve healthspan. The company has partnerships with a number of leading research institutions and is working on a number of promising drugs for age-related diseases.
  4. Insilico Medicine: Insilico Medicine is a biotech company that is using AI and machine learning to develop drugs for age-related diseases. The company has partnerships with a number of leading pharmaceutical companies and is working on a number of promising drugs for age-related diseases.
  5. Geroscience: Geroscience is a biotech company that is focused on developing drugs that can target the biology of aging and age-related diseases. The company has partnerships with a number of leading research institutions and is working on a number of promising drugs for age-related diseases.
  6. Human Longevity: Human Longevity is a health and wellness company that is focused on using technology and data to improve health and extend lifespan. The company offers a range of products and services, including anti-aging treatments and health assessments, and it has partnerships with a number of leading healthcare organizations.

These are just a few of the most well-regarded, prominent, and promising players in the life extension industry. The field is constantly evolving and new players are entering the market all the time, so this list is by no means exhaustive.

Conversation 2. Tutor: Lambda Functions in Python

– Me: ELI5 lambda function in Python

– ChatGPT:

A lambda function in Python is a small anonymous function, which can take any number of arguments, but can only have one expression. The syntax for a lambda function is:

lambda arguments : expression

Lambda functions are used in cases where you need a quick throw-away function for a short period of time. They are often used as arguments to higher-order functions (functions that operate on other functions).

For example:

# A normal function to add two numbers
def add(x, y):
    return x + y

# An equivalent lambda function
add = lambda x, y : x + y

In the above example, add can be used like a normal function to add two numbers.

– Me: What are anonymous functions?

– ChatGPT:

An anonymous function is a function that has no name and is not bound to a variable. Anonymous functions are also called “lambda functions” in Python, because they are created using the lambda keyword. Anonymous functions are used when you need a small, one-time-use function for a short period of time.

Because anonymous functions have no name, they cannot be reused or referenced outside of the expression in which they are defined.

For example:

# An anonymous function to square a number
lambda x: x**2

# An anonymous function to add two numbers
lambda x, y: x + y

These anonymous functions can be assigned to variables, passed as arguments to other functions, or used in other ways, just like any other function.

– Me: So if it has no name, how do I call it?

– ChatGPT:

You can call an anonymous function by assigning it to a variable and then calling the variable as if it were a regular function. Alternatively, you can call the anonymous function directly by passing it as an argument to another function, or by using it in an expression.

For example:

# Assigning an anonymous function to a variable
square = lambda x: x**2
result = square(10)
print(result) # 100

# Calling an anonymous function directly
print((lambda x: x**2)(10)) # 100

# Using an anonymous function as an argument
numbers = [1, 2, 3, 4, 5]
squared_numbers = list(map(lambda x: x**2, numbers))
print(squared_numbers) # [1, 4, 9, 16, 25]

Conversation 3. Editor: Launch Announcement

Had ChatGPT been available in 2020, we could have used it to edit our product launch announcement. For example:

– Me:
Please respond as a highly skilled editor who is a native speaker of American English. Your writing is succinct, articulate, and accessible. Can you please edit and fix grammar in this text?

“Today my co-founder and I are launching the product we’ve been working on for months. It’s an odd time to launch anything but we’re proud of what we’ve built and we hope that our product can also help some people who were laid off recently. A Happy Job is a team-based and culture-centric recruiting platform. We help job-seekers — engineers at first — find teams that are actively hiring and fit their preferences. Search by product type, tech stack, team set-up, culture, values, working styles or perks.”

– ChatGPT:

Today, my co-founder and I are launching the product we have been working on for months. Despite the current circumstances, we are proud of what we have built and hope that our product can assist those who have recently been laid off.

“A Happy Job” is a team-focused and culture-oriented recruitment platform. We help job seekers – specifically engineers – find teams that are actively hiring and align with their preferences. You can search for teams based on product type, technical stack, team structure, culture, values, work style, and even perks.

Leave a Reply