Prompts to try requesting ChatGPT

Welcome to On Tech: AI, a contextual newsletter that teaches you about artificial intelligence, how it works and how it’s used.

A few months ago, my colleagues Cade Metz and Kevin Roose explained the inner workings of AI, including chatbots like OpenAI’s ChatGPT, Microsoft’s Bing, and Google’s Bard. Now we’re back with a new mission: to help you learn to use AI to its full potential.

People from all walks of life – students, coders, artists and accountants – are experimenting with using AI tools. Employers post jobs looking for people who can use them. Soon, if not already, you will be able to use AI to streamline and improve your work and personal life.

As The Times’ Personal Tech Columnist, I’m here to help you understand how to use these tools safely and responsibly to improve many aspects of your life.

I’m going to spend today’s newsletter talking about two general approaches that will be useful in a number of situations.

Then, in the weeks to come, I will give you more specific advice for different aspects of your life, including parenting and family life, work, organizing your personal life, learning/education, creativity and shopping.

A few common sense caveats to start with:

• If you are concerned about privacy, omit personal information such as your name and place of work. Tech companies say your data is used to train their systems, which means other people could possibly see your information.

• Do not share confidential data. Your employer may have specific guidelines or restrictions, but in general, entering trade secrets or sensitive information is a very bad idea.

• Hallucinations: Chatbots are powered by a technology called Large Language Model, or LLM, which derives its capabilities from analyzing huge amounts of digital text mined from the internet. A lot of things on the web are wrong, and chatbots can repeat those untruths. Sometimes, trying to predict patterns from their vast training data, they can make things up.

The golden prompts

ChatGPT, Bing and Bard are among the most popular AI chatbots. (To use ChatGPT, you need to create an OpenAI account, and it requires a subscription for its most advanced version. Bing requires you to use the Microsoft Edge web browser. Bard requires a Google account.)

Although they look simple to use, you type something in a box and you get answers! — Asking questions the wrong way will produce generic, unhelpful and, at times, downright incorrect answers.

It turns out there’s an art to typing the words and the precise framing to generate the most useful responses. I call them golden prompts.

People who get the most out of chatbots use variations of these strategies:

“Act like.” Starting your prompt with these magic words will instruct the bot to impersonate an expert. For example, typing “Act like you’re an SAT tutor” or “Act like you’re a personal trainer” will guide bots to model themselves around people in those professions.

These prompts provide additional context for the AI ​​to generate its response. The AI ​​doesn’t really understand what it means to be a tutor or personal trainer. Instead, the prompt helps the AI ​​rely on specific statistical patterns in its training data.

A weak prompt with no hints will generate less useful results. If all you type is “What should I eat this week?” the chatbot will come up with a generic list of meals for a balanced diet, like a stir-fry of turkey with a side of colorful vegetables for dinner (which, to me, sounds very “meh”).

“Tell me what else you need to do this.” To get more personalized results — for example, health tips for your specific body type or medical conditions — prompt the bot to request more information.

In the personal trainer example, a prompt could be: “Act like you’re my personal trainer. Create a weekly workout schedule and meal plan for me. Tell me what else you have The bot can then ask for your age, height, weight, dietary restrictions, and health goals to customize a week-long meal plan and fitness routine for you.

If you don’t get good answers on your first try, don’t give up just yet. Better yet, in the words of Ethan Mollick, a professor at the Wharton School at the University of Pennsylvania, treat the bot as if it were a human intern: “When it makes a mistake, point it out. and ask him to do better. .” Be forgiving and patient, and you’ll likely get better results.

Thread your chatbot conversations

Once you understand the prompts, you can make your chatbot more useful over time. The key here is to avoid treating your chatbot like a web search and starting with a new query each time. Instead, keep multiple conversation threads open and add to them over time.

This strategy is easiest with ChatGPT. Bing forces you to reset your conversations periodically, and Bard doesn’t make it easy to jump between conversation threads.

Natalie Choprasert, an entrepreneur from Sydney, Australia who advises businesses on the use of AI, uses ChatGPT as a business coach and executive assistant. She maintains separate side-by-side conversations for each of these roles.

For the Business Coaching thread, she shares insights into her professional background as well as business goals and challenges. For the executive assistant thread, she shares scheduling information, like the clients she meets.

“He’s building and training well, so when I ask him a question later, it’ll be in the right context and it’ll give me answers close to what I’m looking for,” Choprasert said.

She shared a bonus golden prompt that trained her assistants to be very useful: applying a frame. She recently read Clockwork, a book about building a business. When she asked ChatGPT-the-business-coach for advice using the “Clockwork” framework, she was delighted to see that he could incorporate the book’s principles into an action plan to develop his business.

Share your prompts

What are your golden prompts that have led to the most impressive and useful results from AI? Email us your examples. We may use your submissions in future editions of this newsletter.