Welcome back to On Tech: AI, a pop-up newsletter that teaches you about artificial intelligence, how it works, and how to use it.
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, programmers, artists, and accountants – are experimenting with the use of AI tools. Employers are posting jobs looking for people who are adept at using them. Very soon, if you haven’t already, you will have the opportunity to use AI to streamline and improve your work and personal life.
As a personal technology columnist for The Times, I’m here to help you figure out how to use these tools safely and responsibly to improve many parts of your life.
I’m going to spend today’s newsletter talking about two general approaches that will be useful in various situations.
Then, in the coming weeks, I’ll 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. .
Some common sense caveats to get you started:
If you’re concerned about privacy, leave out personal details like your name and where you work. Tech companies say that your data is used to train their systems, which means that other people may be able to see your information.
Do not share sensitive data. Your employer may have specific guidelines or restrictions, but in general, entering trade secrets or confidential information is a very bad idea.
Hallucinations: Chatbots are powered by a technology called the Large Language Model, or LLM, which derives its abilities from parsing vast amounts of digital text pulled from the Internet. Lots of things on the web are wrong, and chatbots can repeat those falsehoods. Sometimes, when trying to predict patterns from their vast training data, they can make things up.
the golden indications
ChatGPT, Bing and Bard are among the most popular AI chatbots. (To use ChatGPT, you’ll need to create an OpenAI account, and it requires a subscription for its most advanced version. Bing requires you to use Microsoft’s Edge web browser. Bard requires a Google account.)
Although they seem easy to use, you type something in a box and you get answers! — Asking questions incorrectly will produce generic, unhelpful, and sometimes completely incorrect answers.
It turns out that there is an art to writing the precise words and framing to generate the most useful responses. I call these the golden prompts.
People who are making the most of chatbots have been using variations of these strategies:
“Act as if.” Starting your ad with these magic words will tell the bot to emulate 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 a personal trainer. Instead, the notice is helping the AI draw specific statistical patterns in your training data.
A weak indicator without guidance will generate less useful results. If all you type is “What should I eat this week?” the chatbot will generate a generic list of meals for a balanced diet, such as stir-fried turkey with a side of colorful vegetables for dinner (which sounds very “meh” to me).
“Tell me what else you need to do this.” For more personalized results, for example health advice for your specific body type or medical conditions, invite the bot to request more information.
In the personal trainer example, an ad might be: “Act like you are my personal trainer. Create a weekly training regimen and meal plan for me. Tell me what else you need to do this. The bot could then ask your age, height, weight, dietary restrictions, and health goals to tailor a week-long meal plan and exercise routine for you.
If you don’t get good answers on your first try, don’t give up right away. Better yet, in the words of Ethan Mollick, a professor at the Wharton School of the University of Pennsylvania, treat the bot as if it were a human inmate:: “When he makes a mistake, point it out and ask him to do it better.” Be forgiving and patient, and you are likely to get better results.
Thread your chatbot conversations
Once you’re familiar with 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 start with a new query each time. Instead, keep multiple conversation threads open and add to them over time.
This strategy is easier with ChatGPT. Bing requires you to reset your conversations periodically, and Bard doesn’t make it as easy to jump between conversation threads.
Natalie Choprasert, an entrepreneur from Sydney, Australia who advises companies on how to use AI, uses ChatGPT as a business coach and executive assistant. She holds separate side-by-side conversations for each of these roles.
For the business coach topic, share information about your professional experience and the company’s goals and problems. For the executive assistant thread, you share scheduling information, such as the clients you’re meeting with.
“It’s built and trained correctly, so when I ask it a question later, it’ll be in the right context and give me answers that are close to what I’m looking for,” Choprasert said.
He shared an additional golden message that has empowered his attendees to be more helpful: apply a frame. You recently read “Clockwork”, a book about starting a business. When she asked ChatGPT-the-business-coach for advice using the “Clockwork” framework, he was pleased to see that he was able to incorporate the book’s principles into an action plan to expand his business. .
Share your directions
What are your golden indications that have given you the most impressive and useful results from AI? Email us your examples. We may use your submissions in future editions of this newsletter.