This is another installment of 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 Kate Metz and Kevin Roos explained the inner workings of artificial intelligence, 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 artificial intelligence to its full potential.
People from all walks of life — students, programmers, artists, and accountants — are experimenting with using artificial intelligence tools. Employers post job openings to people who know how to hire them. Very soon, if you haven’t already, you’ll have the opportunity to use artificial intelligence to streamline and improve your work and personal life.
As the personal technology columnist for The New York Times, I’m here to help you discover how to use these tools safely and responsibly to improve many aspects of your life.
In today’s bulletin I’m going to talk about two general criteria that are useful in a variety of situations.
Next, over the next few weeks, I’ll offer more specific advice for different aspects of your life, such as parenting and family life, work, organization in your personal life, learning/education, creativity, and shopping.
Some common sense warnings to get you started:
-
If you are concerned about privacy, avoid personal information such as your name and place of work. Tech companies say your data is used to train their computers, which means other people may see your information.
-
Do not share sensitive 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 based on technology called „large linguistic models” (LLMs), which derive their abilities from analyzing vast amounts of digital text taken from the web. Many things are wrong online, and chatbots can repeat those lies. Sometimes, when they try to predict patterns from their large amounts of data from their training, they can make things up.
Gold’s instructions or 'incitements’
ChatGPT, Ping Y Bart Some of the most popular artificial intelligence chatbots. (To use ChatGPT, you need to create an OpenAI account, and to use its advanced version requires a subscription. Bing asks you to use Microsoft’s Edge browser. For Bard, you need to have a Google Account.)
Although they seem easy to use—you just type something into a box and you get answers!—asking questions the wrong way can lead to generic, unhelpful, and sometimes downright wrong answers.
It turns out that there is an art to typing words and defining precise frames to create the most effective responses. I use them as instructions (or, in English, Stimulates) Gold.
Variations of the following strategies are used by many users of chatbots:
„Act like it.” If you start your prompt with these magic words, the robot will imitate an expert. For example, if you type “act as a tutor for college entrance exams” or “act as a personal trainer,” the robots will be modeled after people in those occupations.
These instructions provide additional context for the AI to develop its response. In fact, artificial intelligence doesn’t understand what it means to be a personal tutor or coach. On the contrary, the Immediately It helps artificial intelligence to draw specific statistical patterns from your training data.
Weak instruction without guidance will produce less effective results. „What should I eat this week?” If you type that, the chatbot will give you a typical list of meals for a balanced meal, such as stir-fried turkey with colorful vegetables for dinner (which, to me, sounds like something without much interest).
„Tell me what else to do with it.” For more personalized results—for example, health tips for your specific body type or specific condition—call the bot to request additional information.
In the personal trainer example, an instruction might be: “You act as my personal trainer. Create a weekly exercise and meal plan for me. Tell me what else you need to do with this. At that time, the robot will create a meal and exercise plan for you to follow for the week based on your age, height, weight, dietary restrictions and health goals.
If you don’t get good answers in your first attempt, don’t give up right away. Even better, in the words of Ethan Molick, a professor at the Wharton School of the University of Pennsylvania, Treat the bot like a human trainer: „When he makes a mistake, point it out and tell him to do better.” Be forgiving and patient and you will get better results.
Continue your chatbot’s conversations
Once you learn how to use the instructions, you can make your chatbot more effective over time. It’s important to avoid treating the chatbot like a web search and starting a new query each time. Instead, keep multiple conversation threads open and add instructions over time.
This strategy is easy with ChatGPT. Bing requires you to restart your conversations frequently, and Bard doesn’t make it easy to jump between conversation threads.
Natalie Choprasert, an entrepreneur from Sydney, Australia who advises companies on how to use artificial intelligence, uses ChatGPT as a business coach and executive assistant. There are separate dialogs for each of these features.
In The Business Coach, he shares his professional experience and information about company goals and issues. In the case of an executive assistant, share information about your schedule, such as clients you meet.
„He builds and trains properly, so when I ask him a question later, he’ll be in the right context and give me answers that are close to what I’m looking for,” Choprasert said.
Sopracert shares an additional golden rule that he trains his assistants to be more effective: Use a frame of reference. Recently read Clockwork, a book on business creation. When he asked ChatGPT, a business coach, to advise him on using the framework ClockworkHe was delighted to find that he could incorporate the principles in the book into an action plan to expand his business.
Brian X. Chen is a consumer technology columnist. He reviews products and writes Tech Fix, a column to address technology-related issues. Before joining The Times in 2011, he reported on the wireless industry for Apple and Wired. @bxchen