Welcome 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 friends Cade Metz and Kevin Ross explain the inner workings of AI., which includes chatbots such as OpenAI’s ChatGPT, Microsoft’s Bing, and Google’s Bard. Now we’re back with a new mission: to help you learn how to harness AI to its full potential.
People from all walks of life – students, coders, artists and accountants – are experimenting with how to use AI tools. Employers are posting jobs looking for people who are adept at using them. Very soon, if not already, you’ll have the chance to use AI to streamline and improve your work and personal life.
As The Times’ personal tech columnist, I’m here to help you learn how to use these devices safely and responsibly to improve many parts of your life.
I’m going to start today’s newsletter talking about two general approaches that will be useful in many situations.
Then, in the coming weeks, I’ll give you more specific tips for different aspects of your life, including parenting and family life, work, organizing your personal life, learning/education, creativity, and shopping.
Some common sense warnings to get you started:
-
If you’re concerned about privacy, leave out personal details like your name and where you work. Tech companies say your data is used to train their systems, which means other people can see your information.
-
Do not share confidential data, Your employer may have specific guidelines or restrictions, but in general, it’s a very bad idea to record trade secrets or sensitive information.
-
Hallucination: Chatbots are powered by a technology called giant language model, or LLM, which derives its capabilities by analyzing large amounts of digital text from the Internet. There are many things wrong on the web, and chatbots can repeat those untruths. Sometimes, when trying to predict patterns from your huge training data, they can make things,
golden signals
chatgpt, bing And forage Among the most popular are AI chatbots. (To use ChatGPT, you’ll need to create an OpenAI account, and that requires a subscription to its most advanced version. Bing requires you to use Microsoft’s Edge web browser. Bard requires a Requires Google Account.)
They look simple to use though – you type something into a box and get answers! – Asking questions in the wrong way will lead to generic, unhelpful and, sometimes, downright wrong answers.
It turns out that there’s an art to typing in the exact words and framing to generate the most useful answers. I call these golden signals.
Those who are getting the most out of chatbots are using different variations of these strategies:
“Assume it.” Beginning your prompt with these magic words will instruct the bot to emulate an expert. For example, “Act as if you’re a tutor for the SAT” or “Act as if you’re a personal trainer” will guide bots to model themselves around people in those occupations.
These signals provide additional context for the AI to generate its response. AI doesn’t really understand what it means to be a tutor or personal trainer. Instead, Prompt is helping the AI draw on specific statistical patterns in its training data.
A weak signal without any guidance will produce less helpful results. If all you type is “what should I eat this week?” The chatbot will come up with a general list of meals for a balanced diet, such as a turkey stir fry with colorful vegetables for dinner (which, to me, sounds very “meh”).
“Tell me what else you need to do it.” To get results that are more personalized – for example, health advice for your specific body type or medical conditions – invite the bot to request more information.
In the personal trainer example, a prompt might be: “Act as if you are my personal trainer. Create a weekly workout regimen and meal plan for me. Tell me what else do you need to do this. The bot can then ask you about your age, height, weight, dietary restrictions and health goals to create 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 right away. Better yet, in the words of Professor Ethan Molick of the Wharton School of the University of Pennsylvania, Treat bot as if it were a human intern: “When it makes a mistake, point it out and tell it to do better.” Be forgiving and patient, and you’re likely to get better results.
Thread your chatbot conversations
After getting the prompts down, you can make your chatbot more useful over time. The key here is to avoid treating your chatbot as a web search and starting over with a new query each time. Instead, keep several threads of conversation open and add to them over time.
This strategy is easiest with ChatGPT. Bing requires you to reset your conversation from time to time, and Bard doesn’t make it so easy to jump between conversation threads.
Natalie Choprasert, an entrepreneur in Sydney, Australia who advises companies on how to use AI, uses ChatGPT as a business coach and an executive assistant. She simultaneously carries on different dialogues for each of these roles.
For the Business Coach thread, she shares information about her professional background and company goals and problems. For the executive assistant thread, she shares scheduling information, such as the clients she’s meeting.
“It builds and trains properly, so when I ask it a question later, it will be in the right context and it will give me an answer close to what I’m looking for,” Choprasert said.
She shared a bonus golden prompt that’s trained her assistants to be extra helpful: Implement a framework. She recently read “Clockwork,” a book about setting up a business. When she asked chatgpt-the-business-coach for advice using “Clockwork’s” framework, she was pleased to see that it could incorporate the principles from the book into an action plan for expanding her company. .
share your hints
What are your golden tips that have given you the most impactful, useful results from AI? email us your examples, We may use your submission in future editions of this newsletter.
