Hey there, friends! Here are some quick tips from the BBC article about how to talk to AI. First, study some useful phrases from it: 🌟 options that vary — варианты, которые отличаются друг от друга (Give me three options that vary in tone.) 🌟 provide a sample — предоставить образец (If you want good results, provide a sample of your writing.) 🌟 a compelling job listing — привлекательная/убедительная вакансия (We need to write a compelling job listing to find a good designer.) 🌟 make something less accurate — сделать что-то менее точным (Role-playing can sometimes make AI less accurate.) 🌟 lean towards something — склоняться к чему-то (при выборе) (I'm leaning towards the Toyota, but I'm still not sure.) Now, here are the tips: How to talk to your chatbot There are some real ethical problems with AI, but learning to get what you want faster is a great skill. Here are some tips: 1️⃣Ask for multiple options Don't ask for one answer. Tell the AI to give you multiple options that vary in some important way. This forces you to think about what you actually like. 2️⃣ Give examples Provide the AI with a sample whenever possible. Don't just say "write an email." Give it your emails (without any sensitive info!) and say: "Here are 10 emails I've sent in the past, use my writing style." 3️⃣ Ask for an interview If you need a compelling job listing, tell the AI: "Ask me questions, one at a time, until you have enough info to write it." By doing it one question at a time, it can adapt to your answers. 4️⃣Be careful about role-playing When you need one right answer, telling the AI to act like an expert can actually make models less accurate. But for brainstorming, advice and exploratory problem solving it’s great! 5️⃣ Stay neutral If you're trying to decide between two cars, don't say you're leaning towards the Toyota. Otherwise, the AI will just agree with you. 👇 Let’s practice! Выбирайте любой вопрос (или все пять!) и используйте новые фразы в ответах: 1) Have you ever used AI to brainstorm options that vary for a project or trip? How did it go? 2) What kind of sample would you need to provide to an AI if you wanted to use it reply to your friends? Is it ethical to do so? 3) Do you think it's compelling for companies to replace most workers with AI?? 4) In your experience, what kinds of tasks make AI less accurate? (Science? Cooking recipes? Coding? Psychology?) 5) Think of a difficult choice you have to make soon. Which option are you leaning towards and why?