{"id":219866,"date":"2026-01-04T11:42:11","date_gmt":"2026-01-04T11:42:11","guid":{"rendered":"https:\/\/www.newsbeep.com\/il\/219866\/"},"modified":"2026-01-04T11:42:11","modified_gmt":"2026-01-04T11:42:11","slug":"how-to-use-chatgpt-like-a-pro","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/il\/219866\/","title":{"rendered":"How to use ChatGPT like a pro"},"content":{"rendered":"<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">Chris Stokel-Walker is a technology journalist and the author of How AI Ate the World (Canbury Press)<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">We\u2019re three years into the ChatGPT AI revolution and this tech isn\u2019t going anywhere so how do you use it properly?<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">ChatGPT uses artificial intelligence tech to generate new content from user queries. That\u2019s why the tech is known as \u201cgenerative AI\u201d. But the \u201cI\u201d in AI is a bit of a misnomer: artificial intelligence isn\u2019t actually intelligent. Like other similar apps, it looks for patterns in the training data on which it\u2019s developed, then tries to output responses \u2014 whether text, audio, video or images \u2014 that best answer the user\u2019s query.<\/p>\n<p>What to use it for<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">ChatGPT can do pretty much anything, from analysing data to planning meals. It can identify plants, suggest budget savings and ideas for work meetings. Children and university students have realised it\u2019s quite handy at homework, much to the chagrin of teachers and lecturers, many of whom use AI to try to detect cheating. <\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">It\u2019s surprisingly nuanced at offering business advice, can power through mundane admin tasks, is good at \u201cvibe coding\u201d (building apps by describing a vision rather than writing traditional line-by-line code) and will work like the clappers without ever complaining.<\/p>\n<p>Pick your model<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">ChatGPT is a good generalist and also has a variety of models. There\u2019s the instant free model, which is fine for everyday tasks, and the \u201cadvanced\u201d models, which are largely paid-for and better at deeper reasoning. You can also switch on \u201cThinking\u201d mode, which takes longer but works through problems step-by-step for more layered answers. <\/p>\n<p>Be clear about your needs<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">The key to unlocking what you want is giving it the right prompts. Asking it to adopt a persona (\u201cYou are a witty journalist who knows your stuff tasked with writing a breezy overview of ChatGPT for an audience, some of whom will have used it and some of whom absolutely will not\u201d) often gets decent results. <\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">The more detailed and specific the prompt, the better the response. Asking general questions is fine but that will get you run-of-the-mill answers. The people who get the most out of their AI chatbots \u2014 such as getting insights into vast spreadsheets of data \u2014 are those who guide the chatbot to provide answers for a specific audience, such as: \u201cProvide an executive summary of the firm\u2019s annual report for discussion at a board meeting.\u201d<\/p>\n<p>Be firm<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">AI chatbots are keen to please \u2014 to the extent that they\u2019ll often stray from reality. Telling the chatbot it has to remain factual encourages it to tamp down one of its fatal flaws: hallucination, where it makes stuff up. <\/p>\n<p>Be supportive and persistent<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">This sounds weird, but there\u2019s a strong school of thought that encouraging AI chatbots to work through a problem step by step gets better answers. Such an instruction gives it the licence to ruminate carefully, rather than rushing to try to do everything at once. Sometimes the simplest tricks work too. Say \u201cThink deeper\u201d and it will ponder longer before answering \u2014 often with better results. <\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">For example, in answer to the question \u201cWill I ever need to speak to my GP\/travel agent\/financial adviser again?\u201d AI writes: \u201cShort answer: yes. Slightly longer answer: yes but you might talk to them differently.\u201d ChatGPT is brilliant at preparing you for talking to a professional. Take medical issues. Got a letter from the hospital full of acronyms? You can paste it in and ask for a plain-English explanation. Wondering what questions to ask your GP at tomorrow\u2019s appointment? It will help you make a list. <\/p>\n<p>Humans will not be redundant<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">What AI must not become is your sole source of advice. Sticking with the medical example above, it can\u2019t examine you, it doesn\u2019t know your full history and it absolutely cannot handle emergencies. <\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">ChatGPT isn\u2019t your doctor, lawyer, therapist or financial adviser. It\u2019s the nerdy friend who\u2019s read everything, types at 200 words a minute and is always online \u2014 but still needs you to exercise judgment. <\/p>\n<p>The rivals<\/p>\n<p class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">If you\u2019re a generative AI newbie it\u2019s likely that you\u2019re using ChatGPT. But it has rivals including Claude, developed by Anthropic, which was founded by former OpenAI employees, and Gemini, Google\u2019s AI model.<\/p>\n<p id=\"last-paragraph\" class=\"responsive__Paragraph-sc-1pktst5-0 gaEeqC\">They\u2019re also good at different tasks. The Gemini AI chatbot has an alarmingly lifelike image generator, ideal for PowerPoint presentations. And if you want to pore over dense documents, Google\u2019s NotebookLM is the best choice \u2014 it produces linked footnotes to show you its exact sources for the answers it has reached.<\/p>\n","protected":false},"excerpt":{"rendered":"Chris Stokel-Walker is a technology journalist and the author of How AI Ate the World (Canbury Press) We\u2019re&hellip;\n","protected":false},"author":2,"featured_media":219867,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[345,343,344,85,46,125],"class_list":{"0":"post-219866","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-il","12":"tag-israel","13":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/219866","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/comments?post=219866"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/219866\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media\/219867"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media?parent=219866"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/categories?post=219866"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/tags?post=219866"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}