Aaron Mok

<ul><li>Is your <a href="https://www.businessinsider.com/guides/tech/how-to-tell-if-iphone-has-water-damage">iPhone wet</a>? If so, don't put it in a bowl of rice.&nbsp;</li><li>Apple's new support doc says rice can actually cause more damage to your iPhone.&nbsp;</li><li>The company also discourages drying your damp iPhone with a blow dryer or paper towel.&nbsp;</li></ul>

Earlier this year, <a href="https://www.businessinsider.com/apple">Apple</a> quietly published new guidelines on what to do when water gets into your iPhone. Typically, when phones, or any electronic devices, get wet, one common course of action is to put them in uncooked rice. The theory is that the raw grains can absorb the moisture.

But Apple's latest <a href="https://support.apple.com/en-us/102643">support document</a> discourages iPhone users from doing that, saying that small grains of rice could actually damage your phone if, say, particles get lodged into the ports.

According to Apple, you also shouldn't try to dry your moist iPhone by inserting a "foreign object" like a cotton swab or paper towel into the port, or use an external heat source like a blow dryer.

Still, the updated guidelines offer a few suggestions on what users can safely do. For example, if you plug your iPhone into a wall outlet with a lightning accessory and a "Liquid Detected" alert appears, immediately unplug the cable from both ends.

Once the cable is disconnected, gently tap your iPhone against your hand with the port facing the floor to allow excess liquid to escape. After that, store the phone in a dry area where there's some airflow for at least 30 minutes, then try charging it.

If the liquid detection alert appears a second time, unplug and leave your phone to fully dry for up to 24 hours. After waiting, try charging the phone again.

If the phone still isn't charging, momentarily unplug the cable from the adapter and the adapter from the wall, then reconnect them.

And if all else fails, you may need to bring your iPhone to a repair shop or, at worst, consider getting a replacement.

Nevertheless, your wet phone may still have a likely chance of surviving. A video of an <a href="https://www.businessinsider.com/iphone-6-drop-test-video-2014-9">iPhone 6 drop test</a> showed that the 2014 version continued to work after being dunked underwater. Years later, the <a href="https://www.businessinsider.com/apple-iphone-11-pro-battery-life-consumer-reports-rankings-2019-10">iPhone 11 Pro</a> passed a similar water resistance test.

Apple didn't immediately respond to a request for comment from Business Insider before publication.

Apple says putting your wet iPhone in rice can actually do more damage to the device.dontree_m/Getty Images

Have you ever been told to put your <a href="https://www.businessinsider.com/little-known-iphone-feature-helped-rescue-lost-hiker-california-2024-2">iPhone</a> in a bowl of rice after accidentally dropping it in the sink or — even worse — toilet? You might just be making the problem worse.

Don't dry your damp iPhone in a bowl of rice, Apple says

<ul><li><a href="https://www.businessinsider.com/everything-you-need-to-know-about-chat-gpt-2023-1">ChatGPT</a> has taken the world by storm — but some struggle to get the chatbot to do what they want.</li><li>Insider asked AI enthusiasts how they interact with the chatbot to produce desirable outputs.</li><li>Here are 12 tips for crafting the best ChatGPT prompts, from assigning it a persona to being polite.</li></ul>

At work, people have used the OpenAI product to <a data-link-role-code="open_new_tab" href="https://www.businessinsider.com/chatgpt-amazon-employees-use-ai-chatbot-software-coding-customer-questions-2023-1">develop code</a>, <a data-link-role-code="open_new_tab" href="https://www.businessinsider.com/marketing-industry-using-ai-save-time-money-boost-productivity-study-2023-6">generate marketing materials</a>, and <a data-link-role-code="open_new_tab" href="https://www.businessinsider.com/high-school-math-science-teacher-uses-openai-chatgpt-education-learning-2023-3">create lesson plans</a>. It's become so popular that <a data-link-role-code="open_new_tab" href="https://www.businessinsider.com/jobs-roles-companies-want-ai-chatgpt-experience-salary-2023-6">companies are now hiring workers who have ChatGPT expertise</a> to boost their bottom lines.

And in their everyday lives, people are turning to the chatbot for help with <a href="https://www.insider.com/chatgpt-fitness-ai-love-exercise-2023-5">losing weight</a>, <a href="https://www.businessinsider.com/how-men-are-using-ai-for-dating-profiles-messaging-study-2023-6">landing dates</a>, and <a href="https://www.insider.com/chatgpt-anti-aging-skincare-routine-wrinkles-ai-2023-6">delaying aging.</a>

But ChatGPT doesn't always produce desirable outcomes, and the tech can be <a href="https://www.businessinsider.com/ai-chatbot-chatgpt-google-microsofty-lying-search-belief-2023-2">prone to errors and misinformation.</a>

It all comes down to the prompts users put into ChatGPT.

"If you really want to generate something that is going to be useful for you, you need to do more than just write a generic sentence," Jacqueline DeStefano-Tangorra, a consultant who uses ChatGPT to secure new contracts, <a href="https://www.businessinsider.com/consultant-saved-time-using-chatgpt-landed-new-deals-business-2023-5">told Insider</a>.

Insider asked AI enthusiasts, ChatGPT coaches, and workers who use the chatbot for tips on how to get ChatGPT to do what you want.

<h2>Here are 12 ways you can write better ChatGPT prompts.&nbsp;</h2>

<h3>1. Assign ChatGPT a specific&nbsp;role</h3>

ChatGPT works best when you assign it a persona — such as a specific job role — Jason Gulya, an AI council chair at Berkeley College who teaches clients how to use ChatGPT, said.

Rob Cressy, the founder of the AI-coaching firm GPT Leaders, told Insider to "talk to ChatGPT like an employee" to help accomplish particular goals or tasks.

To do this, Gulya suggests that users write a prompt that includes a specific, concrete description of the persona you want the chatbot to take on. Begin your prompt with "act as a professor" or "act as a marketing professional," followed by a description of the desired outcome.

<h3>2. Be specific — and only give the bot one task at a time</h3>

Once you give ChatGPT a role, craft the prompt so it can accomplish a singular task such as writing a 300-word cover letter or generating a recipe for a protein-packed dinner.

"Don't ask it to do too much at once," Cressy said.

If you're a marketing professional, and you want ChatGPT to build a list of emails, <a href="https://www.businessinsider.com/chatgpt-courses-instruction-academic-lucrative-side-hustle-2023-4">Peggy Dean, an artist who runs a ChatGPT course for creatives</a>, recommends crafting what she calls a "power prompt," a concise and detailed prompt.

If asking ChatGPT to brief a marketing campaign, she said she'd include target audiences, key features, and calls to action.

If asking the chatbot to come up with an email list and calls to action, she said she'd say:

"Pretend you are an expert email marketer and your client is a [role] specializing in [offerings] for [target audience]. Your goal is to build a robust email list in order to accomplish [goal]. Your client uses [platform(s)] to reach their audience. Come up with [details or quantity] ideal call to action ideas of [freebies or lead magnets] your client can provide.

"It's crucial to have a clear idea of what you hope to achieve," Dean told Insider.

<h3>3. Refine your prompts based on a previous outputs</h3>

If ChatGPT's response isn't quite what you're looking for, Cressy said to build on its output by fine-tuning the initial prompt. He calls this process "peeling back an onion."

"Don't be afraid to refine your prompts," <a href="https://www.businessinsider.com/consultant-saved-time-using-chatgpt-landed-new-deals-business-2023-5">DeStefano-Tangorra</a> said. "If the initial output doesn't match your expectation, rephrase the prompt, add more detail, or clarify the context."

If the answer to a prompt asking ChatGPT to "suggest a good book" is too vague, refine it to something like: "As someone who loves mystery novels with strong female leads, like Agatha Christie's Miss Marple series, can you suggest other similar books that I may enjoy?"

<h3>4. Provide context&nbsp;</h3>

ChatGPT prompts should include context such as historical information, user profiles, preferences, or any relevant details to guide its response, DeStefano-Tangorra said. The more specific, the better.

Asking ChatGPT to "suggest dinner recipes," will lead to a generic output. Instead, DeStefano-Tangorra suggests tweaking that prompt to say: "As someone who loves trying out new cuisines and has a particular fondness of spicy food, can you suggest an exciting dinner menu for my next weekend get-together with my friends?"

If you want to apply ChatGPT to your business, Cressy suggests creating a "best-practices document" that includes details on who you are, what you do, and what your brand voice sounds like. That way, users can copy and paste the information into the chatbot whenever they start a new conversation.

Instead of asking ChatGPT to "create me a marketing strategy" the prompt should say "I am a world-class [role] who helps [target audience] for business growth. Our brand voice is friendly, positive, inspiring, brand-safe, conversational. Create me a marketing strategy to help build my brand on Facebook and Instagram by leveraging my podcast."

<h3>5. Break down the desired output into a series of steps</h3>

While it's best for prompts to be specific and include context, writing a long prompt can be counterproductive, Gulya said.

"More often than not, a long mega-prompt does not give the desirable output," he said.

To avoid this, Gulya suggests breaking down the desired output into a series of steps. That way, if the chatbot generates errors, the user can pinpoint what exactly the chatbot may not understand.

"This allows you to validate each step before proceeding, course-correcting when necessary," Gulya said.

If the goal is to use ChatGPT to generate a widely read blog post, the user should ask the chatbot to first research which SEO terms will most likely make the article appear at the top of search-engine results. In a separate prompt, ask it to apply what it learned to the blog post.

<h3>6. Ask ChatGPT for advice on how to prompt it better&nbsp;</h3>

To ensure your prompt is as thorough as it can be, Dean suggested asking ChatGPT what other details it needs from the user to produce the best output.

To do this, Dean suggests adding a line to your prompt that follows this template: "If I want to [desired outcome], what prompts should I share with ChatGPT in order to get the best results?"

Once ChatGPT has generated an output, tell the chatbot what you like and dislike about the output and ask it to "request additional results, edits, or tweaks," she said.

<h3>7. Prioritize clarity and precision&nbsp;</h3>

DeStefano-Tangorra suggests that ChatGPT users "explicitly outline your expectations within the prompt" by adding precise words.

"Clear and specific prompts lead to more relevant and useful responses," she said.

The prompt "compare and contrast using an oven versus a microwave for preparing dinner," should be tweaked to "can you compare and contrast the advantages and disadvantages of using a traditional oven versus a microwave for preparing a family dinner?"

<h3>8. Use a thesaurus</h3>

To write your prompt with precision, Anna Bernstein, a prompt engineer at the generative-AI writing tool Copy.ai, suggests using a thesaurus to find the words that can increase your chances of getting what you want out of the chatbot.

"Don't give up on a concept just because your first prompt didn't get the result you wanted," <a data-link-role-code="open_new_tab" href="https://www.businessinsider.com/how-to-write-better-ai-chatgpt-prompts-according-prompt-engineer-2023-3">Bernstein previously told Insider</a>. "Often, finding the right word or phrasing can unlock what you're doing."

READ MORE: <a data-link-role-code="open_new_tab" href="https://mssdicuss.com/9-seo-web-chrome-extensions-you-need/">Best chrome extension 2024</a>

<h3>9. Pay attention to verbs</h3>

A thesaurus can help you find verbs that clearly express your intent. That way, the AI has a better chance of fully understanding your request, Bernstein said.

She said that a prompt including the phrase "condense this" is stronger than "rewrite this to be shorter."

<h3>10. Be polite, but direct&nbsp;</h3>

While ChatGPT users may have different conversational styles, Gulya said he finds that talking to the AI using polite, direct language — as if he's writing to a friend — yields the best results.

"Doing so puts me in a more collaborative, more flexible mindset," he said.

When interacting with the chatbot for, say, advice on how college professors can enhance their skillsets, Gulya suggests writing flattering comments such as, "You're magnificent at seeing the root causes in faculty member's anxieties about artificial intelligence."

After the chatbot spits out a response you like, express gratitude by saying something like, "This is great. Thank you so much!" followed by a request to make revisions to its output.

<h3>11. Check and tweak the copy's tone and reading level&nbsp;</h3>

If you're using ChatGPT to generate copy or captions for social-media posts, make sure to tweak its tone so the content resonates with your target audience, <a href="https://www.businessinsider.com/chatgpt-hacks-reduce-workload-example-prompts-2023-4">Ashley Couto, a marketing professional who uses the chatbot to reduce her workload, told Insider.</a>

Couto finds that the best marketing copy reads at a fifth-or sixth-grade level, which includes "short sentences and paragraphs, a conversational tone, and simple language."

To do this, Couto recommends asking ChatGPT to "change the reading level and tone" after it spits out a response.

<h3>12. Feed ChatGPT an outline&nbsp;</h3>

If you want ChatGPT to generate longer posts, Couto suggests giving the AI a specific structure and outline. She said the more specific you can be with your instructions, the better its output will be.

Here's one prompt Couto uses to generate a company blog post:

"Following this story structure — 1. Capture the heart, 2. Set up a tension, 3. Resolve the tension, 4. Conclude by offering value — write a 1,000-word story at a grade-five reading level in the first person using the following information."

CEOs are turning to ChatGPT as a miracle solution to their business problems.Hannes P Albert/Picture Alliance via Getty Images

Here are 12 tips for crafting the best ChatGPT prompts, from assigning it a persona to being polite.

12 ways to get better at using ChatGPT: Comprehensive prompt guide

<ul><li>Workers using OpenAI's ChatGPT may actually perform more poorly than those who don't, new BCG research finds.</li><li>That's because some workers take the AI chatbot's outputs at face value and don't check for errors.</li><li>BCG's findings may be a cautionary tale for <a href="https://www.businessinsider.com/ai-tools-make-your-job-easier-boost-productivity-work-chatgpt-2023-5">workers turning to AI.</a></li></ul>

Using AI at work can actually hurt your job performance — if it's used for tasks outside of its capabilities, <a href="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4573321&amp;utm_source=newsletter&amp;utm_medium=email&amp;utm_campaign=newsletter_axiosam&amp;stream=top">new research from Boston Consulting Group found</a>.

A group of researchers from BCG, Harvard, Wharton, and MIT conducted an experiment to see how access to AI impacts white-collar workers' productivity and quality of work.

To test this, researchers randomly assigned 758 consultants at BCG across one of three groups: one with no access to AI; one with access to <a href="https://www.businessinsider.com/gpt-4-openai-model-api-details-2023-3">ChatGPT powered by GPT-4</a>; and one with access to ChatGPT, as well as instructional videos and documents on prompt engineering strategies.

After establishing performance baselines, consultants in each group were assigned one of two categories of tasks.

One category included 18 tasks that exist "inside the frontier" of what the AI can do, like brainstorming innovative beverage concepts or coming up with a thorough business plan for a new footwear concept.

The other category contained more open-ended tasks that exist "outside the frontier" of AI's capabilities. While "consultants would excel" at these tasks, "AI would struggle without extensive guidance," the study said.

For example, consultants assigned this set of tasks were asked to offer recommendations to the CEO of a hypothetical company by using internal financial data and interviews with company insiders — information the AI didn't have access to.

Researchers found stark differences in the results of the three groups, depending on their access to ChatGPT.

For tasks "inside the frontier," consultants using AI were "significantly more productive" and "produced significantly higher quality results" than those who weren't using the chatbot.

However, consultants using AI to complete tasks "outside the frontier" were "19 percentage points less likely to produce correct solutions compared to those without AI." That's because the consultants with AI were found to indiscriminately listen to its output — even if the answers were wrong.

These findings demonstrate AI's "uneven" capabilities.

While the study's findings show that AI is "exceedingly good" at helping humans with some tasks, humans should exercise caution when using the technology to avoid errors, Saren Rajendran, one of the researchers involved in the study, told Insider in an email.

"We should be mindful when using GenAI," he added.

BCG's findings demonstrate a cautionary tale for workers thinking about using ChatGPT to help do their jobs. Since ChatGPT came out last November, workers across industries have been <a href="https://www.businessinsider.com/ai-chatgpt-jobs-side-hustle-make-more-money-accessible-2023-8">using the AI chatbot</a> — <a href="https://www.businessinsider.com/chatgpt-secret-productivity-work-ai-technology-ban-employees-coworkers-job-2023-8">sometimes without telling their bosses</a> — to <a href="https://www.businessinsider.com/chatgpt-amazon-employees-use-ai-chatbot-software-coding-customer-questions-2023-1">develop code</a>, <a href="https://www.businessinsider.com/how-use-ai-beginner-easy-increase-productivity-2023-8">create marketing materials</a>, and <a href="https://www.businessinsider.com/high-school-math-science-teacher-uses-openai-chatgpt-education-learning-2023-3">generate lesson plans</a>.

However, ChatGPT's outputs aren't perfect and can contain "<a href="https://www.businessinsider.com/ai-chatbot-chatgpt-google-microsofty-lying-search-belief-2023-2">hallucinations</a>."

Tech publicationCNET was put on blast earlier this year after readers noticed that a number of its <a href="https://www.businessinsider.com/tech-site-issued-corrections-after-ai-writing-got-facts-wrong-2023-1">AI-generated articles included factual errors</a>.

As of September 28, media watchdog <a href="https://www.newsguardtech.com/special-reports/ai-tracking-center/">NewsGuard</a> has identified 487 "unreliable" AI-generated news sites with "little to no human oversight."

In an ad for Google's Bard, <a href="https://www.businessinsider.com/google-ad-ai-chatgpt-rival-bard-gives-inaccurate-answer-2023-2">the AI chatbot made a factual error</a> when asked about the James Webb Space Telescope.

AI-generated errors may only get worse: In a recent paper, AI researchers found that <a href="https://www.businessinsider.com/ai-model-collapse-threatens-to-break-internet-2023-8">generative AI models could soon be trained on AI-generated content </a>— a phenomenon they call "model collapse." The result could be more low-quality outputs in the near future.

"As the boundaries of AI capabilities continue to expand, often exponentially, it becomes incumbent upon human professionals to recalibrate their understanding of the frontier and for organizations to prepare for a new world of work combining humans and AI," the researchers wrote.

Educators have been struggling to get a grips with the rise of generative AI tools such as ChatGPTFrank Rumpenhorst/picture alliance via Getty Images

If you're using <a href="https://www.businessinsider.com/ai-tools-make-your-job-easier-boost-productivity-work-chatgpt-2023-5">ChatGPT as a shortcut at work</a>, you may want to be extra careful.

OpenAI's ChatGPT can actually make workers perform worse, a new study found

Politics

Local

Metro

World

News 

Celebrities

Music

Movies

Entertainment

Fashion

Beauty & Health

Relationships & Weddings

Food & Travel

Lifestyle

Domestic

International 

Business

Sports 

Celebrity Picks

Pulse Picks

Pulse Marketing

Explore categories

Checkout our authors for the latest content across entertainment, sports, business and more. Be first to receive exclusive updates with your free subscription straight to your phone | Pulse Nigeria 

Authors | Pulse Nigeria

| Pulse Nigeria

Read the latest news across entertainment, sports, business and more. Be first to receive exclusive updates with your free subscription straight to your phone | Pulse Nigeria

Breaking News & Top Stories | Pulse Nigeria

Pulse Nigeria is the most followed news and entertainment platform, informing and engaging young Nigerians round the clock, providing updates by the hour.

Pulse Nigeria

Search for the latest content across entertainment, sports, business and more. Be first to receive exclusive updates with your free subscription straight to your phone | Pulse Nigeria

Search Results | Pulse Nigeria

Watch the latest videos across entertainment, sports, business and more. Be first to receive exclusive updates with your free subscription straight to your phone | Pulse Nigeria

Aaron Mok

Articles written by the author

Don't dry your damp iPhone in a bowl of rice, Apple says

12 ways to get better at using ChatGPT: Comprehensive prompt guide

OpenAI's ChatGPT can actually make workers perform worse, a new study found