Don't blame the Bot: Master your AI prompts for better results
If you're using ChatGPT but getting mediocre results, don't blame the chatbot. Instead, try sharpening up your prompts.
Generative AI chatbots such as OpenAI's ChatGPT, Google's Gemini and Anthropic's Claude have become hugely popular and embedded into daily life for many users. They're powerful tools that can help us with so many different tasks.
What you shouldn't overlook, however, is that a chatbot's output depends on what you tell it to do, and how. There's a lot you can do to improve the prompt — also known as the request or query — that you type in.
Here are some tips for general users on how to get higher quality chatbot replies, based on tips from the AI model makers: ChatGPT can't read your mind. You need to give it clear and explicit instructions on what you need it to do.
Unlike a standard Google search, you can't just ask for an answer based on some keywords. And you'll need to do more than just tell it to, say, 'design a logo' because you'll end up with a generic design. Flesh it out with details on the company that the logo is for, the industry it will be used in and the design style you're going for.
'Ensure your prompts are clear, specific, and provide enough context for the model to understand what you are asking,' ChatGPT maker OpenAI advises on its help page. 'Avoid ambiguity and be as precise as possible to get accurate and relevant responses.' Think of using a chatbot like holding a conversation with a friend. You probably wouldn't end your chat after the first answer. Ask follow-up questions or refine your original prompt.
OpenAI's advice: 'Adjust the wording, add more context, or simplify the request as needed to improve the results.' You might have to have an extended back-and-forth that elicits better output. Google advises that you'll need to try a 'few different approaches' if you don't get what you're looking for the first time.
'Fine-tune your prompts if the results don't meet your expectations or if you believe there's room for improvement,' Google recommends in its prompting guide for Gemini. 'Use follow-up prompts and an iterative process of review and refinement to yield better results.' When making your request, you can also ask an AI large language model to respond in a specific voice or style.
'Words like formal, informal, friendly, professional, humorous, or serious can help guide the model,' OpenAI writes.
You also tell the chatbot the type of person the response is aimed at.
These parameters will help determine the chatbot's overall approach to its answer, as well as the tone, vocabulary and level of detail.
For example, you could ask ChatGPT to describe quantum physics in the style of a distinguished professor talking to a class of graduate students. Or you could ask it to explain the same topic in the voice of a teacher talking to a group of schoolchildren.
However, there's plenty of debate among AI experts about these methods. On one hand, they can make answers more precise and less generic. But an output that adopts an overly empathetic or authoritative tone raises concerns about the text sounding too manipulative.
Give the chatbot all the background behind the reason for your request.
Don't just ask: 'Help me plan a weeklong trip to London.' ChatGPT will respond with a generic list of London's greatest hits: historic sites on one day, museums and famous parks on another, trendy neighborhoods and optional excursions to Windsor Castle. It's nothing you couldn't get from a guidebook or travel website, but just a little better organized.
But if, say, you're a theatre-loving family, try this: 'Help me plan a weeklong trip to London in July, for a family of four. We don't want too many historic sites, but want to see a lot of West End theatre shows.
We don't drink alcohol so we can skip pubs. Can you recommend mid-range budget hotels where we can stay and cheap places to eat for dinner?' This prompt returns a more tailored and detailed answer: a list of four possible hotels within walking distance of the theater district, a seven-day itinerary with cheap or low-cost ideas for things to do during the day, suggested shows each evening, and places for an affordable family dinner.
You can tell any of the chatbots just how extensive you want the answer to be. Sometimes, less is more.
Try nudging the model to provide clear and succinct responses by imposing a limit. For example, tell the chatbot to reply with only 300 words.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Qatar Tribune
4 hours ago
- Qatar Tribune
How a GOP rift over tech regulation doomed a ban on state AI laws in Trump's tax bill
Agencies A controversial bid to deter states from regulating artificial intelligence for a decade seemed on its way to passing as the Republican tax cut and spending bill championed by President Donald Trump worked its way through the U.S. Senate. But as the bill neared a final vote, a relentless campaign against it by a constellation of conservatives — including Republican governors, lawmakers, think tanks and social groups — had been eroding support. One, conservative activist Mike Davis, appeared on the show of right-wing podcaster Steve Bannon, urging viewers to call their senators to reject this 'AI amnesty' for 'trillion-dollar Big Tech monopolists.' He said he also texted with Trump directly, advising the president to stay neutral on the issue despite what Davis characterized as significant pressure from White House AI czar David Sacks, Commerce Secretary Howard Lutnick, Texas Sen. Ted Cruz and others. Conservatives passionate about getting rid of the provision had spent weeks fighting others in the party who favored the legislative moratorium because they saw it as essential for the country to compete against China in the race for AI dominance. The schism marked the latest and perhaps most noticeable split within the GOP about whether to let states continue to put guardrails on emerging technologies or minimize such the end, the advocates for guardrails won, revealing the enormous influence of a segment of the Republican Party that has come to distrust Big Tech. They believe states must remain free to protect their citizens against potential harms of the industry, whether from AI, social media or emerging technologies. 'Tension in the conservative movement is palpable,' said Adam Thierer of the R Street Institute, a conservative-leaning think tank. Thierer first proposed the idea of the AI moratorium last year. He noted 'the animus surrounding Big Tech' among many Republicans. 'That was the differentiating factor.'The Heritage Foundation, children's safety groups and Republican state lawmakers, governors and attorneys general all weighed in against the AI moratorium. Democrats, tech watchdogs and some tech companies opposed it, too. Sensing the moment was right on Monday night, Republican Sen. Marsha Blackburn of Tennessee, who opposed the AI provision and had attempted to water it down, teamed up with Democratic Sen. Maria Cantwell of Washington to suggest striking the entire proposal. By morning, the provision was removed in a 99-1 whirlwind demise of a provision that initially had the backing of House and Senate leadership and the White House disappointed other conservatives who felt it gave China, a main AI competitor, an advantage. Ryan Fournier, chairman of Students for Trump and chief marketing officer of the startup Uncensored AI, had supported the moratorium, writing on X that it 'stops blue states like California and New York from handing our future to Communist China.' 'Republicans are that way ... I get it,' he said in an interview, but added there needs to be 'one set of rules, not 50' for AI innovation to be companies, tech trade groups, venture capitalists and multiple Trump administration figures had voiced their support for the provision that would have blocked states from passing their own AI regulations for years. They argued that in the absence of federal standards, letting the states take the lead would leave tech innovators mired in a confusing patchwork of rules. Lutnick, the commerce secretary, posted that the provision 'makes sure American companies can develop cutting-edge tech for our military, infrastructure, and critical industries — without interference from anti-innovation politicians.' AI czar Sacks had also publicly supported the measure. After the Senate passed the bill without the AI provision, the White House responded to an inquiry for Sacks with the president's position, saying Trump 'is fully supportive of the Senate-passed version of the One, Big, Beautiful Bill.'Acknowledging defeat of his provision on the Senate floor, Cruz noted how pleased China, liberal politicians and 'radical left-wing groups' would be to hear the news. But Blackburn pointed out that the federal government has failed to pass laws that address major concerns about AI, such as keeping children safe and securing copyright protections. 'But you know who has passed it?' she said. 'The states.'Conservatives distrusting Big Tech for what they see as social media companies stifling speech during the COVID-19 pandemic and surrounding elections said that tech companies shouldn't get a free pass, especially on something that carries as much risk as AI. Many who opposed the moratorium also brought up preserving states' rights, though proponents countered that AI issues transcend state borders and Congress has the power to regulate interstate commerce. Eric Lucero, a Republican state lawmaker in Minnesota, noted that many other industries already navigate different regulations established by both state and local jurisdictions. 'I think everyone in the conservative movement agrees we need to beat China,' said Daniel Cochrane from the Heritage Foundation. 'I just think we have different prescriptions for doing so.' Many argued that in the absence of federal legislation, states were best positioned to protect citizens from the potential harms of AI technology. 'We have no idea what AI will be capable of in the next 10 years and giving it free rein and tying states hands is potentially dangerous,' Rep. Marjorie Taylor Greene wrote on Republican, Texas state Sen. Angela Paxton, wrote to Cruz and his counterpart, Sen. John Cornyn, urging them to remove the moratorium. She and other conservatives said some sort of federal standard could help clarify the landscape around AI and resolve some of the party's disagreements.
Qatar Tribune
a day ago
- Qatar Tribune
Don't blame the Bot: Master your AI prompts for better results
Agencies If you're using ChatGPT but getting mediocre results, don't blame the chatbot. Instead, try sharpening up your prompts. Generative AI chatbots such as OpenAI's ChatGPT, Google's Gemini and Anthropic's Claude have become hugely popular and embedded into daily life for many users. They're powerful tools that can help us with so many different tasks. What you shouldn't overlook, however, is that a chatbot's output depends on what you tell it to do, and how. There's a lot you can do to improve the prompt — also known as the request or query — that you type in. Here are some tips for general users on how to get higher quality chatbot replies, based on tips from the AI model makers: ChatGPT can't read your mind. You need to give it clear and explicit instructions on what you need it to do. Unlike a standard Google search, you can't just ask for an answer based on some keywords. And you'll need to do more than just tell it to, say, 'design a logo' because you'll end up with a generic design. Flesh it out with details on the company that the logo is for, the industry it will be used in and the design style you're going for. 'Ensure your prompts are clear, specific, and provide enough context for the model to understand what you are asking,' ChatGPT maker OpenAI advises on its help page. 'Avoid ambiguity and be as precise as possible to get accurate and relevant responses.' Think of using a chatbot like holding a conversation with a friend. You probably wouldn't end your chat after the first answer. Ask follow-up questions or refine your original prompt. OpenAI's advice: 'Adjust the wording, add more context, or simplify the request as needed to improve the results.' You might have to have an extended back-and-forth that elicits better output. Google advises that you'll need to try a 'few different approaches' if you don't get what you're looking for the first time. 'Fine-tune your prompts if the results don't meet your expectations or if you believe there's room for improvement,' Google recommends in its prompting guide for Gemini. 'Use follow-up prompts and an iterative process of review and refinement to yield better results.' When making your request, you can also ask an AI large language model to respond in a specific voice or style. 'Words like formal, informal, friendly, professional, humorous, or serious can help guide the model,' OpenAI writes. You also tell the chatbot the type of person the response is aimed at. These parameters will help determine the chatbot's overall approach to its answer, as well as the tone, vocabulary and level of detail. For example, you could ask ChatGPT to describe quantum physics in the style of a distinguished professor talking to a class of graduate students. Or you could ask it to explain the same topic in the voice of a teacher talking to a group of schoolchildren. However, there's plenty of debate among AI experts about these methods. On one hand, they can make answers more precise and less generic. But an output that adopts an overly empathetic or authoritative tone raises concerns about the text sounding too manipulative. Give the chatbot all the background behind the reason for your request. Don't just ask: 'Help me plan a weeklong trip to London.' ChatGPT will respond with a generic list of London's greatest hits: historic sites on one day, museums and famous parks on another, trendy neighborhoods and optional excursions to Windsor Castle. It's nothing you couldn't get from a guidebook or travel website, but just a little better organized. But if, say, you're a theatre-loving family, try this: 'Help me plan a weeklong trip to London in July, for a family of four. We don't want too many historic sites, but want to see a lot of West End theatre shows. We don't drink alcohol so we can skip pubs. Can you recommend mid-range budget hotels where we can stay and cheap places to eat for dinner?' This prompt returns a more tailored and detailed answer: a list of four possible hotels within walking distance of the theater district, a seven-day itinerary with cheap or low-cost ideas for things to do during the day, suggested shows each evening, and places for an affordable family dinner. You can tell any of the chatbots just how extensive you want the answer to be. Sometimes, less is more. Try nudging the model to provide clear and succinct responses by imposing a limit. For example, tell the chatbot to reply with only 300 words.
Al Jazeera
3 days ago
- Al Jazeera
Is ChatGPT hurting our critical thinking skills?
The Take An MIT study finds ChatGPT may be hurting critical thinking skills. How do you use AI tools while protecting your brain? Are AI chatbots dulling our brains? A new MIT study suggests critical thinking skills are at risk from tools like ChatGPT. What does the science say happens to brains that rely on AI? And how can you use AI tools while protecting your ability to think for yourself? Video Duration 22 minutes 45 seconds 22:45 Video Duration 22 minutes 02 seconds 22:02 Video Duration 21 minutes 00 seconds 21:00 Video Duration 22 minutes 49 seconds 22:49 Video Duration 21 minutes 18 seconds 21:18 Video Duration 21 minutes 49 seconds 21:49 Video Duration 24 minutes 29 seconds 24:29
