Skip the pleasantries: UN report says shorter AI prompts could cut ChatGPT energy use by 25%

Ditch the niceties in AI prompts to save energy use, say researchers

A UN report warns of the rapid growth in AI energy consumption, but suggests users can improve efficiency by making prompts more concise UN researchers are urging people to be less polite to artificial intelligences after a report found that cutting words from prompts could reduce ChatGPT's energy consumption by up to 25 per cent. Removing "please", "thank you" and other unnecessary words from AI prompts could save 87 to 98 gigawatt-hours of electricity per year, the report from the UN University Institute for Water, Environment and Health (UNU-INWEH) found. That is the equivalent of the annual residential electricity use of up to 760,000 people in sub-Saharan Africa. To reduce their energy consumption and carbon footprint, people should write concise prompts, avoid getting sucked into conversation loops and refrain from starting relationships with AI, the researchers said. "We are not saying be rude to your AI. But don't fall into the interaction trap and don't go falling in love with it either," says Kaveh Madani at UNU-INWEH. The large language models behind AI chatbots process text in small units known as tokens. Madani says concise prompts can save energy because they can reduce both the number of tokens the model has to process and the number it generates in response. In some cases, shorter prompts may also simplify the task, further reducing the power required. The UN study - one of the most comprehensive assessments of the environmental costs of AI to date - warns of rapidly increasing energy, land and water use due to the growing adoption of the technology. ChatGPT alone now processes around 2.5 billion queries every day and Google 16 billion, the majority of which have integrated AI summaries. Tech companies disclose little information on their energy use, so the researchers used the available data for their data centres. AI currently accounts for about 20 per cent of the energy used by data centres, but that share is projected to double to around 40 per cent in the next few years. By 2030, AI alone could consume around 378 terawatt-hours a year and data centres could use 945 TWh in total -- almost 3 per cent of projected global electricity use. The 9.3 trillion litres of water projected to be needed by data centres by 2030 is enough to meet the minimum annual domestic water needs of all 1.3 billion people in sub-Saharan Africa. "You're looking at something on a global scale that is being adopted faster than any other technology in the history of technology, so the energy use is increasing very rapidly," says Miriam Aczel at UNU-INWEH. The researchers said AI companies should be required to publish their energy consumption, while governments should introduce energy caps on companies and individuals, but it is also crucial to educate the public on how to use AI efficiently. People should be encouraged to avoid using AI unnecessarily and, when they do use it, to cut words and use less powerful models, says Madani. They should also be aware that generating an image uses 60 times more energy than a text query, enough to power a 10-watt LED bulb for about 17 minutes. A complex video uses up to 8000 times more than text and could power the same bulb for about 1.7 days. "We are not saying AI is bad," says Madani. "We are just saying let's use it in a proper way. It's like a knife: you can save a patient's life in the operating theatre, but you can also kill someone with it."

You can literally save the planet by being less polite to AI bots like ChatGPT and Gemini

Every "please" you type to ChatGPT is quietly costing the planet. Here is something that will make you think twice before typing a long, detailed prompt to ChatGPT or Gemini. Every word you type costs energy, and a lot more than you would think. A recent report by the United Nations University Institute for Water, Environment and Health paints a pretty alarming picture of AI's environmental footprint. The numbers are staggering and will make you pause next time you want to make a request to your favorite AI chatbot. Recommended Videos According to the report, ChatGPT alone processes around 2.5 billion prompts every single day, and at a conservative 0.42 Wh per prompt, that adds up to roughly 383 GWh of electricity per year. That is enough to meet the annual electricity needs of nearly 3 million people in Sub-Saharan Africa. Does the length of your prompt actually matter? The report says that the length of your prompt directly impacts how much energy AI chatbots use. The report highlights something called "concise mode," which is basically the idea that shorter prompts use less energy because AI inference energy scales with the number of tokens processed. If a concise mode reduced tokens by just 30% for everyday interactions, cutting per-query energy by roughly 25%, it would save somewhere between 87 and 98 GWh of electricity per year. To put that in perspective, that is the annual residential electricity use of up to 756,000 people. The same logic applies to the type of AI task you pick. A typical ChatGPT-style text query uses about 200 times more energy than basic spam filtering. Generating a single AI image requires 2.9 Wh, which is 60 times more demanding than a short text answer. Video generation is even worse, with complex clips drawing over 415 Wh each. To think that AI slop videos that are not only ruining our video streaming websites, but also using such high amounts of electricity, is something I find hard to digest. What can you do about it? You do not need to stop using AI if it's helping you in every day tasks or work. But you should stop using it to generate silly memes or brainrot content. Also, the next time you are asking ChatGPT something simple, keep it short. Skip the pleasantries, get to the point, and choose a lighter model when the task does not require serious computer power. Small habits at scale add up to a surprisingly big difference.