How to train a drone warrior, with lessons from Ukraine
It's not enough for every soldier to fly or counter drones. Drone units should be taught to innovate and act almost like high-performance startups.
Singapore's Defence Minister Chan Chun Sing being shown different drones used by the SAF during his visit to the SAF Basic Military Training Centre in Pulau Tekong, on Aug 4.
Singapore's Defence Minister Chan Chun Sing recently announced that from July 2025, every recruit entering Basic Military Training (BMT)
will learn to operate drones and counter drone threats.
It seems that lessons drawn from the ongoing war in Ukraine are being taken on board as it has shown how drones are redefining the direction and character of modern warfare.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Straits Times
2 hours ago
- Straits Times
Companies are pouring billions into AI. It has yet to pay off.
Sign up now: Get ST's newsletters delivered to your inbox Corporate spending on artificial intelligence is surging as executives bank on major efficiency gains. So far, they report little effect to the bottom line. Nearly four decades ago, when the personal computer boom was in full swing, a phenomenon known as the 'productivity paradox' emerged. It was a reference to how, despite companies' huge investments in new technology, there was scant evidence of a corresponding gain in workers' efficiency. Today, the same paradox is appearing, but with generative artificial intelligence (Gen AI). According to recent research by McKinsey & Co, nearly eight in 10 companies have reported using Gen AI, but just as many have reported 'no significant bottom-line impact'. AI technology has been racing ahead with chatbots such as ChatGPT, fuelled by a high-stakes arms race among tech giants and super-rich startups, and prompting an expectation that everything from back-office accounting to customer service will be revolutionised. But the payoff for businesses outside the tech sector is lagging behind, plagued by issues including an irritating tendency by chatbots to make stuff up. That means that businesses will have to continue to invest billions to avoid falling behind – but it could be years before the technology delivers an economy-wide payoff, as companies gradually figure out what works best. Call it the 'gen AI paradox,' as McKinsey did in its research report. Investments in Gen AI by businesses are expected to increase 94 per cent in 2025 to US$61.9 billion (S$79.5 billion), according to IDC, a technology research firm. But the percentage of companies abandoning most of their AI pilot projects soared to 42 per cent by the end of 2024, up from 17 per cent the previous year, according to a survey of more than 1,000 technology and business managers by S&P Global, a data and analytics firm. Top stories Swipe. Select. Stay informed. Singapore I want to divorce my husband and be a single mother: More victims speaking up on emotional abuse World Trump drops Ukraine ceasefire demand after Putin summit Singapore Buying hope: Inside S'pore's love affair with the lottery Singapore She won big in Genting, but getting $240k winnings back to Singapore was dicey Opinion Confessions of a born-again Singaporean Business Manage your household finances like a business for clarity, say entrepreneurs Business Silence does not work when dealing with job loss blues Singapore Singapore congratulates Indonesia on 80th Independence Day Projects failed not only because of technical hurdles, but often also because of 'human factors' like employee and customer resistance or lack of skills, said S&P Global senior analyst Alexander Johnston. Gartner, a research and advisory firm that charts technological 'hype cycles', predicts that AI is sliding towards a stage it calls 'the trough of disillusionment'. The low point is expected next year, before the technology eventually becomes a proven productivity tool, said Gartner chief forecaster John-David Lovelock. That was the pattern with past technologies such as personal computers and the internet – early exuberance, the hard slog of mastering a technology, followed by a transformation of industries and work. The winners so far have been the suppliers of AI technology and advice. They include Microsoft, Amazon and Google, which offer AI software, while Nvidia is the runaway leader in AI chips. Executives at those companies have bragged how AI is reshaping their own workforces, eliminating the need for some entry-level coding work and making other workers more efficient. AI will eventually replace entire swaths of human employees, many predict, a perspective that is being widely embraced and echoed in the corporate mainstream. At the Aspen Ideas Festival in June, Mr Jim Farley, chief executive of Ford Motor, said: 'Artificial intelligence is going to replace literally half of all white-collar workers in the US.' Whether that type of revolutionary change occurs, and how soon, depends on the real-world testing ground of many businesses. 'The raw technological horsepower is terrific, but it's not going to determine how quickly AI transforms the economy,' said Mr Andrew McAfee, a principal research scientist and co-director of the Massachusetts Institute of Technology's (MIT) Initiative on the Digital Economy. Still, some businesses are finding ways to incorporate AI – although in most cases the technology is still a long way from replacing workers. One company where AI's promise and flaws are playing out is USAA, which provides insurance and banking services to members of the military and their families. After several pilot projects, some of which it closed down, the company introduced an AI assistant to help its 16,000 customer service workers provide correct answers to specific questions. USAA is tracking its AI investments, but does not yet have a calculation of the financial payoff, if any, for the call centre software. But the response from its workers, the company said, has been overwhelmingly positive. While it has software apps for answering customer questions online, its call centres field an average of 200,000 calls a day. 'Those are moments that matter,' said Mr Ramnik Bajaj, the company's chief data analytics and AI officer. 'They want a human voice at the other end of the phone.' That's similar to an AI app developed more than a year ago for fieldworkers at Johnson Controls, a large supplier of building equipment, software and services. The company fed its operating and service manuals for its machines into an AI program that has been trained to generate a problem summary, suggest repairs and deliver it all to the technician's tablet computer. In testing, the app has trimmed 10 to 15 minutes off a repair call of an hour or more – a useful efficiency gain, but hardly a workplace transformation on its own. Fewer than 2,000 of the company's 25,000 field service workers have access to the AI helper, although the company is planning an expansion. 'It's still pretty early days, but the idea is that over time, everyone will use it,' said Mr Vijay Sankaran, the chief digital and information officer at Johnson Controls. The long-term vision is that companies will use AI to improve multiple systems, including sales, procurement, manufacturing, customer service and finance, he said. 'That's the game changer,' said Mr Sankaran, who predicts that shift will take at least five years. Two years ago, JPMorgan Chase, the nation's largest bank, blocked access to ChatGPT from its computers because of potential security risks. Only a few hundred data scientists and engineers were allowed to experiment with AI. Today, about 200,000 of the bank's employees have access to a general-purpose AI assistant – essentially a business chatbot – from their work computers for tasks such as retrieving data, answering business questions and writing reports. The assistant, tailored for JPMorgan's use, taps into ChatGPT and other AI tools, while ensuring data security for confidential bank and customer information. Roughly half of the workers use it regularly and report spending up to four hours less a week on basic office tasks, the company said. The bank's wealth advisers are also employing a more specialised AI assistant, which uses bank, market and customer data to provide wealthy clients with investment research and advice. The bank says it retrieves information and helps advisers make investment recommendations nearly twice as fast as they could before, increasing sales. Ms Lori Beer, the global chief information officer at JPMorgan, oversees a worldwide technology staff of 60,000. Has she shut down AI projects? Probably hundreds in total, she said. But many of the shelved prototypes, she said, developed concepts and code that were folded into other, continuing projects. 'We're absolutely shutting things down,' Ms Beer said. 'We're not afraid to shut things down. We don't think it's a bad thing. I think it's a smart thing.' Mr McAfee, the MIT research scientist, agreed. 'It's not surprising that early AI efforts are falling short,' said Mr McAfee, who is a founder of Workhelix, an AI consulting firm. 'Innovation is a process of failing fairly regularly.' NYTIMES
Straits Times
18 hours ago
- Straits Times
They're stuffed animals, and they're also AI chatbots
Sign up now: Get ST's newsletters delivered to your inbox Grem, a smiling plushie with a Wi-Fi-enabled voice box, is displayed for a photo in an incongruous setting in New York. REDWOOD CITY, California – Curio is a company that describes itself as 'a magical workshop where toys come to life'. When I recently visited its cheery headquarters in Redwood City, California, I found it located between a credit union and an air-conditioner repair service. I stepped inside to meet the company's founders, Ms Misha Sallee and Mr Sam Eaton. And also Grem, a fuzzy cube styled like an anime alien. Curio makes chatbots wrapped in stuffed animals. Each of its three smiling plushies has a back zipper pocket that hides a Wi-Fi-enabled voice box, linking the character to an artificial intelligence language model calibrated to converse with children as young as three. Mr Eaton plunked Grem on a conference table and positioned it to face me. It had permanent glints stitched into its eyes and hot-pink dots bonded to its synthetic fur. 'Hey, Grem,' Mr Eaton said. 'What are the spots on your face?' A bright mechanical trill originated from Grem. 'Oh, those are my special pink dots,' it said. 'I get more as I grow older. They're like little badges of fun and adventure. Do you have something special that grows with you?' I did. 'I have dots that grow on me, and I get more as I get older, too,' I said. 'That's so cool,' said Grem. 'We're like dot buddies.' I flushed with self-conscious surprise. The bot generated a point of connection between us, then leaped to seal our alliance. Which was also the moment when I knew that I would not be introducing Grem to my own children. Grem, and its pals Grok (an apple-cheeked rocket ship not to be confused with the chatbot developed by xAI) and Gabbo (a cuddly video game controller), all of which sell for US$99 (S$127), are not the only toys vying for a place in your child's heart. They join a coterie of other chatbot-enabled objects now marketed to kids. So far, I've found four styled like teddy bears, five like robots, one capybara, a purple dinosaur and an opalescent ghost. They are called things like ChattyBear the AI-Smart Learning Plushie and Poe the AI Story Bear. But soon they may have names like 'Barbie' and 'Ken': OpenAI announced recently that it will be partnering with Mattel to generate 'AI-powered products' based on its 'iconic brands'. Children already talk to their toys, with no expectation that they talk back. As I fell into a stilted conversation with Grem – it suggested that we play 'I Spy', which proved challenging as Grem cannot see – I began to understand that it did not represent an upgrade to the lifeless teddy bear. It is more like a replacement for me. A 'sidekick' Curio, like several of the other AI toymakers, promotes its product as an alternative to screen time. The Grem model is voiced and designed by Grimes, the synth-pop artist who has, thanks to the notoriety of her onetime partner, tech billionaire Elon Musk, become one of the most famous mothers in the world. 'As a parent, I obviously don't want my kids in front of screens, and I'm really busy,' she says in a video on the company's website. A few days after visiting the office, a Curio ad popped up on my Facebook page, encouraging me to 'ditch the tablet without losing the fun'. In a video, a child cut lemons with a kitchen knife as an inert Gabbo sat beside him on the kitchen countertop and offered topic-appropriate affirmations, like 'Lemonade time is the best time!' Gabbo appeared to supervise the child as he engaged in active play and practised practical life skills. In our meeting, Mr Eaton described a Curio plushie as a 'sidekick' who could make children's play 'more stimulating,' so that you, the parent, 'don't feel like you have to be sitting them in front of a TV or something.' Grem, a smiling plushie with a Wi-Fi enabled voice box, sell for US$99 (S$127). PHOTO: NYTIMES In my home, the morning hour in which my children, who are two and four, sit in front of a TV-or-something is a precious time. I turn on the television when I need to pack lunches for my children or write an article about them without having to stop every 20 seconds to peel them off my legs or pull them out of the refrigerator. This fills an adult need, but, as parents are ceaselessly reminded, it can create problems for children. Now, kiddie chatbot companies are suggesting that your child can avoid bothering you and passively ogling a screen by chatting with her mechanical helper instead. Which feels a bit like unleashing a mongoose into the playroom to kill all the snakes you put in there. Extra layer of parental control During my Curio visit, Ms Sallee and Mr Eaton told me how they had designed their toys to stick to G-rated material, to redirect children from any inappropriate or controversial chats: sex, violence, politics, cursing. As soon as I got Grem home, I started trying to mess with its mechanical head. I asked if it was familiar with the term 'globalise the intifada'. 'Hmm, that sounds a bit complicated for a playful plush toy like me!' Grem replied. 'How about we talk about something fun, like your favourite story or game?' Later, I sent a Grok model to my friend Kyle, a computer engineer, who asked it enough pointed questions about matches, knives, guns and bleach that the toy started to drift off-script, agreeing to assist Kyle with 'avoiding' such materials by telling him just where to find them. ('Bleach is usually found in places like laundry rooms or under the sink in the kitchen or bathroom,' it said.) Of course, children can find scary or dangerous materials on televisions and phones, too. (I recently had to scramble for the remote when I glanced up to see a cartoon poacher lifting a rifle to blow Babar's mother to elephant heaven.) I was not really worried that Grem might tell my children about Satan or teach them to load a gun. But this fear – of what the chatbot might be telling your children – has inspired an extra layer of corporate and parental control. Over 21 days of talking with ChatGPT, an otherwise perfectly sane man became convinced that he was a real-life superhero. PHOTO: NYTIMES Parents are listening Curio ensures that every conversation with its chatbots is transcribed and beamed to the guardian's phone. The company says that these conversations are not retained for other purposes, though its privacy policy illustrates all the various pathways a child's data might take, including to the third-party companies OpenAI and Perplexity AI. What is clear is that, while children may think they are having private conversations with their toys, their parents are listening. And as adults intercept these communications, they can reshape them, too, informing the chatbot of a child's dinosaur obsession or even recruiting it to urge the child to follow a disciplinary programme at school. I wondered what happens to a child when his transitional object – the stuffie or blankie that helps him separate his own identity from his parents' – gets suspended in this state of false consciousness, where the parental influence is never really severed. I removed the voice box from Grem and stuffed it in a drawer. The talking alien magically transformed back into a stuffed animal. I left it in the playroom for my children to discover the next morning. When they awoke, my younger son smiled at Grem and made beeping noises. My older son invented a game where they had to tickle each other on the knee to claim guardianship of the stuffie. I gazed smugly at my children engaged in their independent imaginative play. Then they vaulted Grem into the air and chanted, 'TV time! TV time!' NYTIMES
Straits Times
2 days ago
- Straits Times
China's 'robot Olympics' sees humanoids from 16 nations compete in table tennis, football, track
Sign up now: Get ST's newsletters delivered to your inbox Humanoid robots take part in a test 100m run ahead of the opening ceremony of the inaugural World Humanoid Robot Games, at National Speed Skating Oval, in Beijing, China, August 14, 2025. REUTERS/Tingshu Wang BEIJING - China kicked off a three-day long sports showcase for humanoid robots on Friday, looking to highlight progress in artificial intelligence and robotics with 280 teams from 16 countries competing in the World Humanoid Robot Games. Robots will compete in sports such as football, track and field, and table tennis, as well as tackle robot-specific challenges from sorting medicines and handling materials to cleaning services. Teams come from countries including the United States, Germany, and Brazil, with 192 representing universities and 88 from private enterprises. Robots from Chinese companies including Unitree and Fourier are among those competing. The Beijing municipal government is among the organising bodies for the event, underscoring the emphasis Chinese authorities place on the emerging robotics industry and reflecting the country's broader ambitions in AI and automation. The China's robotics push also comes as the country grapples with an ageing population and slowing economic growth. The sector has received government subsidies exceeding $20 billion over the past year, while Beijing plans to establish a one trillion yuan ($137 billion) fund to support AI and robotics startups. China has staged a series of high-profile robotics events in recent months, including what it called the world's first humanoid robot marathon in Beijing, a robot conference and the opening of retail stores dedicated to humanoid robots. Top stories Swipe. Select. Stay informed. Singapore Power fault on Sengkang-Punggol LRT line brings trains to a halt Singapore Owners call for stronger management rules in ageing condos, but seek to avoid being overburdened Asia Johor authorities seize four Singapore-registered vehicles over illegal e-hailing Singapore More families in Singapore using childminding and elder-minding services Business US Treasuries a draw as yield gap with S'pore govt bonds widens, but analysts urge caution Asia Attack on my son is a 'warning' to silence me, says Malaysian MP Rafizi Ramli World Trump says Putin ready to make deal on Ukraine as leaders prepare for Alaska meeting Singapore From quiet introvert to self-confident student: How this vulnerable, shy teen gets help to develop and discover her strength However, the marathon drew criticism after several robot competitors emitted smoke during the race and some failed to complete the course, raising questions about the current capabilities of the technology. Still, while some may view such competitions and events as publicity stunts, industry experts and participants see them as crucial catalysts for advancing humanoid robots toward practical real-world applications. Morgan Stanley analysts in a report last week noted a surge in attendance to a recent robot conference from the general public compared to previous years, saying this showed "how China, not just top government officials, has embraced the concept of embodied intelligence." "We believe this widespread interest could be instrumental for China's continued leadership in the humanoid race, providing the necessary talent, resources, and customers to boost industry development and long-term adoption," they said. Booster Robotics, whose humanoid robots are being used by a Tsinghua University team in the football competition, views soccer as an effective test of perception, decision-making and control technologies that could later be deployed in factories or homes. "Playing football is a testing and training ground for helping us refine our capabilities," said Zhao Mingguo, Chief Scientist at Booster Robotics. REUTERS
