Latest news with #ATxSummit
CNA
30-05-2025
- Entertainment
- CNA
An app to 'talk' to a kebaya? Peranakan Museum partners with OpenAI to let you do just that
Museum visits can be semi-intimidating. You listen to a passionate docent tell you about an artefact's rich history. Then at the end of the tour, they ask: Any questions? You have several. Why is a vase pink? Why does the man look so sad in the photograph? Why do these people have their portrait displayed in a museum? But of course, you don't ask. Because you don't want to come off stupid. Instead, you ask how the artefact influenced a certain ethic group's identity in modern day. It makes you sound well-informed, you believe. But a museum visit should encourage curiosity, not stem it. And it's this belief that forms the basis of artificial intelligence (AI) organisation OpenAI's first museum partnership in Asia with Singapore's Peranakan Museum, announced at the OpenAI Forum during tech event ATxSummit on Thursday (May 29). The pilot collaboration with Ask Mona – a French AI studio that uses an OpenAI large language model to enhance cultural experiences – will allow visitors to 'speak' with certain museum artefacts via AI-generated conversations on Ask Mona's web app, accessible on any mobile device. It will be available till Jul 6. Selected artefacts include traditional Peranakan attire, a kamcheng jar (a type of porcelain storage jar that's often decorated) and several pictures depicting various aspects and key personalities of Peranakan culture. For instance, with the kebaya, I posed Ask Mona a question one may hesitate to ask out loud: 'Why does a kebaya look so uncomfortable to wear?' Its response, generated after a few seconds, read: 'The kebaya might seem uncomfortable due to its form-fitting design. This style became popular in the 1930s. 'The kebaya is often made with translucent European fabrics. These fabrics can appear delicate and restrictive. Historically, it was a loose-fitting garment, evolving over time. Its design reflects a blend of cultural influences, making it unique. 'The kebaya is paired with a sarong or kain panjang, adding to its elegance.' TWO-WAY CONVERSATIONS This AI technology, to be clear, isn't the same as having a digital screen display information about an exhibit or listening to an audio narration about an artefact's history. Such methods remain helpful in engaging museum goers. But they can 'feel like a one-way conversation', said Lum Jia Yi, assistant director of audience, communications and digital at the Peranakan Museum. 'With Ask Mona, audiences get to ask their questions. And we get to find out their train of thought (that) helps us shape what audiences are trying to find out about the collections, and (understand) how we can present our materials better.' Ultimately, the museum aims to make its collections and culture 'more accessible to the general audience', not least since the Peranakan culture is a 'living, breathing culture that's constantly evolving', Lum added. And since audiences are constantly on their phone, the AI technology simply allows them to interact with the museum 'in a way that they are comfortable with'. While ATxSummit attendees got to see the initiative up close alongside the artefacts, which were brought to the summit, the experience isn't currently available at the Peranakan Museum itself. Non-attendees can access the experience by joining the OpenAI Forum community at where they will receive a link to the Ask Mona web app. They can then "speak" with the various Peranakan Museum artefacts listed in the app - from anywhere in the world. On one hand, such experiences make museums more accessible, allowing anyone the opportunity to learn about other cultures at their own pace - and without the fear of judgement. Understandably, this may then beg the question: Will AI eventually replace the need for human docents? In short, no, said CEO and co-founder of Ask Mona, Marion Carre. Not only does she believe we need to move beyond the classic opposition of human versus AI, she has also observed that most people use such AI technology to start conversations with friends and family about their museum experience. Some museums have even told Carre that people used to look at artwork for three to five seconds on average – but with the likes of Ask Mona, they now spend three to five minutes interacting with an artwork. 'We're really about using AI to improve the museum experience globally,' she told CNA Lifestyle. Her team also ensures that all data fed into OpenAI's large language model used by Ask Mona strictly comes from the museum, which means anticipating the questions visitors may actually have at each exhibit. USING AI FOR CULTURE AND HERITAGE Crucially, the partnership reveals the possibilities of using AI beyond the typical spaces of the classroom and the workplace. What's not often explored is the impact that AI can have to 'bring people closer to culture and heritage', said Sandy Kunvatanagarn, head of Asia-Pacific policy at OpenAI. 'Inspired by that and the fact that this year is SG60, we thought it'd be a perfect opportunity to really see how we can use AI technology and the Peranakan Museum's focus on accessibility and community – and combine that with the work that Ask Mona has been doing around the world – to bring everybody together to have a conversation about the richness of Peranakan culture. 'Not just in Singapore, but through the web app (which gives people) the ability to access it all around the world.' OpenAI believes AI has the power to change many aspects of life, Kunvatanagarn added, 'but one thing that is consistent, and that should be for everybody, is culture and understanding their own heritage'. 'If AI can play a part in language preservation or cultural accessibility, or whatever it is that people want to learn about who they are, we think there's a place for AI to be in that. And it's done by working with partners who are experts in this space, and us providing the tools to make it happen.'
Yahoo
29-05-2025
- Business
- Yahoo
A Salesforce exec tells BI there's an even more important skill for employees than coding
Coding is no longer the most important skill in the AI era, said Salesforce's chief futures officer. Peter Schwartz said in an interview that employees need empathy more than anything else. "Parents ask me what should my kids study, shall they be coders? I said, 'learn how to work with others.'" Coding is no longer the must-have skill of the AI era, said Salesforce's chief futures officer, Peter Schwartz. "The most important skill is empathy, working with other people," said Schwartz in an interview with Business Insider at the Singapore tech conference ATxSummit. "Parents ask me what should my kids study, shall they be coders? I said, 'learn how to work with others.'" Schwartz said empathy is the ability to understand and relate to another human being, like with coworkers. It's the ability to "collaborate and to creatively work together." "That will be the most important thing because the AIs can deal with all the routine stuff," he added. When asked how to screen for it, Schwartz said it's hard to measure. "I don't have a good answer," he said. "But that's what I am looking for. I look for that empathy that this is a person who's really going to be a great teammate, somebody I can work closely with," he added. Salesforce CEO Marc Benioff said earlier this year that his company might not hire software engineers in 2025 because of how much AI agents have helped boost some coders' productivity. Schwartz called AI's impact on coding for Salesforce "huge." "We've seen a massive increase in productivity of our coders because they have the tools to be able to do coding much faster — frankly, more creatively," Schwartz said. During Google's third-quarter earnings call in October, CEO Sundar Pichai said more than a quarter of the company's new code was generated by AI. As AI gets better at writing code, some product managers have speculated that AI will increasingly take on some technical coding tasks and circumvent their need for engineers. Job postings for software engineers on Indeed have hit a five-year low. Some tech leaders said learning the fundamentals is still essential, while others emphasized the importance of soft skills in setting candidates apart. Mark Zuckerberg said in a July interview with Bloomberg that he believed the most important skill was "learning how to think critically and learning values when you're young." "If people have shown that they can go deep and do one thing really well, then they've probably gained experience in, like, the art of learning something," Zuckerberg said, discussing what he looked for in job candidates. Read the original article on Business Insider
Business Insider
29-05-2025
- Business
- Business Insider
A Salesforce exec tells BI there's an even more important skill for employees than coding
Coding is no longer the must-have skill of the AI era, said Salesforce's chief futures officer, Peter Schwartz. "The most important skill is empathy, working with other people," said Schwartz in an interview with Business Insider at the Singapore tech conference ATxSummit. Schwartz said empathy is the ability to understand and relate to another human being, like with coworkers. It's the ability to "collaborate and to creatively work together." "That will be the most important thing because the AIs can deal with all the routine stuff," he added. When asked how to screen for it, Schwartz said it's hard to measure. "I don't have a good answer," he said. "But that's what I am looking for. I look for that empathy that this is a person who's really going to be a great teammate, somebody I can work closely with," he added. AI has come for coding Salesforce CEO Marc Benioff said earlier this year that his company might not hire software engineers in 2025 because of how much AI agents have helped boost some coders' productivity. Schwartz called AI's impact on coding for Salesforce "huge." "We've seen a massive increase in productivity of our coders because they have the tools to be able to do coding much faster — frankly, more creatively," Schwartz said. During Google's third-quarter earnings call in October, CEO Sundar Pichai said more than a quarter of the company's new code was generated by AI. As AI gets better at writing code, some product managers have speculated that AI will increasingly take on some technical coding tasks and circumvent their need for engineers. Job postings for software engineers on Indeed have hit a five-year low. Some tech leaders said learning the fundamentals is still essential, while others emphasized the importance of soft skills in setting candidates apart. Mark Zuckerberg said in a July interview with Bloomberg that he believed the most important skill was "learning how to think critically and learning values when you're young." "If people have shown that they can go deep and do one thing really well, then they've probably gained experience in, like, the art of learning something," Zuckerberg said, discussing what he looked for in job candidates.
Yahoo
28-05-2025
- Business
- Yahoo
AI is advancing faster than data centers can keep up in Asia, says a Groq exec
Asia is struggling to keep up with the pace of AI adoption, said a Groq exec. The chief revenue officer said there is not enough compute and infrastructure in the region. Ian Andrews' comments come amid a global AI spending boom. As the world scrambles to scale artificial intelligence, Asia is running into a very physical problem: not enough data centers and infrastructure, said Ian Andrews, the chief revenue officer at semiconductor startup Groq. There's a "huge challenge getting enough compute" for what the company wants to do in Asia, Andrews said on Wednesday during a panel at Singapore tech conference ATxSummit. "It's a big problem that we have to go tackle," he added. While most AI companies have focused on training large language models, Groq is betting on speed, building its own chips to run models faster. The gambit is that as AI models get better, inference — where the AI makes decisions or answers questions — will demand more computing power than training will. The region is already seeing bottlenecks when it comes to infrastructure like data centers and power, Andrews said, adding that it's likely to worsen as AI becomes more widely adopted in the region. "Keep in mind, we're still in the infancy of AI," he said. Andrews also said that over the next five years, all applications might be driven by AI. "There is no model in which we have enough data center capacity, enough power, and enough infrastructure to run all of that in this region," he added. Model progression is a more solvable problem than the infrastructure ones, Andrews said. Andrews' comments come as AI heavyweights like OpenAI deepen their footprint in Asia and governments across the region ramp up spending on infrastructure to support the technology. OpenAI on Monday said it will soon set up an office in South Korea, its third in Asia. The company's chief strategy officer, Jason Kwon, said growth in ChatGPT's user base in South Korea has been "off the charts." South Korea has the highest number of paid ChatGPT subscribers outside the US, he said. In November, Taiwan's science and technology minister said that the government would spend $3 billion over three years to ramp up AI data centers and their computing ability. Meanwhile, big tech companies are pouring hundreds of billions of dollars into global infrastructure to ramp up AI development. To grasp how quickly AI is evolving, Andrews pointed to ChatGPT. "It was only about 30 months ago that ChatGPT launched," Andrews said. "If you go back and look at what you can do with ChatGPT compared to where we are today, it was a toy," he added. There's an "acceleration" in AI's capability, Andrews said. "In the first quarter of 2025 alone, there were more state-of-the-art, frontier models launched than all of 2024," he said. "I'm an accelerationist on this point. Things are going to move quicker than we expect in terms of the capabilities," he added. Read the original article on Business Insider Sign in to access your portfolio
Business Insider
28-05-2025
- Business
- Business Insider
AI is advancing faster than data centers can keep up in Asia, says a Groq exec
As the world scrambles to scale artificial intelligence, Asia is running into a very physical problem: not enough data centers and infrastructure, said Ian Andrews, the chief revenue officer at semiconductor startup Groq. There's a "huge challenge getting enough compute" for what the company wants to do in Asia, Andrews said on Wednesday during a panel at Singapore tech conference ATxSummit. "It's a big problem that we have to go tackle," he added. While most AI companies have focused on training large language models, Groq is betting on speed, building its own chips to run models faster. The gambit is that as AI models get better, inference — where the AI makes decisions or answers questions — will demand more computing power than training will. The region is already seeing bottlenecks when it comes to infrastructure like data centers and power, Andrews said, adding that it's likely to worsen as AI becomes more widely adopted in the region. "Keep in mind, we're still in the infancy of AI," he said. Andrews also said that over the next five years, all applications might be driven by AI. "There is no model in which we have enough data center capacity, enough power, and enough infrastructure to run all of that in this region," he added. Model progression is a more solvable problem than the infrastructure ones, Andrews said. Andrews' comments come as AI heavyweights like OpenAI deepen their footprint in Asia and governments across the region ramp up spending on infrastructure to support the technology. OpenAI on Monday said it will soon set up an office in South Korea, its third in Asia. The company's chief strategy officer, Jason Kwon, said growth in ChatGPT's user base in South Korea has been "off the charts." South Korea has the highest number of paid ChatGPT subscribers outside the US, he said. In November, Taiwan's science and technology minister said that the government would spend $3 billion over three years to ramp up AI data centers and their computing ability. Meanwhile, big tech companies are pouring hundreds of billions of dollars into global infrastructure to ramp up AI development. Early ChatGPT was a 'toy' To grasp how quickly AI is evolving, Andrews pointed to ChatGPT. "It was only about 30 months ago that ChatGPT launched," Andrews said. "If you go back and look at what you can do with ChatGPT compared to where we are today, it was a toy," he added. There's an "acceleration" in AI's capability, Andrews said. "In the first quarter of 2025 alone, there were more state-of-the-art, frontier models launched than all of 2024," he said. "I'm an accelerationist on this point. Things are going to move quicker than we expect in terms of the capabilities," he added.
