-
Japanese minnows one win from fairytale Champions League title
-
Rugby Australia eyes brighter future as Lions tour brings cash windfall
-
Blazers rally stuns Spurs after Wembanyama injury
-
Young Chinese use AI to launch one-person firms over job anxiety
-
Delicate extraction: Malaysia offers rare earths alternative to China
-
Oil, stocks fall as traders weigh outlook after Trump extends truce
-
Pope to visit prison on final leg of Africa tour
-
US military says key weapons system staying in South Korea
-
India strangles final Maoist bastion as mining looms
-
AI-powered robots offer new hope to German factories
-
Indonesia orangutan forest cleared for 'carbon-neutral' packaging firm
-
PGA Tour mulls pathway back for golfers as LIV plots survival
-
One month phone-free: Young Americans try digital detox
-
Questions about Tesla spending binge ahead of earnings
-
Rome summons Russian ambassador over insults against Meloni
-
US tells Afghans to choose Taliban home or DR Congo: activist
-
John Ternus to lead Apple in the age of AI
-
SpaceX partners with AI startup Cursor, may buy it for $60 bn
-
Mexico pyramid shooter inspired by Columbine attack, pre-Hispanic sacrifices
-
Mexico pyramid shooter planned attack, fixated on US massacre
-
Mbappe on the mark as Real Madrid sink Alaves
-
Rosenior blasts Chelsea flops after 'unacceptable' Brighton defeat
-
Inter roar back to beat Como and reach Italian Cup final
-
Lens sweep past Toulouse to reach French Cup final
-
Brighton crush Chelsea to pile pressure on under-fire Rosenior
-
Strait of Hormuz blockade drives up costs at Panama Canal
-
Trump extends ceasefire, says giving Iran time to negotiate
-
Michelle Bachelet hopes the world is ready for a female UN chief
-
Nowitzki, Bird among eight inductees into FIBA Hall of Fame
-
Stocks fall, oil climbs amid uncertainty over US-Iran talks
-
Iran war means more orders for US defense giants
-
Mexico pyramid shooting was planned attack, officials say
-
Trump's messaging on Iran grows increasingly erratic
-
Churchill Downs buys Preakness for $85 million
-
Unregulated AI like speeding with no steering wheel: AI godfather Hinton
-
Tourists return to Rio viewpoint after shootout scare
-
Maradona's daughter slams 'manipulation' of family by his doctors
-
Abhishek's 135 powers Hyderabad to third straight IPL win
-
Vance still in Washington as uncertainty mounts over US-Iran talks
-
No.1 Jeeno seeks first major win at LPGA Chevron event
-
New batch of World Cup tickets to go on sale
-
Material girl: Madonna offers reward for missing clothes
-
Maker of Argentina's first Oscar-winning film, Luis Puenzo, dies at 80:
-
Rape retrial hears Weinstein 'preyed' on aspiring US actress
-
Arrests, hangings, blackout: Iran cranks up wartime repression
-
Seixas relishes 'steep' challenge at Fleche Wallonne
-
US Fed chair nominee says will not be controlled by Trump
-
Singapore's Tang gets second term at UN's patent agency
-
Taiwan leader postpones Eswatini trip after overflight permits revoked
-
Lula warns will respond after US expels police attache
Nairobi startup's bid to be 'operating system for global South'
Away from the heady rush to build ultra-capable, sci-fi style artificial intelligence in Silicon Valley, ambitious Nairobi-based startup Amini AI is betting on the technology addressing emerging countries' prosaic problems in the here and now.
Chief executive Kate Kallot aims for Amini -- still a relatively small firm with $6 million in funding and 25 employees -- to become "the operating system for the Global South" in the coming years, creating the infrastructure foundation for others to build AI and data processing applications.
"There is a huge opportunity for emerging economies to focus on more applied AI innovation rather than fundamental research, which is what a lot of the US and Europe is doing," Kallot told AFP at the Vivatech trade fair in Paris.
On its website, the company highlights uses of its platform such as slashing crop insurance costs for farmers across Africa by monitoring conditions, or warning dairy producers in Morocco of water sources at risk from climate change.
Such efforts are only a hint of what will become possible as more data is collected, organised and processed from across the emerging world, Kallot believes.
"Data in Africa, Latin America, Southeast Asia, a lot of these emerging economies is still analogue and still scattered and still unstructured," she noted.
"There is a lot of work that needs to go into building that data infrastructure that can help those countries move from analogue systems to digital and help them be ready to move to AI."
Kallot said Amini's small team was helping multiple countries develop such infrastructure, highlighting a recent memorandum of understanding with Ivory Coast and projects in Barbados, India, Nepal and Cambodia.
- Digital natives short on data -
Western tech firms have notoriously turned to cheap labour from emerging economies for tasks upstream of AI, such as arduous labelling of vast datasets used to "train" AI models to recognise patterns.
But in countries like Kenya or the Philippines, "you have a population that is digitally native, extremely young... a lot of them have studied computer science" and speak English, Kallot said.
"The problem they have is that they lack the opportunity to practice their craft, because these regions are still seen as consumers of technology and are still seen as regions where innovation doesn't happen."
This is also reflected in how data is stored and processed.
A 2024 report from American research firm Xalam Analytics found that just one percent of the world's data centre capacity is located in Africa -- a region with almost 19 percent of the global population.
What's more, only two percent of African data gets processed on the continent, Kallot said.
"We're still in a very data-scarce environment, and until this is fixed we won't be able to adopt a lot of the very fancy new systems that are being put in place by... the big tech companies," she pointed out.
- Frugal and local -
Kallot sees little fallout for now in emerging economies from the US-China confrontation over the advanced chips powering the top-performing AI models.
But nations are "becoming some sort of battleground" for infrastructure investment by the superpowers' tech giants like Huawei and Microsoft.
One area where Kallot would like to see change is emerging countries coming together to build shared infrastructure like data centres, rather than relying on processing abroad or waiting for foreign firms to build them locally.
"Before, building critical infrastructure for your country meant building a road, building a hospital -- today it's actually building the data infrastructure," she said.
The choice to leave data to be processed abroad risks "erasing... a lot of your knowledge system and your culture," she warned, as most artificial intelligence training has not included information from much of the emerging world.
Looking forward, the limited infrastructure and computing power available outside top economies may actually foster frugal innovations that save energy and resources, Kallot said.
Emerging economies boast "brilliant developers that are doing things that are extremely environmentally friendly, that know how to work in a very contained and constrained environment... we just have to surface it and make sure we give them a platform," Kallot said.
A.Ruegg--VB