-
Hello Kitty firm apologises, scraps Japan TV tie-up after China anger
-
TotalEnergies profit hits record on high oil prices
-
Taiwan says Pakistan briefly closed airspace to Taiwanese flights
-
Key of seethe: I.Coast row with Sahel juntas spills into concert halls
-
'My blood was spilled here': a year on, Tanzania unable to mourn election violence
-
Romanian writer Cartarescu hails books as balm in turmoil
-
Afghanistan opium poppy cultivation surges despite Taliban govt ban: UN
-
Mbappe, Real Madrid and La Liga face long road to redemption in China
-
No World Series miracle for weary Rays
-
North Korea fires 'around a dozen' ballistic missiles into East Sea
-
Miami Heat earn first win of NBA season with Antetokounmpo
-
Brewers catcher Contreras named World Series MVP
-
Brewers beat Rays 4-1 to capture first World Series title
-
Asian stock markets fluctuate after mixed tech results
-
Philippine island fights rising seas with nature, not concrete
-
Samsung logs record quarterly profits despite investor AI jitters
-
Bangladesh presses India before Ganges water treaty expires
-
Miami stumble to draw against Cincinnati despite Suarez strike
-
Trump accuses Alaska Democrats of fraud over same-name scandal
-
Bangladesh scrambling as Ganges water treaty to expire
-
Spain mourns after latest train tragedy kills 68
-
England in peril with Rugby League World Cup semi spots at stake
-
Trump's border: quiet, but few people are happy
-
Antonelli ready to rewrite the Formula One record books in Mexico
-
Australian defence chief says China military buildup creating 'pressure' in SE Asia
-
EU, Canada to build 'new chapter' in alliance at Montreal summit
-
No penalty practice? No problem for Man City in shoot-out win
-
Argentine football fan jailed for threats over Di Maria return
-
Microsoft beats expectations fueled by Azure cloud business
-
Liverpool beat Chelsea in League Cup shoot-out, Man City survive scare
-
Chelsea win as Bayern draw with Madrid in Women's Champions League
-
Inter leave it late again in Serie A as AC Milan, Juventus lose
-
Kane watches as Bayern cruise into German Cup last 16
-
Shares in Google owner Alphabet plummet on profit miss, ad slowdown
-
Bayern boss Kompany out of hospital after meningeal irritation
-
Putin hails Elon Musk as 'truly a genius'
-
Shares in Google owner Alphabet sink on profit miss, ad slowdown
-
US stocks eye big tech earnings as Fed holds rates steady
-
Chelsea win as Bayern and Madrid draw in Women's Champions League
-
US Fed holds interest rates steady despite 'too high' inflation
-
Made with munitions from the Falklands War, a 'Chalice of Peace' for the pope
-
Rwanda cannot be blamed for what happens in DR Congo, FM says
-
Pioneering US labor leader Dolores Huerta dies at 96
-
Inter leave it late again in Serie A as Bologna sink AC Milan
-
Italian PM slams 'shameful' release of alleged protest organiser
-
Bolsonaro's escape to the US: How it happened
-
Hollywood producer Kennedy to head LA28 Olympic ceremony plans
-
Russell calls on Scotland to 'kick on' and beat big teams
-
Djokovic wins Basel opener to boost ATP Finals bid
-
Airbus aims for record deliveries despite disappointing quarter
Does "vibe coding" make everyone a programmer?
Can a complete tech novice create a website using everyday language on ChatGPT?
That's the promise, misleading for some, of "vibe coding," the latest Silicon Valley catchphrase for an advance in generative AI that some say makes computer programming as simple as chatting online.
"You fully give in to the vibes, embrace exponentials, and forget that the code even exists," OpenAI co-founder and former Tesla employee Andrej Karpathy described in early February, in a message posted on X (formerly Twitter), using the term for the first time.
"I'm building a project or web app, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works," he said.
The developer and entrepreneur was referring to the new generative AI models that produce lines of code on demand in everyday language, through writing or speech.
The concept of "vibe coding" remained confined to the AI community until New York Times columnist Kevin Roose claimed to have created websites and apps without any knowledge of programming.
"Just having an idea, and a little patience, is usually enough," he wrote.
The ChatGPT and Claude interfaces can write an entire program line by line on demand, as can Gemini, which launched its dedicated version, Gemini Canvas, on Tuesday.
Other generative AI platforms specifically dedicated to coding have also made their mark in recent months, from Cursor to Loveable, or Bolt, Replit and Windsurf.
"Maybe, just maybe, we're looking at a fundamental shift in how software is created and who creates it," said online marketing specialist Mattheo Cellini on Substack.
"It's unlikely to make coding irrelevant, but it may change the way developers work," suggested Yangfeng Ji, professor of computer science at the University of Virginia.
"This could lead to some job displacement, particularly for those focused solely on basic coding tasks."
Even before "vibe coding," a downturn was being seen by some in IT employment as the first effects of generative AI began to be felt.
The sector shed nearly 10,000 jobs in the US in February, according to the Department of Labor, and its headcount is at a three-year low.
- Expertise needed? -
Among code novices, many find it hard to catch the vibe.
"People who do not have programming expertise often struggle to use these kinds of models because they don't have the right kinds of tools or knowledge to actually evaluate the output," said Nikola Banovic, professor of computer science at the University of Michigan.
On social media, the few newbies who report on their "vibe coding" quickly complain that it's not as easy as some want to believe.
Without mastering computing complexities like digital directories, runtime environments or application programming interfaces (APIs), it's hard to create an app that works.
Despite his coding knowhow, Claude Rubinson, a professor of sociology at the University of Houston-Downtown, wanted to create an application for his students two years ago without tinkering with the code generated by ChatGPT.
After a lot of trial and error, the app finally worked, but "I'm convinced it wouldn't have worked if I hadn't understood the code," which allowed him to guide the interface using the appropriate language.
This brought home the importance of the "prompt": mastering the request submitted to obtain the desired result.
"Programmers have certain levels of AI literacy that allows them to get what they want out of the models," said Banovic.
Everyday users "will not know how to prompt," h warned.
G.Frei--VB