-
Prince Harry and family arrive back in Britain: UK media
-
Improving standards transform pole vault as spectacle, says Duplantis
-
German plan for sugar tax on Coke Zero fizzles out
-
India close in on win despite Sri Lanka fightback in second Test
-
Deadly flood hits Nepal-Tibet border, hundreds unaccounted for
-
MEXC TradFi Gala Concludes With Over 170,000 Registrations and $4.3 Billion in Daily Trading Volume
-
Tongue says Root has left England in no doubt over conduct standards
-
Olympic skating champion Liu to skip new season
-
Flags lowered across US for country music legend Dolly Parton
-
Benfica sign midfielder Palhinha from Bayern
-
Stocks gain as oil drops on Mideast hopes
-
Flick says Barca may go without striker as Atletico resist Alvarez sale
-
Bouaddi joins Man City for Premier League teenage record £85.6 mn
-
Too hot to incubate: Nile crocodiles hatch on their own in French reserve
-
Reclusive Hungarian author Peter Nadas dies aged 83
-
Spurs closing in on Man City's Marmoush after signing Savio
-
Man City sign Lille's Bouaddi for 100 mn euros
-
Celtic count the cost of Champions League flop
-
Sooriyabandara, Mendis lead Sri Lanka fightback after follow-on
-
Lebanon accuses Israel of burning forest, farmland in south
-
With ropes and chants, thousands move Japanese castle
-
Nepal floods at China border kill 8, cause 'major casualties' in Tibet
-
Zurich Diamond League: five events to watch
-
France eases cow diets as cheesemakers sweat
-
'Black smoke' chokes Pakistan maternity ward as hospital fire kills 14 infants
-
America unites in mourning for Dolly Parton
-
French flight attendant wins landmark breast cancer ruling
-
Meta and US states discuss settlement in landmark social media trial: report
-
Sri Lanka 83-2 after India enforce follow-on in second Test
-
Fire haze threatens health of millions in Indonesia, ministry warns
-
Pakistan hospital fire kills 14 infants
-
Senegal-made sickle cell treatment raises hopes, reduces costs
-
Iceland to vote on resuming EU talks in close referendum
-
Iran says Hormuz strait still closed despite transit corridor talks
-
North Korea to 'bring joy' to Kim with 100 athletes at Asian Games
-
'Our patron saint': Tennesseans mourn local hero Dolly Parton
-
US LGBTQ community mourns 'diva' Dolly Parton
-
Australian police hunt thieves in $250,000 oyster heist
-
England bid to banish booze woes as Pakistan seek self-respect
-
Coordinated attacks: Thailand's southern insurgency flares
-
High quality, low risk: record number of Japanese in Premier League
-
Asian Games chiefs hold talks as participant numbers balloon
-
Stocks edge higher as oil drops on fresh Mideast hopes
-
Too small for fries: drought shrinks Belgian potatoes
-
Pakistan's girls fight for their place in the boxing ring
-
Drought-hit Danube gives way to fossil hunt in Bulgaria
-
Five things to know about Anthropic ahead of Wall Street debut
-
Julia Curlee, CIA officer fired by White House for being transgender
-
Social media use on the rise among Australian under-16s after ban: data
-
Fave or flop? A guide to gauging video game success
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.
A.Taylor--AT