-
German AfD's love for Simson mopeds dismays Jewish family behind brand
-
Italy's Meloni throws party to celebrate record in power
-
Two trapped tunnel workers rescued in Nepal 'miracle'
-
After heatwaves, will EU pivot back to the climate fight?
-
Ex-Pakistan coach Gillespie tells Javed 'look in the mirror' over sackings
-
South Korean football referee faces hearing over 'period' insult
-
Monfils falls to Tien in US Open in Grand Slam farewell
-
Toulouse eye Top 14 history after 'difficult' summer
-
Arsenal brace for Chelsea test as Spurs seek spark
-
Springboks and All Blacks seek series lead after war of words
-
Efficient Rybakina reaches US Open third round
-
Bundesliga brings the band back together in Premier League's shadow
-
Taiwan boxer Lin considered 'graceful exit' after Paris Games gold
-
Asian stocks rally as traders pare rate bets ahead of jobs data
-
'I miss my home': Cambodians displaced by conflict start over
-
War-bruised Myanmar finds relief in bareknuckle bloodsport
-
Ailing Auger-Aliassime falls at US Open as Swiatek, Osaka and Gauff advance
-
Gauff downs Badosa to reach US Open third round
-
Tesla launches self-driving 'Cybercab' in Texas
-
New Zealand approves use of party drug MDMA to treat trauma
-
'Wallace & Gromit' creators turn 50 with spook-tacular Shaun yarn
-
Westerners test their mettle at World Nomad Games in Kyrgyzstan
-
New York's Muslims reclaim their city after 9/11 backlash
-
Gauff cruises into US Open third round
-
Premier League transfer windfall a lifeline for ailing French clubs
-
Kyrgios gets month ban for cocaine, enters treatment programme
-
Chile protesters see shades of Pinochet in new security plan
-
Colombian judge bans strikes on guerrillas if minors are present
-
Carreras reverts to fullback as Argentina change four for Australia Test
-
Khachanov shocks ailing Auger-Aliassime, Swiatek and Osaka advance at US Open
-
Wilson back to lead Australia as Kiss rotates team for Argentina
-
Lone juror blocking verdict in US mother's child murder trial: defense
-
Yen surges on new intervention talk, US stocks rally
-
'Kinda chic' - Williams sisters set to launch US Open doubles bid
-
Japan's Ueda fires Lille top of Ligue 1 on debut
-
Volkswagen says cutting 100,000 jobs by end of decade
-
Arsenal chief executive reveals 'dynasty' ambition
-
Russia slaps curfew on charity director over army criticism
-
Spanish PM says no 'solid proof' Morocco planned migrant rush
-
Ailing Auger-Aliassime upset by Khachanov at US Open
-
Iran war is not a war, US VP Vance says
-
Richarlison omitted from Tottenham's Premier League squad
-
Khachanov stuns third-seeded Auger-Aliassime in US Open second round
-
How El Nino is choking the Panama Canal
-
Bordeaux facing sixth-tier football after French federation upholds relegation
-
Hamilton drives his Ferrari dream at Monza
-
Stoic Verstappen looking beyond 'painful' Monza weekend
-
Senegal has an IMF loan, now what?
-
OpenAI begins rollout of new powerful AI model GPT-6 Astra
-
Auger-Aliassime upset by Khachanov at US Open
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.
X.Karnes--AMWN