-
Vietnam, South Korea sign deals on tech, nuclear power
-
EU nears approval of Ukraine loan after Hungary pipeline row
-
Duterte jurisdiction appeal quashed at ICC
-
Three ships targeted in Hormuz, Iran seizes two: monitors, Guards
-
Iran murals project defiance in war with US
-
Oil prices rise despite US-Iran ceasefire extension
-
Ships attacked in Gulf as Trump extends Iran ceasefire
-
Germany set to slash growth forecast due to Mideast war
-
Pakistan's capital holds its breath with US-Iran talks in limbo
-
Groundbreaking Iranian snooker star Vafaei takes on the world
-
Sakib Hussain: IPL quick whose mum sold her jewellery to fund cricket dream
-
US-based Buddhist monks bring peace walk to Sri Lanka
-
NASA unveils new space telescope to give 'atlas of the universe'
-
Trump extends ceasefire, claims Iran 'collapsing financially'
-
The tiny, defiant Nile island caught in the heart of Sudan's war
-
UK inflation jumps as Mideast war propels energy prices
-
Oil, stocks mixed as traders weigh outlook after Trump extends truce
-
Anthropic probes unauthorized access to Mythos AI model
-
Stadium that was symbol of NZ post-quake rebuild to hold first match
-
Blazers stun Spurs after Wemby injury, Lakers down Rockets
-
Chinese carmakers aim to build up presence in Europe
-
Maoist landmine legacy haunts India
-
Fiji villagers reject plan for 'Pacific ashtray' in beach paradise
-
India orders school water bells to beat heat
-
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
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