Dubai Telegraph - Does "vibe coding" make everyone a programmer?

EUR -
AED 4.314099
AFN 76.936429
ALL 96.605599
AMD 448.400944
ANG 2.102883
AOA 1077.044807
ARS 1691.556453
AUD 1.764619
AWG 2.114155
AZN 2.001365
BAM 1.959379
BBD 2.366212
BDT 143.572249
BGN 1.956545
BHD 0.440843
BIF 3482.482632
BMD 1.17453
BND 1.517265
BOB 8.117793
BRL 6.365607
BSD 1.174841
BTN 106.244614
BWP 15.566367
BYN 3.463412
BYR 23020.795811
BZD 2.362806
CAD 1.618562
CDF 2630.948518
CHF 0.934916
CLF 0.027253
CLP 1069.11676
CNY 8.28573
CNH 8.284609
COP 4467.326371
CRC 587.670939
CUC 1.17453
CUP 31.125056
CVE 110.728901
CZK 24.276491
DJF 208.738004
DKK 7.472132
DOP 74.994227
DZD 152.329593
EGP 55.571073
ERN 17.617956
ETB 182.316528
FJD 2.660605
FKP 0.879936
GBP 0.878351
GEL 3.175767
GGP 0.879936
GHS 13.489529
GIP 0.879936
GMD 85.741137
GNF 10207.844111
GTQ 8.998437
GYD 245.78791
HKD 9.137671
HNL 30.777205
HRK 7.537789
HTG 153.990624
HUF 385.234681
IDR 19536.845016
ILS 3.785271
IMP 0.879936
INR 106.356551
IQD 1538.634822
IRR 49474.161194
ISK 148.465122
JEP 0.879936
JMD 188.10359
JOD 0.832789
JPY 182.940203
KES 151.401433
KGS 102.713135
KHR 4705.169188
KMF 492.719958
KPW 1057.060817
KRW 1732.409297
KWD 0.360233
KYD 0.979084
KZT 612.71658
LAK 25463.81945
LBP 105179.197597
LKR 363.02155
LRD 207.92129
LSL 19.826521
LTL 3.468083
LVL 0.710462
LYD 6.366402
MAD 10.795403
MDL 19.860192
MGA 5297.132504
MKD 61.543973
MMK 2466.385496
MNT 4167.553805
MOP 9.420668
MRU 46.676283
MUR 53.915339
MVR 18.092159
MWK 2039.576425
MXN 21.158465
MYR 4.812408
MZN 75.064681
NAD 19.826516
NGN 1706.088063
NIO 43.193401
NOK 11.906572
NPR 169.991784
NZD 2.023657
OMR 0.449616
PAB 1.174841
PEN 4.232665
PGK 5.002564
PHP 69.43241
PKR 329.132826
PLN 4.225315
PYG 7891.414466
QAR 4.276587
RON 5.092651
RSD 117.424033
RUB 93.579038
RWF 1704.243608
SAR 4.407202
SBD 9.603843
SCR 17.568707
SDG 706.484352
SEK 10.887784
SGD 1.517538
SHP 0.881202
SLE 28.335591
SLL 24629.319496
SOS 671.248424
SRD 45.275842
STD 24310.407882
STN 24.958771
SVC 10.279733
SYP 12986.886804
SZL 19.826507
THB 37.021631
TJS 10.796675
TMT 4.122602
TND 3.424975
TOP 2.827988
TRY 50.147872
TTD 7.972529
TWD 36.804032
TZS 2901.090478
UAH 49.639761
UGX 4175.627205
USD 1.17453
UYU 46.104017
UZS 14097.305357
VES 314.116117
VND 30897.196663
VUV 142.580188
WST 3.259869
XAF 657.154562
XAG 0.018954
XAU 0.000273
XCD 3.174228
XCG 2.117359
XDR 0.816516
XOF 655.388352
XPF 119.331742
YER 280.129715
ZAR 19.820676
ZMK 10572.187233
ZMW 27.109403
ZWL 378.198309
  • SCS

    0.0200

    16.14

    +0.12%

  • RBGPF

    0.0000

    81.17

    0%

  • CMSD

    -0.1500

    23.25

    -0.65%

  • NGG

    0.2400

    74.93

    +0.32%

  • GSK

    -0.0700

    48.81

    -0.14%

  • BTI

    -1.2700

    57.1

    -2.22%

  • RIO

    -1.0800

    75.66

    -1.43%

  • RELX

    0.1000

    40.38

    +0.25%

  • CMSC

    -0.1300

    23.3

    -0.56%

  • BCE

    0.3100

    23.71

    +1.31%

  • BCC

    0.2500

    76.51

    +0.33%

  • JRI

    -0.0200

    13.7

    -0.15%

  • RYCEF

    -0.2500

    14.6

    -1.71%

  • AZN

    -0.4600

    89.83

    -0.51%

  • BP

    -0.2700

    35.26

    -0.77%

  • VOD

    0.0500

    12.59

    +0.4%

Does "vibe coding" make everyone a programmer?
Does "vibe coding" make everyone a programmer? / Photo: Lionel BONAVENTURE - AFP

Does "vibe coding" make everyone a programmer?

Can a complete tech novice create a website using everyday language on ChatGPT?

Text size:

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.

U.Siddiqui--DT