The China Mail - Does "vibe coding" make everyone a programmer?

USD -
AED 3.672504
AFN 64.000368
ALL 82.087167
AMD 368.450607
ANG 1.790403
AOA 918.000367
ARS 1428.330353
AUD 1.418842
AWG 1.801525
AZN 1.70397
BAM 1.689603
BBD 2.013822
BDT 122.983888
BGN 1.69088
BHD 0.37683
BIF 2970.152477
BMD 1
BND 1.283746
BOB 6.909421
BRL 5.061504
BSD 0.99987
BTN 95.052482
BWP 13.460326
BYN 2.766446
BYR 19600
BZD 2.010971
CAD 1.39945
CDF 2295.000362
CHF 0.796927
CLF 0.022916
CLP 904.902596
CNY 6.771504
CNH 6.76346
COP 3492.894475
CRC 454.839964
CUC 1
CUP 26.5
CVE 95.257224
CZK 20.874704
DJF 178.057103
DKK 6.461104
DOP 58.710207
DZD 133.120816
EGP 51.846573
ERN 15
ETB 157.556391
EUR 0.863904
FJD 2.215904
FKP 0.745521
GBP 0.745768
GEL 2.65504
GGP 0.745521
GHS 11.098441
GIP 0.745521
GMD 73.000355
GNF 8759.016889
GTQ 7.622133
GYD 209.191828
HKD 7.83605
HNL 26.736642
HRK 6.513804
HTG 130.733014
HUF 304.250388
IDR 17779.3
ILS 2.92082
IMP 0.745521
INR 95.110504
IQD 1309.835428
IRR 1375877.503816
ISK 124.650386
JEP 0.745521
JMD 158.489914
JOD 0.70904
JPY 160.22904
KES 129.480368
KGS 87.450384
KHR 4017.105093
KMF 426.00035
KPW 900.00035
KRW 1518.230383
KWD 0.30848
KYD 0.833312
KZT 488.937843
LAK 22017.191482
LBP 89543.518639
LKR 335.207982
LRD 181.97918
LSL 16.286467
LTL 2.95274
LVL 0.60489
LYD 6.372943
MAD 9.260766
MDL 17.462745
MGA 4172.605935
MKD 53.254719
MMK 2099.254457
MNT 3578.100965
MOP 8.070062
MRU 39.65617
MUR 47.250378
MVR 15.460378
MWK 1733.834392
MXN 17.222904
MYR 4.057604
MZN 63.903729
NAD 16.286467
NGN 1360.503725
NIO 36.793227
NOK 9.513504
NPR 152.084143
NZD 1.714972
OMR 0.384251
PAB 0.99987
PEN 3.400458
PGK 4.378213
PHP 60.771038
PKR 278.191957
PLN 3.66995
PYG 6122.413719
QAR 3.65522
RON 4.526104
RSD 101.386549
RUB 72.4589
RWF 1468.359898
SAR 3.753804
SBD 8.045573
SCR 14.065224
SDG 600.503676
SEK 9.47869
SGD 1.284504
SHP 0.746601
SLE 24.650371
SLL 20969.503664
SOS 571.465595
SRD 37.509504
STD 20697.981008
STN 21.165392
SVC 8.74865
SYP 110.532098
SZL 16.273163
THB 32.873038
TJS 9.318906
TMT 3.51
TND 2.933437
TOP 2.40776
TRY 46.232504
TTD 6.791931
TWD 31.621504
TZS 2624.681439
UAH 44.803507
UGX 3749.298086
UYU 40.387024
UZS 11975.292644
VES 581.95784
VND 26310
VUV 119.415431
WST 2.743477
XAF 566.677033
XAG 0.014699
XAU 0.000237
XCD 2.70255
XCG 1.801996
XDR 0.704764
XOF 566.677033
XPF 103.027947
YER 238.603589
ZAR 16.313845
ZMK 9001.203584
ZMW 17.467928
ZWL 321.999592
  • CMSC

    -0.0200

    22.33

    -0.09%

  • NGG

    0.3200

    81.84

    +0.39%

  • RBGPF

    0.0000

    60.72

    0%

  • VOD

    0.2700

    15.53

    +1.74%

  • BTI

    0.9300

    62.32

    +1.49%

  • RELX

    0.6300

    33.74

    +1.87%

  • RYCEF

    0.4600

    17.5

    +2.63%

  • GSK

    0.1800

    53.04

    +0.34%

  • AZN

    -3.5300

    178.75

    -1.97%

  • RIO

    1.7100

    105.35

    +1.62%

  • CMSD

    -0.0400

    22.26

    -0.18%

  • JRI

    -0.0300

    12.8

    -0.23%

  • BCE

    0.0200

    24.59

    +0.08%

  • BCC

    0.4800

    71.14

    +0.67%

  • BP

    0.1000

    42.78

    +0.23%

Does "vibe coding" make everyone a programmer?
Does "vibe coding" make everyone a programmer? / Photo: © 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.

A.Sun--ThChM