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

USD -
AED 3.672504
AFN 66.379449
ALL 81.856268
AMD 381.460103
ANG 1.790403
AOA 917.000011
ARS 1450.462977
AUD 1.491335
AWG 1.80025
AZN 1.698291
BAM 1.658674
BBD 2.014358
BDT 122.21671
BGN 1.6605
BHD 0.377225
BIF 2957.76141
BMD 1
BND 1.284077
BOB 6.926234
BRL 5.521501
BSD 1.00014
BTN 89.856547
BWP 13.14687
BYN 2.919259
BYR 19600
BZD 2.011466
CAD 1.367605
CDF 2200.000277
CHF 0.788565
CLF 0.023065
CLP 904.839701
CNY 7.028499
CNH 7.00831
COP 3743.8
CRC 499.518715
CUC 1
CUP 26.5
CVE 93.513465
CZK 20.600098
DJF 177.720217
DKK 6.343725
DOP 62.690023
DZD 129.439714
EGP 47.548496
ERN 15
ETB 155.604932
EUR 0.84928
FJD 2.269206
FKP 0.741553
GBP 0.740975
GEL 2.68498
GGP 0.741553
GHS 11.126753
GIP 0.741553
GMD 74.502446
GNF 8741.153473
GTQ 7.662397
GYD 209.237241
HKD 7.776215
HNL 26.362545
HRK 6.397502
HTG 130.951927
HUF 330.13797
IDR 16729.15
ILS 3.186051
IMP 0.741553
INR 89.82965
IQD 1310.19773
IRR 42125.000032
ISK 125.698917
JEP 0.741553
JMD 159.532199
JOD 0.708958
JPY 156.016038
KES 128.949983
KGS 87.449982
KHR 4008.85391
KMF 417.999917
KPW 900.017709
KRW 1444.450346
KWD 0.30719
KYD 0.833489
KZT 514.029352
LAK 21644.588429
LBP 89561.205624
LKR 309.599834
LRD 177.018844
LSL 16.645168
LTL 2.95274
LVL 0.60489
LYD 5.412442
MAD 9.124909
MDL 16.777482
MGA 4573.672337
MKD 52.285777
MMK 2099.828827
MNT 3555.150915
MOP 8.011093
MRU 39.604456
MUR 45.94957
MVR 15.449981
MWK 1734.230032
MXN 17.93969
MYR 4.044952
MZN 63.909872
NAD 16.645168
NGN 1450.45006
NIO 36.806642
NOK 10.006865
NPR 143.770645
NZD 1.71416
OMR 0.384496
PAB 1.000136
PEN 3.365433
PGK 4.319268
PHP 58.787497
PKR 280.16122
PLN 3.579481
PYG 6777.849865
QAR 3.645469
RON 4.325201
RSD 99.566018
RUB 78.999707
RWF 1456.65485
SAR 3.750695
SBD 8.153391
SCR 15.233419
SDG 601.495856
SEK 9.171285
SGD 1.284155
SHP 0.750259
SLE 24.074983
SLL 20969.503664
SOS 570.585342
SRD 38.335501
STD 20697.981008
STN 20.777943
SVC 8.75133
SYP 11056.879194
SZL 16.631683
THB 31.069917
TJS 9.19119
TMT 3.51
TND 2.909675
TOP 2.40776
TRY 42.846198
TTD 6.803263
TWD 31.442297
TZS 2473.447014
UAH 42.191946
UGX 3610.273633
UYU 39.087976
UZS 12053.751267
VES 288.088835
VND 26320
VUV 121.140543
WST 2.788621
XAF 556.301203
XAG 0.013898
XAU 0.000223
XCD 2.70255
XCG 1.802508
XDR 0.691025
XOF 556.303562
XPF 101.141939
YER 238.449905
ZAR 16.667502
ZMK 9001.203383
ZMW 22.577472
ZWL 321.999592
  • SCS

    0.0200

    16.14

    +0.12%

  • NGG

    0.2500

    77.49

    +0.32%

  • JRI

    0.0600

    13.47

    +0.45%

  • BCC

    1.4800

    74.71

    +1.98%

  • AZN

    0.3100

    92.45

    +0.34%

  • BTI

    0.2000

    57.24

    +0.35%

  • RIO

    -0.0800

    80.89

    -0.1%

  • RYCEF

    -0.0300

    15.53

    -0.19%

  • BCE

    0.2800

    23.01

    +1.22%

  • GSK

    0.1100

    48.96

    +0.22%

  • BP

    -0.2700

    34.31

    -0.79%

  • RBGPF

    0.0000

    81.26

    0%

  • CMSC

    0.0100

    23.02

    +0.04%

  • CMSD

    0.1200

    23.14

    +0.52%

  • RELX

    -0.0400

    41.09

    -0.1%

  • VOD

    0.0400

    13.1

    +0.31%

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