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

USD -
AED 3.672504
AFN 65.503991
ALL 80.193613
AMD 365.443623
ANG 1.789783
AOA 918.000367
ARS 1475.150612
AUD 1.415829
AWG 1.80125
AZN 1.70397
BAM 1.690479
BBD 2.011669
BDT 122.606854
BGN 1.696366
BHD 0.37668
BIF 2985.954449
BMD 1
BND 1.277583
BOB 11.640953
BRL 5.222404
BSD 0.998833
BTN 95.261679
BWP 13.45607
BYN 3.037988
BYR 19600
BZD 2.008816
CAD 1.38765
CDF 2273.000362
CHF 0.813662
CLF 0.023213
CLP 913.600415
CNY 6.743204
CNH 6.74452
COP 3115.519253
CRC 449.371191
CUC 1
CUP 26.5
CVE 95.306625
CZK 20.930304
DJF 177.864212
DKK 6.460604
DOP 58.464065
DZD 131.663425
EGP 49.854358
ERN 15
ETB 161.573793
EUR 0.864504
FJD 2.234204
FKP 0.739036
GBP 0.73929
GEL 2.610391
GGP 0.739036
GHS 10.937378
GIP 0.739036
GMD 73.503851
GNF 8773.931458
GTQ 7.6209
GYD 208.928649
HKD 7.84715
HNL 26.775574
HRK 6.512304
HTG 130.645231
HUF 313.830388
IDR 17828.1
ILS 2.955104
IMP 0.739036
INR 95.450504
IQD 1308.440296
IRR 1374587.503816
ISK 122.903814
JEP 0.739036
JMD 158.174511
JOD 0.70904
JPY 159.30404
KES 129.09806
KGS 87.450384
KHR 4041.661265
KMF 427.00035
KPW 900.000294
KRW 1416.470383
KWD 0.30868
KYD 0.832361
KZT 463.468603
LAK 22542.892951
LBP 89443.536886
LKR 332.365271
LRD 181.287005
LSL 16.158607
LTL 2.95274
LVL 0.60489
LYD 6.359825
MAD 9.264013
MDL 17.319677
MGA 4300.099399
MKD 53.178616
MMK 2099.791609
MNT 3596.010349
MOP 8.073123
MRU 40.112364
MUR 47.103741
MVR 15.450378
MWK 1731.967674
MXN 17.023504
MYR 4.085904
MZN 63.910377
NAD 16.158607
NGN 1359.570377
NIO 36.760448
NOK 9.442604
NPR 152.41886
NZD 1.677149
OMR 0.381252
PAB 0.998833
PEN 3.368858
PGK 4.486797
PHP 61.465038
PKR 277.41994
PLN 3.72275
PYG 5995.073253
QAR 3.641125
RON 4.526704
RSD 101.421842
RUB 83.996716
RWF 1468.77566
SAR 3.752773
SBD 8.048583
SCR 13.755996
SDG 600.503676
SEK 9.527038
SGD 1.279604
SHP 0.740866
SLE 24.503667
SLL 20969.499227
SOS 570.811185
SRD 37.974504
STD 20697.981008
STN 21.176369
SVC 8.739358
SYP 13001.999906
SZL 16.156273
THB 33.143038
TJS 9.223994
TMT 3.51
TND 2.928476
TOP 2.40776
TRY 47.867504
TTD 6.76693
TWD 32.021604
TZS 2646.873244
UAH 44.681879
UGX 3710.618436
UYU 40.019016
UZS 11890.747223
VES 770.109104
VND 26148.5
VUV 117.940389
WST 2.73449
XAF 566.970915
XAG 0.015456
XAU 0.000229
XCD 2.70255
XCG 1.800078
XDR 0.707052
XOF 566.970915
XPF 103.081378
YER 237.203589
ZAR 16.16923
ZMK 9001.203584
ZMW 18.87722
ZWL 321.999592
  • CMSC

    -0.0250

    21.45

    -0.12%

  • NGG

    -0.1500

    81.05

    -0.19%

  • VOD

    0.2000

    16.42

    +1.22%

  • RBGPF

    0.0000

    71.34

    0%

  • BTI

    -0.2900

    57.06

    -0.51%

  • RYCEF

    0.1300

    20.84

    +0.62%

  • RIO

    -0.4100

    95.68

    -0.43%

  • BCE

    0.1500

    23.47

    +0.64%

  • BCC

    -0.8900

    83.24

    -1.07%

  • BP

    0.2196

    42.53

    +0.52%

  • CMSD

    -0.0100

    21.58

    -0.05%

  • RELX

    -0.2400

    34.43

    -0.7%

  • GSK

    -0.4785

    49.52

    -0.97%

  • AZN

    -0.7900

    156.45

    -0.5%

  • JRI

    0.0635

    12.61

    +0.5%

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