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

USD -
AED 3.672504
AFN 69.456103
ALL 84.764831
AMD 381.290295
ANG 1.789623
AOA 916.000367
ARS 1179.376574
AUD 1.538935
AWG 1.8025
AZN 1.70397
BAM 1.692527
BBD 2.010212
BDT 121.665008
BGN 1.696633
BHD 0.375579
BIF 2964.389252
BMD 1
BND 1.278698
BOB 6.879841
BRL 5.543904
BSD 0.99563
BTN 85.673489
BWP 13.382372
BYN 3.258189
BYR 19600
BZD 1.999913
CAD 1.35865
CDF 2877.000362
CHF 0.812438
CLF 0.024131
CLP 926.026567
CNY 7.181604
CNH 7.18941
COP 4135.519882
CRC 501.838951
CUC 1
CUP 26.5
CVE 95.422093
CZK 21.500904
DJF 177.292199
DKK 6.45704
DOP 58.803167
DZD 130.034183
EGP 49.707931
ERN 15
ETB 134.317771
EUR 0.865404
FJD 2.24825
FKP 0.736781
GBP 0.737708
GEL 2.740391
GGP 0.736781
GHS 10.254857
GIP 0.736781
GMD 70.503851
GNF 8627.060707
GTQ 7.650902
GYD 208.299078
HKD 7.849415
HNL 25.985029
HRK 6.522704
HTG 130.569859
HUF 348.50504
IDR 16299.3
ILS 3.620404
IMP 0.736781
INR 86.184504
IQD 1304.227424
IRR 42100.000352
ISK 124.650386
JEP 0.736781
JMD 159.404613
JOD 0.70904
JPY 144.10604
KES 128.631388
KGS 87.450384
KHR 3992.038423
KMF 426.503794
KPW 899.999993
KRW 1367.140383
KWD 0.30622
KYD 0.829648
KZT 510.665917
LAK 21481.545584
LBP 89206.525031
LKR 298.109126
LRD 199.125957
LSL 17.917528
LTL 2.95274
LVL 0.60489
LYD 5.439834
MAD 9.103111
MDL 17.04989
MGA 4495.694691
MKD 53.251698
MMK 2099.702644
MNT 3581.705956
MOP 8.049154
MRU 39.525767
MUR 45.510378
MVR 15.405039
MWK 1726.364069
MXN 18.95075
MYR 4.245504
MZN 63.950377
NAD 17.917528
NGN 1542.440377
NIO 36.640561
NOK 9.912804
NPR 137.077582
NZD 1.661972
OMR 0.384259
PAB 0.99563
PEN 3.593613
PGK 4.159058
PHP 56.090375
PKR 282.254944
PLN 3.698316
PYG 7944.268963
QAR 3.631864
RON 4.350504
RSD 101.423565
RUB 79.779066
RWF 1437.670373
SAR 3.753593
SBD 8.347391
SCR 14.210372
SDG 600.503676
SEK 9.483995
SGD 1.281904
SHP 0.785843
SLE 22.050371
SLL 20969.503664
SOS 568.99312
SRD 37.528038
STD 20697.981008
SVC 8.711869
SYP 13001.852669
SZL 17.905759
THB 32.405038
TJS 10.055644
TMT 3.5
TND 2.945956
TOP 2.342104
TRY 39.40328
TTD 6.751763
TWD 29.520367
TZS 2573.66622
UAH 41.29791
UGX 3587.901865
UYU 40.932889
UZS 12650.253126
VES 102.167038
VND 26075
VUV 119.102168
WST 2.619186
XAF 567.657825
XAG 0.027532
XAU 0.000291
XCD 2.70255
XDR 0.705984
XOF 567.657825
XPF 103.206265
YER 243.350363
ZAR 17.92535
ZMK 9001.203587
ZMW 24.069058
ZWL 321.999592
  • CMSC

    0.0900

    22.314

    +0.4%

  • CMSD

    0.0250

    22.285

    +0.11%

  • RBGPF

    0.0000

    69.04

    0%

  • SCS

    0.0400

    10.74

    +0.37%

  • RELX

    0.0300

    53

    +0.06%

  • RIO

    -0.1400

    59.33

    -0.24%

  • GSK

    0.1300

    41.45

    +0.31%

  • NGG

    0.2700

    71.48

    +0.38%

  • BP

    0.1750

    30.4

    +0.58%

  • BTI

    0.7150

    48.215

    +1.48%

  • BCC

    0.7900

    91.02

    +0.87%

  • JRI

    0.0200

    13.13

    +0.15%

  • VOD

    0.0100

    9.85

    +0.1%

  • BCE

    -0.0600

    22.445

    -0.27%

  • RYCEF

    0.1000

    12

    +0.83%

  • AZN

    -0.1200

    73.71

    -0.16%

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