The Japan Times - Does "vibe coding" make everyone a programmer?

EUR -
AED 4.028808
AFN 70.755553
ALL 90.130026
AMD 393.764039
ANG 1.964109
AOA 1005.967559
ARS 1715.99365
AUD 1.649531
AWG 1.974637
AZN 1.858873
BAM 1.957121
BBD 2.215475
BDT 136.812363
BGN 1.945534
BHD 0.415076
BIF 3303.985376
BMD 1.097021
BND 1.418438
BOB 12.93073
BRL 6.510598
BSD 1.099933
BTN 102.56484
BWP 15.537348
BYN 3.289396
BYR 21501.603945
BZD 2.212273
CAD 1.572776
CDF 2501.207019
CHF 0.924783
CLF 0.028303
CLP 1113.925714
CNY 7.313453
CNH 7.322267
COP 3763.416962
CRC 492.427954
CUC 1.097021
CUP 26.39898
CVE 110.338988
CZK 24.434762
DJF 195.880455
DKK 7.474418
DOP 66.214098
DZD 150.55884
EGP 59.01894
ERN 16.455309
ETB 180.54224
FJD 2.517335
FKP 0.836539
GBP 0.837767
GEL 2.846799
GGP 0.836539
GHS 12.930671
GIP 0.836539
GMD 81.179603
GNF 9751.40549
GTQ 8.409639
GYD 230.065319
HKD 8.60249
HNL 29.568693
HRK 7.494806
HTG 144.211443
HUF 373.498767
IDR 20049.148659
ILS 3.619022
IMP 0.836539
INR 102.350159
IQD 1667.572592
IRR 2125273.93073
ISK 137.182022
JEP 0.836539
JMD 174.088322
JOD 0.777758
JPY 174.632506
KES 142.67832
KGS 95.934847
KHR 4475.919736
KMF 492.562405
KPW 987.318932
KRW 1468.954689
KWD 0.342238
KYD 0.916719
KZT 495.234338
LAK 24784.732418
LBP 98508.203863
LKR 366.137183
LRD 184.792228
LSL 18.950594
LTL 3.239217
LVL 0.663577
LYD 7.118741
MAD 10.939385
MDL 20.184627
MGA 4966.307532
MKD 61.596584
MMK 2303.531767
MNT 3957.130087
MOP 8.888217
MRU 44.86886
MUR 51.384788
MVR 16.905341
MWK 1907.370298
MXN 20.989284
MYR 4.51369
MZN 70.110927
NAD 18.949989
NGN 1483.709679
NIO 40.476588
NOK 10.72263
NPR 164.104293
NZD 2.000093
OMR 0.422051
PAB 1.100043
PEN 3.753434
PGK 4.948296
PHP 70.089718
PKR 304.062704
PLN 4.43893
PYG 6896.593092
QAR 3.998681
RON 5.348411
RSD 117.718937
RUB 90.107204
RWF 1627.984228
SAR 4.11572
SBD 8.919456
SCR 15.313199
SDG 659.851711
SEK 11.186083
SGD 1.416517
SHP 0.834363
SLE 24.99005
SLL 23003.97769
SOS 628.627258
SRD 40.984339
STD 22706.11174
STN 24.516663
SVC 9.624498
SYP 14263.462334
SZL 18.945618
THB 37.232934
TJS 10.119794
TMT 3.850542
TND 3.333035
TOP 2.641363
TRY 55.480293
TTD 7.463801
TWD 36.207719
TZS 2918.072676
UAH 49.552101
UGX 4658.123514
USD 1.097021
UYU 44.649533
UZS 13177.896528
VES 1006.645583
VND 28266.381534
VUV 132.90864
WST 3.097199
XAF 655.957
XAG 0.02655
XAU 0.000310854369
XCD 2.964753
XCG 1.982375
XDR 0.77565
XOF 655.957
XPF 119.331742
YER 259.500618
ZAR 19.245932
ZMK 9874.49523
ZMW 22.605055
ZWL 353.240189
SSP 6343.680987
MXV 2.353445
  • RYCEF

    0.1000

    19.81

    +0.5%

  • VOD

    -0.2500

    16.33

    -1.53%

  • CMSC

    -0.2800

    20.12

    -1.39%

  • RBGPF

    -2.0000

    65

    -3.08%

  • RIO

    -0.2500

    94.16

    -0.27%

  • BTI

    -1.2000

    54.85

    -2.19%

  • NGG

    -0.3000

    74.94

    -0.4%

  • GSK

    -0.3500

    49.35

    -0.71%

  • BCE

    -0.4200

    20.14

    -2.09%

  • CMSD

    -0.3400

    19.93

    -1.71%

  • BP

    -0.9100

    43.52

    -2.09%

  • RELX

    0.1700

    33.24

    +0.51%

  • BCC

    -0.6200

    75.97

    -0.82%

  • AZN

    -1.9400

    164.21

    -1.18%

  • JRI

    0.0000

    10.77

    0%

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.

K.Inoue--JT