The Prague Post - Does "vibe coding" make everyone a programmer?

EUR -
AED 4.268335
AFN 73.221319
ALL 95.995822
AMD 435.377378
ANG 2.0801
AOA 1065.775351
ARS 1645.160368
AUD 1.642686
AWG 2.09494
AZN 1.975549
BAM 1.956114
BBD 2.328974
BDT 141.422701
BGN 1.914963
BHD 0.438701
BIF 3434.762603
BMD 1.162242
BND 1.480699
BOB 8.019287
BRL 6.049697
BSD 1.156391
BTN 106.669958
BWP 15.71459
BYN 3.379943
BYR 22779.934575
BZD 2.325573
CAD 1.578737
CDF 2510.44169
CHF 0.903591
CLF 0.026942
CLP 1063.823364
CNY 8.032363
CNH 8.001632
COP 4374.409916
CRC 550.490732
CUC 1.162242
CUP 30.799401
CVE 110.282702
CZK 24.359438
DJF 205.913939
DKK 7.470743
DOP 69.061383
DZD 152.855691
EGP 61.354848
ERN 17.433623
ETB 177.577468
FJD 2.562917
FKP 0.867634
GBP 0.864999
GEL 3.172683
GGP 0.867634
GHS 12.465001
GIP 0.867634
GMD 84.843804
GNF 10136.67072
GTQ 8.869576
GYD 241.918832
HKD 9.094017
HNL 30.607045
HRK 7.534234
HTG 151.49171
HUF 387.561655
IDR 19620.962015
ILS 3.590658
IMP 0.867634
INR 107.013159
IQD 1514.849677
IRR 1535204.877032
ISK 145.106082
JEP 0.867634
JMD 181.149078
JOD 0.824067
JPY 183.15532
KES 150.103752
KGS 101.638377
KHR 4640.66505
KMF 493.952675
KPW 1046.051654
KRW 1709.634418
KWD 0.357563
KYD 0.963659
KZT 575.824907
LAK 24770.976172
LBP 103549.821546
LKR 360.137808
LRD 211.040231
LSL 19.388012
LTL 3.431797
LVL 0.703028
LYD 7.385217
MAD 10.859243
MDL 20.039217
MGA 4802.791593
MKD 61.635083
MMK 2440.635948
MNT 4168.12319
MOP 9.309294
MRU 46.163609
MUR 53.405163
MVR 17.95628
MWK 2005.130484
MXN 20.519102
MYR 4.564699
MZN 74.279251
NAD 19.388012
NGN 1622.768117
NIO 42.557014
NOK 11.151545
NPR 170.67013
NZD 1.964891
OMR 0.446894
PAB 1.156386
PEN 4.025846
PGK 4.982821
PHP 68.792842
PKR 325.105184
PLN 4.252989
PYG 7441.194441
QAR 4.217149
RON 5.096895
RSD 117.439871
RUB 90.945831
RWF 1690.571366
SAR 4.363313
SBD 9.350445
SCR 16.671951
SDG 697.936729
SEK 10.628338
SGD 1.480423
SHP 0.871982
SLE 28.504002
SLL 24371.623637
SOS 659.705894
SRD 43.77813
STD 24056.053735
STN 24.504039
SVC 10.117668
SYP 128.493777
SZL 19.401198
THB 36.892447
TJS 11.083813
TMT 4.067845
TND 3.401104
TOP 2.798399
TRY 51.228511
TTD 7.846259
TWD 36.940104
TZS 3010.205727
UAH 50.818476
UGX 4353.698844
USD 1.162242
UYU 46.258818
UZS 14097.262856
VES 502.815511
VND 30497.218534
VUV 139.229241
WST 3.178155
XAF 656.062309
XAG 0.013061
XAU 0.000225
XCD 3.141016
XCG 2.084043
XDR 0.815934
XOF 656.065132
XPF 119.331742
YER 277.314768
ZAR 18.97568
ZMK 10461.571777
ZMW 22.347587
ZWL 374.241308
  • RBGPF

    0.1000

    82.5

    +0.12%

  • GSK

    1.0000

    55.51

    +1.8%

  • CMSC

    0.0350

    23.22

    +0.15%

  • RELX

    0.0000

    35.68

    0%

  • NGG

    0.5500

    90.41

    +0.61%

  • RIO

    0.1400

    90.35

    +0.15%

  • BTI

    0.4600

    58.33

    +0.79%

  • BCE

    -0.1800

    25.88

    -0.7%

  • AZN

    0.7300

    194.95

    +0.37%

  • BP

    0.2100

    40.65

    +0.52%

  • BCC

    -0.8600

    74.49

    -1.15%

  • CMSD

    -0.0400

    23.16

    -0.17%

  • RYCEF

    -0.0600

    16.9

    -0.36%

  • JRI

    0.0100

    12.58

    +0.08%

  • VOD

    -0.0300

    14.48

    -0.21%

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.

M.Jelinek--TPP