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

EUR -
AED 4.037723
AFN 78.405346
ALL 98.420291
AMD 430.063576
ANG 1.967954
AOA 1006.947624
ARS 1179.886018
AUD 1.807638
AWG 1.978718
AZN 1.867362
BAM 1.942096
BBD 2.211255
BDT 133.080933
BGN 1.954622
BHD 0.414334
BIF 3255.513116
BMD 1.099288
BND 1.46436
BOB 7.56914
BRL 6.372358
BSD 1.095103
BTN 93.431266
BWP 15.252046
BYN 3.584442
BYR 21546.045319
BZD 2.199837
CAD 1.560626
CDF 3158.254105
CHF 0.942092
CLF 0.027613
CLP 1059.702983
CNY 8.004521
CNH 8.009033
COP 4635.367821
CRC 553.940027
CUC 1.099288
CUP 29.131133
CVE 109.495349
CZK 25.193457
DJF 195.023683
DKK 7.460197
DOP 69.153158
DZD 146.804392
EGP 55.617155
ERN 16.48932
ETB 144.337093
FJD 2.54474
FKP 0.838408
GBP 0.84903
GEL 3.023354
GGP 0.838408
GHS 17.024058
GIP 0.838408
GMD 79.302206
GNF 9504.38923
GTQ 8.457027
GYD 229.952518
HKD 8.547168
HNL 28.11702
HRK 7.532764
HTG 143.780006
HUF 400.567225
IDR 18406.998962
ILS 4.107435
IMP 0.838408
INR 93.811211
IQD 1436.22734
IRR 46540.544582
ISK 143.530896
JEP 0.838408
JMD 172.691987
JOD 0.779382
JPY 160.205849
KES 142.070065
KGS 95.299876
KHR 4365.927003
KMF 489.345406
KPW 989.2802
KRW 1595.478081
KWD 0.338158
KYD 0.914124
KZT 551.751806
LAK 23752.230091
LBP 98435.221736
LKR 324.493107
LRD 219.617313
LSL 20.600601
LTL 3.245911
LVL 0.664948
LYD 5.301262
MAD 10.461542
MDL 19.680364
MGA 5091.764792
MKD 61.846595
MMK 2308.005039
MNT 3852.70846
MOP 8.805893
MRU 43.598454
MUR 49.875785
MVR 16.974212
MWK 1903.971347
MXN 22.497397
MYR 4.88372
MZN 70.225378
NAD 20.600601
NGN 1688.641626
NIO 40.404225
NOK 11.792777
NPR 150.168296
NZD 1.95852
OMR 0.423173
PAB 1.099288
PEN 4.030369
PGK 4.513916
PHP 62.717814
PKR 307.785903
PLN 4.205052
PYG 8725.050394
QAR 4.001442
RON 4.951813
RSD 116.524798
RUB 92.431316
RWF 1557.89252
SAR 4.122563
SBD 9.343154
SCR 15.750661
SDG 659.987561
SEK 11.006852
SGD 1.467226
SHP 0.863868
SLE 25.008714
SLL 23051.521461
SOS 626.240165
SRD 40.195204
STD 22753.042694
SVC 9.618903
SYP 14292.301853
SZL 20.600601
THB 37.493751
TJS 11.964127
TMT 3.845056
TND 3.358629
TOP 2.647431
TRY 41.776116
TTD 7.422472
TWD 36.361535
TZS 2917.860209
UAH 45.384397
UGX 4014.640468
USD 1.099288
UYU 46.504626
UZS 14189.63069
VES 76.997561
VND 28367.538939
VUV 135.878891
WST 3.104262
XAF 652.460541
XAG 0.036881
XAU 0.000361
XCD 2.976062
XDR 0.82882
XOF 652.460541
XPF 119.331742
YER 270.29784
ZAR 20.931049
ZMK 9894.911968
ZMW 30.735254
ZWL 353.970296
  • RBGPF

    1.0200

    69.02

    +1.48%

  • JRI

    -0.8500

    11.97

    -7.1%

  • CMSC

    -0.1190

    22.141

    -0.54%

  • BCC

    -0.2700

    94.36

    -0.29%

  • RYCEF

    -1.3800

    8.42

    -16.39%

  • NGG

    -2.9000

    66.49

    -4.36%

  • RIO

    -4.0630

    54.367

    -7.47%

  • BCE

    0.4200

    23.08

    +1.82%

  • RELX

    -2.4000

    49.04

    -4.89%

  • SCS

    -0.1900

    10.55

    -1.8%

  • CMSD

    -0.2300

    22.44

    -1.02%

  • VOD

    -0.8350

    8.535

    -9.78%

  • AZN

    -4.8800

    69.04

    -7.07%

  • BTI

    -1.6650

    40.255

    -4.14%

  • BP

    -2.8250

    28.515

    -9.91%

  • GSK

    -2.2240

    36.786

    -6.05%

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