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

EUR -
AED 4.177613
AFN 80.776958
ALL 98.674291
AMD 442.254844
ANG 2.049839
AOA 1041.815217
ARS 1325.015571
AUD 1.77753
AWG 2.050078
AZN 1.930861
BAM 1.954283
BBD 2.277932
BDT 138.142794
BGN 1.956115
BHD 0.428723
BIF 3381.475805
BMD 1.137352
BND 1.489844
BOB 7.855869
BRL 6.392603
BSD 1.136928
BTN 96.840421
BWP 15.522091
BYN 3.720713
BYR 22292.106206
BZD 2.283828
CAD 1.574386
CDF 3273.299627
CHF 0.936661
CLF 0.028029
CLP 1075.582507
CNY 8.267979
CNH 8.266601
COP 4773.467844
CRC 574.769111
CUC 1.137352
CUP 30.139837
CVE 110.179011
CZK 24.924961
DJF 202.462879
DKK 7.464893
DOP 66.999772
DZD 150.740411
EGP 57.771771
ERN 17.060285
ETB 152.189631
FJD 2.605106
FKP 0.849211
GBP 0.849329
GEL 3.121981
GGP 0.849211
GHS 16.258311
GIP 0.849211
GMD 81.322521
GNF 9847.271442
GTQ 8.756166
GYD 238.573806
HKD 8.823421
HNL 29.504363
HRK 7.53724
HTG 148.764551
HUF 404.313979
IDR 19017.555034
ILS 4.12516
IMP 0.849211
INR 96.949905
IQD 1489.444117
IRR 47882.534347
ISK 146.081688
JEP 0.849211
JMD 180.101815
JOD 0.806612
JPY 161.979428
KES 146.946635
KGS 99.461261
KHR 4551.427846
KMF 491.620598
KPW 1023.732863
KRW 1625.236725
KWD 0.348326
KYD 0.947465
KZT 581.578666
LAK 24591.915438
LBP 101870.04373
LKR 340.575696
LRD 227.392532
LSL 21.096928
LTL 3.358306
LVL 0.687973
LYD 6.220173
MAD 10.546369
MDL 19.566815
MGA 5131.063151
MKD 61.575461
MMK 2388.195606
MNT 4063.055995
MOP 9.08475
MRU 45.011465
MUR 51.407236
MVR 17.515996
MWK 1971.487361
MXN 22.252725
MYR 4.908247
MZN 72.801774
NAD 21.096928
NGN 1821.492028
NIO 41.837532
NOK 11.805172
NPR 154.949838
NZD 1.9184
OMR 0.437884
PAB 1.136913
PEN 4.168365
PGK 4.710324
PHP 63.575149
PKR 319.398439
PLN 4.267346
PYG 9104.934114
QAR 4.144765
RON 4.977848
RSD 117.109117
RUB 93.263383
RWF 1625.253012
SAR 4.266304
SBD 9.509741
SCR 16.177403
SDG 682.98601
SEK 10.969993
SGD 1.48723
SHP 0.89378
SLE 25.875339
SLL 23849.691791
SOS 649.801435
SRD 41.911684
STD 23540.897494
SVC 9.94828
SYP 14787.811104
SZL 21.089819
THB 38.01543
TJS 12.005819
TMT 3.992107
TND 3.400946
TOP 2.663793
TRY 43.778882
TTD 7.714014
TWD 36.458396
TZS 3059.478312
UAH 47.234259
UGX 4166.748076
USD 1.137352
UYU 47.871797
UZS 14721.575318
VES 98.435697
VND 29576.848055
VUV 137.968789
WST 3.15057
XAF 655.454098
XAG 0.034511
XAU 0.000344
XCD 3.073752
XDR 0.815175
XOF 655.448339
XPF 119.331742
YER 278.708486
ZAR 21.117949
ZMK 10237.534291
ZMW 31.806317
ZWL 366.226995
  • SCS

    0.1500

    10.01

    +1.5%

  • NGG

    0.1900

    73.04

    +0.26%

  • GSK

    0.9100

    38.97

    +2.34%

  • BTI

    0.4700

    42.86

    +1.1%

  • BCC

    -0.8300

    94.5

    -0.88%

  • CMSC

    -0.0800

    22.24

    -0.36%

  • RBGPF

    -0.4500

    63

    -0.71%

  • AZN

    1.7800

    71.71

    +2.48%

  • RIO

    0.0100

    60.88

    +0.02%

  • BP

    -1.0600

    28.07

    -3.78%

  • JRI

    0.1300

    12.93

    +1.01%

  • CMSD

    -0.1300

    22.35

    -0.58%

  • RYCEF

    -0.1300

    10.12

    -1.28%

  • BCE

    0.1100

    21.92

    +0.5%

  • RELX

    0.4300

    53.79

    +0.8%

  • VOD

    0.0100

    9.58

    +0.1%

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