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

EUR -
AED 4.234205
AFN 72.635449
ALL 95.291257
AMD 424.896943
ANG 2.06431
AOA 1058.40772
ARS 1667.722533
AUD 1.638004
AWG 2.07531
AZN 1.96177
BAM 1.95496
BBD 2.320153
BDT 141.397441
BGN 1.925334
BHD 0.434806
BIF 3441.55544
BMD 1.15295
BND 1.484562
BOB 7.98857
BRL 6.001147
BSD 1.15188
BTN 110.192247
BWP 15.634218
BYN 3.232112
BYR 22597.817964
BZD 2.316755
CAD 1.609178
CDF 2635.069328
CHF 0.920238
CLF 0.027052
CLP 1064.703328
CNY 7.800456
CNH 7.82246
COP 4144.612757
CRC 531.560209
CUC 1.15295
CUP 30.553172
CVE 110.855632
CZK 24.19477
DJF 204.901748
DKK 7.473893
DOP 67.159736
DZD 154.300451
EGP 60.010698
ERN 17.294248
ETB 183.094229
FJD 2.558743
FKP 0.863874
GBP 0.864684
GEL 3.066585
GGP 0.863874
GHS 13.622125
GIP 0.863874
GMD 84.165444
GNF 10120.015556
GTQ 8.782076
GYD 241.005461
HKD 9.035121
HNL 30.749309
HRK 7.534641
HTG 150.612711
HUF 355.899502
IDR 21001.443537
ILS 3.377025
IMP 0.863874
INR 110.324219
IQD 1510.364364
IRR 1585450.225714
ISK 143.392527
JEP 0.863874
JMD 181.851908
JOD 0.817464
JPY 184.657035
KES 149.169027
KGS 100.825126
KHR 4626.211365
KMF 493.462561
KPW 1037.488016
KRW 1765.587115
KWD 0.356724
KYD 0.959984
KZT 561.019353
LAK 25364.898309
LBP 103246.662974
LKR 388.346498
LRD 210.442162
LSL 19.081853
LTL 3.404361
LVL 0.697407
LYD 7.326944
MAD 10.6775
MDL 20.067296
MGA 4842.390027
MKD 61.646331
MMK 2420.387206
MNT 4126.163609
MOP 9.297686
MRU 46.158362
MUR 55.227814
MVR 17.813489
MWK 2002.674362
MXN 20.139325
MYR 4.694929
MZN 73.684672
NAD 19.081277
NGN 1569.314586
NIO 42.20938
NOK 10.923797
NPR 176.309524
NZD 1.987346
OMR 0.4433
PAB 1.151985
PEN 4.002178
PGK 5.027019
PHP 71.099535
PKR 321.099049
PLN 4.240723
PYG 7088.955835
QAR 4.193851
RON 5.242579
RSD 117.387629
RUB 84.134649
RWF 1686.765698
SAR 4.327941
SBD 9.279613
SCR 15.169328
SDG 692.348129
SEK 10.885265
SGD 1.485951
SHP 0.860794
SLE 28.364128
SLL 24176.785273
SOS 658.334487
SRD 43.062102
STD 23863.735053
STN 24.788423
SVC 10.079453
SYP 127.437971
SZL 19.081455
THB 37.896886
TJS 10.776526
TMT 4.035325
TND 3.363732
TOP 2.776026
TRY 53.16425
TTD 7.80248
TWD 36.428374
TZS 3026.491153
UAH 51.422618
UGX 4343.116129
USD 1.15295
UYU 46.400276
UZS 13797.928439
VES 648.632415
VND 30374.465013
VUV 136.370435
WST 3.14411
XAF 655.672595
XAG 0.016979
XAU 0.000267
XCD 3.115905
XCG 2.076063
XDR 0.816756
XOF 650.836836
XPF 119.331742
YER 275.122609
ZAR 19.05296
ZMK 10377.933385
ZMW 20.245306
ZWL 371.249396
  • RIO

    0.2400

    100.93

    +0.24%

  • CMSC

    -0.0800

    22.36

    -0.36%

  • BCE

    -0.2300

    24.18

    -0.95%

  • RBGPF

    1.4900

    61.5

    +2.42%

  • JRI

    -0.1400

    12.46

    -1.12%

  • BTI

    -0.0300

    59.69

    -0.05%

  • NGG

    -1.6900

    80.17

    -2.11%

  • BCC

    -0.1100

    67.97

    -0.16%

  • CMSD

    -0.1050

    22.41

    -0.47%

  • RYCEF

    -0.3300

    16.52

    -2%

  • GSK

    -0.8800

    50.64

    -1.74%

  • RELX

    -0.6300

    34.52

    -1.83%

  • AZN

    -4.4000

    181.55

    -2.42%

  • VOD

    0.1100

    14.81

    +0.74%

  • BP

    0.7500

    43.72

    +1.72%

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