Berliner Boersenzeitung - Does "vibe coding" make everyone a programmer?

EUR -
AED 4.097314
AFN 78.26226
ALL 97.735734
AMD 430.960091
ANG 1.996429
AOA 1022.935278
ARS 1276.705185
AUD 1.744232
AWG 2.007942
AZN 1.893371
BAM 1.947148
BBD 2.251297
BDT 135.478035
BGN 1.950941
BHD 0.420434
BIF 3317.857862
BMD 1.115523
BND 1.447867
BOB 7.704766
BRL 6.352238
BSD 1.115046
BTN 95.324448
BWP 15.078004
BYN 3.648987
BYR 21864.259196
BZD 2.239748
CAD 1.560177
CDF 3201.55203
CHF 0.936292
CLF 0.027385
CLP 1050.978991
CNY 8.039527
CNH 8.044686
COP 4683.357785
CRC 564.790483
CUC 1.115523
CUP 29.561371
CVE 109.77723
CZK 24.91301
DJF 198.557754
DKK 7.460508
DOP 65.61844
DZD 148.563192
EGP 55.92343
ERN 16.732851
ETB 150.530453
FJD 2.537091
FKP 0.839344
GBP 0.841066
GEL 3.056169
GGP 0.839344
GHS 13.826565
GIP 0.839344
GMD 80.317675
GNF 9656.095362
GTQ 8.560961
GYD 233.283459
HKD 8.717698
HNL 29.013087
HRK 7.533014
HTG 145.901719
HUF 403.001784
IDR 18393.419601
ILS 3.969406
IMP 0.839344
INR 95.510333
IQD 1460.709673
IRR 46963.536444
ISK 145.899306
JEP 0.839344
JMD 177.750208
JOD 0.79135
JPY 162.848011
KES 144.181413
KGS 97.552621
KHR 4462.17336
KMF 491.381483
KPW 1004.028199
KRW 1562.458207
KWD 0.342901
KYD 0.929271
KZT 568.513939
LAK 24114.851208
LBP 99905.891163
LKR 333.637558
LRD 222.999155
LSL 20.128464
LTL 3.293851
LVL 0.674769
LYD 6.151666
MAD 10.344238
MDL 19.423695
MGA 4997.793455
MKD 61.372791
MMK 2342.013577
MNT 3996.175754
MOP 8.975519
MRU 44.132709
MUR 51.436586
MVR 17.246174
MWK 1933.409341
MXN 21.800328
MYR 4.792315
MZN 71.283094
NAD 20.128464
NGN 1785.953064
NIO 41.027703
NOK 11.609085
NPR 152.519316
NZD 1.898666
OMR 0.42944
PAB 1.115046
PEN 4.110934
PGK 4.634408
PHP 62.265158
PKR 313.989858
PLN 4.267379
PYG 8902.444039
QAR 4.064042
RON 5.108879
RSD 116.71142
RUB 90.029187
RWF 1596.705407
SAR 4.183906
SBD 9.319489
SCR 15.859904
SDG 669.868908
SEK 10.919804
SGD 1.450655
SHP 0.876626
SLE 25.323173
SLL 23391.968769
SOS 637.268444
SRD 40.807519
STD 23089.082734
SVC 9.756649
SYP 14503.96289
SZL 20.133541
THB 37.309807
TJS 11.495821
TMT 3.90991
TND 3.361862
TOP 2.612668
TRY 43.322457
TTD 7.563394
TWD 33.70186
TZS 3009.12579
UAH 46.284339
UGX 4079.872027
USD 1.115523
UYU 46.393653
UZS 14456.700182
VES 104.901631
VND 28916.040548
VUV 133.857834
WST 3.096927
XAF 653.055299
XAG 0.034788
XAU 0.000351
XCD 3.014758
XDR 0.819505
XOF 653.055299
XPF 119.331742
YER 272.293457
ZAR 20.199988
ZMK 10041.049761
ZMW 29.971827
ZWL 359.198089
  • JRI

    0.0100

    12.75

    +0.08%

  • CMSC

    -0.0200

    22.08

    -0.09%

  • BCC

    0.9800

    91.97

    +1.07%

  • RIO

    -0.5100

    62.24

    -0.82%

  • SCS

    0.0200

    10.52

    +0.19%

  • RBGPF

    1.5000

    64.5

    +2.33%

  • NGG

    0.6500

    70.68

    +0.92%

  • BCE

    -0.0600

    21.57

    -0.28%

  • BTI

    1.0750

    42.445

    +2.53%

  • GSK

    0.2591

    37.4

    +0.69%

  • RYCEF

    0.0100

    10.8

    +0.09%

  • BP

    0.1450

    29.775

    +0.49%

  • RELX

    0.2600

    54.3

    +0.48%

  • AZN

    0.5550

    68.515

    +0.81%

  • VOD

    0.1150

    9.385

    +1.23%

  • CMSD

    0.0372

    22.05

    +0.17%

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.

(O.Joost--BBZ)