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

EUR -
AED 4.35745
AFN 77.716132
ALL 96.672648
AMD 443.429494
ANG 2.123942
AOA 1088.026572
ARS 1695.052999
AUD 1.714878
AWG 2.137492
AZN 2.018143
BAM 1.957263
BBD 2.365788
BDT 143.687374
BGN 1.992584
BHD 0.442833
BIF 3478.799614
BMD 1.186507
BND 1.502423
BOB 8.1171
BRL 6.293705
BSD 1.174583
BTN 107.822118
BWP 16.293244
BYN 3.325313
BYR 23255.530235
BZD 2.362385
CAD 1.623912
CDF 2586.584313
CHF 0.921993
CLF 0.025884
CLP 1022.054308
CNY 8.274224
CNH 8.248126
COP 4242.674865
CRC 581.336867
CUC 1.186507
CUP 31.442426
CVE 110.347925
CZK 24.262045
DJF 209.177194
DKK 7.468004
DOP 74.005614
DZD 153.304853
EGP 55.343057
ERN 17.7976
ETB 182.969299
FJD 2.669991
FKP 0.86969
GBP 0.868208
GEL 3.191928
GGP 0.86969
GHS 12.803622
GIP 0.86969
GMD 86.614852
GNF 10288.775241
GTQ 9.015699
GYD 245.754682
HKD 9.247129
HNL 30.984284
HRK 7.531968
HTG 154.055121
HUF 381.911543
IDR 19904.835471
ILS 3.71952
IMP 0.86969
INR 108.63975
IQD 1538.856431
IRR 49981.592593
ISK 145.79734
JEP 0.86969
JMD 184.898949
JOD 0.841251
JPY 182.891727
KES 151.417916
KGS 103.75953
KHR 4727.532759
KMF 498.332658
KPW 1067.97987
KRW 1710.687469
KWD 0.363546
KYD 0.978936
KZT 591.316859
LAK 25384.182861
LBP 105188.791311
LKR 363.905004
LRD 217.296886
LSL 18.959027
LTL 3.503446
LVL 0.717706
LYD 7.473616
MAD 10.759386
MDL 19.992108
MGA 5313.993399
MKD 61.677129
MMK 2490.828896
MNT 4229.231187
MOP 9.43449
MRU 46.96249
MUR 54.472944
MVR 18.331255
MWK 2036.830652
MXN 20.607126
MYR 4.711027
MZN 75.829212
NAD 18.959027
NGN 1670.969013
NIO 43.222663
NOK 11.547023
NPR 172.516644
NZD 1.989629
OMR 0.454692
PAB 1.174683
PEN 3.940661
PGK 5.023796
PHP 69.937414
PKR 328.662286
PLN 4.212876
PYG 7854.90286
QAR 4.282518
RON 5.124995
RSD 117.489777
RUB 88.861996
RWF 1713.187439
SAR 4.449167
SBD 9.638718
SCR 16.924364
SDG 713.686021
SEK 10.562733
SGD 1.505398
SHP 0.890187
SLE 28.933502
SLL 24880.450216
SOS 670.103574
SRD 45.23083
STD 24558.291997
STN 24.518529
SVC 10.277724
SYP 13122.2591
SZL 18.954244
THB 36.927654
TJS 10.982622
TMT 4.152773
TND 3.419541
TOP 2.856823
TRY 51.486202
TTD 7.97903
TWD 37.302935
TZS 3014.088736
UAH 50.648362
UGX 4152.120266
USD 1.186507
UYU 44.482491
UZS 14256.894113
VES 417.965256
VND 31078.761797
VUV 141.792264
WST 3.269526
XAF 656.450314
XAG 0.010921
XAU 0.000234
XCD 3.206593
XCG 2.116991
XDR 0.816414
XOF 656.450314
XPF 119.331742
YER 282.769152
ZAR 19.077307
ZMK 10679.987975
ZMW 23.044415
ZWL 382.054655
  • RIO

    3.1300

    90.43

    +3.46%

  • BTI

    0.9400

    59.16

    +1.59%

  • BP

    1.1000

    36.53

    +3.01%

  • SCS

    0.0200

    16.14

    +0.12%

  • GSK

    0.5000

    49.15

    +1.02%

  • CMSC

    0.1000

    23.75

    +0.42%

  • NGG

    1.3200

    81.5

    +1.62%

  • CMSD

    0.0900

    24.13

    +0.37%

  • BCC

    -1.1800

    84.33

    -1.4%

  • BCE

    0.4900

    25.2

    +1.94%

  • AZN

    1.2600

    92.95

    +1.36%

  • JRI

    0.0100

    13.68

    +0.07%

  • RYCEF

    0.3000

    17.12

    +1.75%

  • RBGPF

    -0.8100

    83.23

    -0.97%

  • VOD

    0.2300

    14.17

    +1.62%

  • RELX

    0.0600

    39.9

    +0.15%

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)