The Fort Worth Press - Does "vibe coding" make everyone a programmer?

USD -
AED 3.6725
AFN 63.503502
ALL 81.990336
AMD 370.903715
ANG 1.789884
AOA 918.000197
ARS 1401.993023
AUD 1.39913
AWG 1.8025
AZN 1.696504
BAM 1.67146
BBD 2.014355
BDT 122.739548
BGN 1.668102
BHD 0.377403
BIF 2975
BMD 1
BND 1.275858
BOB 6.936925
BRL 4.965705
BSD 1.000128
BTN 95.070143
BWP 13.576443
BYN 2.828953
BYR 19600
BZD 2.011854
CAD 1.36214
CDF 2315.999417
CHF 0.784106
CLF 0.023178
CLP 912.21986
CNY 6.83025
CNH 6.83533
COP 3728.45
CRC 454.739685
CUC 1
CUP 26.5
CVE 94.650328
CZK 20.87905
DJF 177.720468
DKK 6.39432
DOP 59.600085
DZD 132.411933
EGP 53.530803
ERN 15
ETB 157.075029
EUR 0.8557
FJD 2.202202
FKP 0.736222
GBP 0.739275
GEL 2.685011
GGP 0.736222
GHS 11.195005
GIP 0.736222
GMD 73.49532
GNF 8777.497369
GTQ 7.643867
GYD 209.252937
HKD 7.83558
HNL 26.629448
HRK 6.447202
HTG 130.892468
HUF 312.100503
IDR 17433
ILS 2.95367
IMP 0.736222
INR 95.350202
IQD 1310
IRR 1314999.999816
ISK 122.709857
JEP 0.736222
JMD 157.565709
JOD 0.709029
JPY 157.276498
KES 129.191543
KGS 87.420503
KHR 4011.999844
KMF 420.502192
KPW 899.999998
KRW 1475.990178
KWD 0.30811
KYD 0.833593
KZT 463.980036
LAK 21962.493505
LBP 89401.229103
LKR 319.60688
LRD 183.624998
LSL 16.83005
LTL 2.95274
LVL 0.60489
LYD 6.334982
MAD 9.246963
MDL 17.22053
MGA 4154.999745
MKD 52.771476
MMK 2099.74975
MNT 3576.675528
MOP 8.070745
MRU 39.949922
MUR 46.950046
MVR 15.454942
MWK 1741.501824
MXN 17.509742
MYR 3.964503
MZN 63.909913
NAD 16.830069
NGN 1370.929942
NIO 36.719711
NOK 9.27435
NPR 152.110449
NZD 1.702285
OMR 0.384497
PAB 1.000329
PEN 3.505986
PGK 4.332503
PHP 61.7085
PKR 278.749656
PLN 3.64193
PYG 6218.192229
QAR 3.642973
RON 4.441799
RSD 100.477983
RUB 75.00169
RWF 1460.5
SAR 3.752195
SBD 8.025868
SCR 13.35873
SDG 600.507781
SEK 9.299335
SGD 1.277245
SHP 0.746601
SLE 24.649962
SLL 20969.496166
SOS 571.499363
SRD 37.455993
STD 20697.981008
STN 21.15
SVC 8.752948
SYP 110.524984
SZL 16.82975
THB 32.770189
TJS 9.363182
TMT 3.505
TND 2.885502
TOP 2.40776
TRY 45.21975
TTD 6.794204
TWD 31.6445
TZS 2609.999854
UAH 44.075497
UGX 3753.577989
UYU 40.286638
UZS 11997.999952
VES 488.94275
VND 26323
VUV 118.778782
WST 2.715188
XAF 560.591908
XAG 0.013699
XAU 0.00022
XCD 2.70255
XCG 1.8029
XDR 0.69563
XOF 558.501381
XPF 102.375041
YER 238.625019
ZAR 16.80115
ZMK 9001.200271
ZMW 18.731492
ZWL 321.999592
  • RBGPF

    1.6000

    64.7

    +2.47%

  • RYCEF

    -0.0200

    16.33

    -0.12%

  • CMSC

    -0.0100

    22.87

    -0.04%

  • RELX

    0.0100

    36.36

    +0.03%

  • VOD

    -0.1000

    16.05

    -0.62%

  • RIO

    -1.9500

    98.63

    -1.98%

  • GSK

    -0.7100

    50.9

    -1.39%

  • BTI

    -0.3600

    58.35

    -0.62%

  • BP

    0.5300

    46.94

    +1.13%

  • CMSD

    -0.0300

    23.25

    -0.13%

  • NGG

    -0.9800

    87.5

    -1.12%

  • BCE

    -0.0300

    23.93

    -0.13%

  • BCC

    -3.8000

    74.33

    -5.11%

  • AZN

    -1.2800

    183.46

    -0.7%

  • JRI

    -0.0500

    12.93

    -0.39%

Does "vibe coding" make everyone a programmer?
Does "vibe coding" make everyone a programmer? / Photo: © 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.

X.Silva--TFWP