Dubai Telegraph - Does "vibe coding" make everyone a programmer?

EUR -
AED 4.183233
AFN 72.900796
ALL 91.877285
AMD 414.797448
ANG 2.039348
AOA 1045.665194
ARS 1736.794975
AUD 1.614555
AWG 2.050323
AZN 1.940938
BAM 1.955317
BBD 2.295033
BDT 140.215334
BGN 1.917554
BHD 0.429594
BIF 3432.051477
BMD 1.139068
BND 1.45584
BOB 13.964547
BRL 5.909605
BSD 1.139418
BTN 109.116023
BWP 15.516164
BYN 3.442749
BYR 22325.7403
BZD 2.291733
CAD 1.611725
CDF 2665.420428
CHF 0.943457
CLF 0.027745
CLP 1095.522249
CNY 7.646851
CNH 7.670833
COP 3814.157008
CRC 518.071915
CUC 1.139068
CUP 27.347239
CVE 110.237745
CZK 24.358299
DJF 202.909834
DKK 7.475483
DOP 67.763247
DZD 152.391449
EGP 59.13438
ERN 17.086026
ETB 184.850299
FJD 2.559772
FKP 0.859986
GBP 0.859642
GEL 2.97871
GGP 0.859986
GHS 13.234728
GIP 0.859986
GMD 83.725913
GNF 10021.522331
GTQ 8.701849
GYD 238.411056
HKD 8.934226
HNL 30.583439
HRK 7.533575
HTG 149.123132
HUF 365.202455
IDR 20405.384913
ILS 3.471949
IMP 0.859986
INR 109.142689
IQD 1492.730945
IRR 1565734.922454
ISK 136.984803
JEP 0.859986
JMD 180.27543
JOD 0.807645
JPY 179.158416
KES 147.67349
KGS 99.609484
KHR 4633.85435
KMF 493.217009
KPW 1025.161906
KRW 1543.648431
KWD 0.351563
KYD 0.949565
KZT 504.7852
LAK 25558.681004
LBP 102039.372314
LKR 376.226984
LRD 195.991544
LSL 18.590804
LTL 3.363373
LVL 0.689012
LYD 7.285199
MAD 10.934597
MDL 20.225999
MGA 5030.756222
MKD 61.55978
MMK 2391.810486
MNT 4098.584327
MOP 9.206124
MRU 45.840667
MUR 54.140351
MVR 17.599037
MWK 1975.811511
MXN 20.137822
MYR 4.640683
MZN 72.79829
NAD 18.590804
NGN 1510.837951
NIO 41.929634
NOK 10.830092
NPR 174.585836
NZD 1.992947
OMR 0.439191
PAB 1.139418
PEN 3.868244
PGK 5.076745
PHP 71.01754
PKR 315.746636
PLN 4.37146
PYG 6716.339487
QAR 4.153473
RON 5.27298
RSD 117.420969
RUB 96.076247
RWF 1684.083636
SAR 4.274755
SBD 9.11313
SCR 15.836085
SDG 685.153819
SEK 11.296996
SGD 1.45562
SHP 0.859999
SLE 28.078458
SLL 23885.685201
SOS 651.238991
SRD 42.905863
STD 23576.41575
STN 24.493944
SVC 9.970535
SYP 14810.167401
SZL 18.586405
THB 38.01645
TJS 10.511601
TMT 3.99813
TND 3.373266
TOP 2.742603
TRY 55.748859
TTD 7.750084
TWD 36.141163
TZS 3024.152324
UAH 51.024285
UGX 4462.896617
USD 1.139068
UYU 45.648714
UZS 13485.665874
VES 970.977713
VND 29588.440307
VUV 134.963505
WST 3.127488
XAF 655.957
XAG 0.017716
XAU 0.000265798393
XCD 3.07839
XCG 2.053592
XDR 0.80538
XOF 655.957
XPF 119.331742
YER 269.560946
ZAR 18.57165
ZMK 10252.986409
ZMW 22.227505
ZWL 366.779554
SSP 6507.032816
MXV 2.282055
  • BTI

    -0.3900

    55.63

    -0.7%

  • NGG

    0.2600

    75.49

    +0.34%

  • GSK

    -0.4100

    49.24

    -0.83%

  • RBGPF

    -0.5900

    65.4

    -0.9%

  • RELX

    0.0100

    33.52

    +0.03%

  • CMSC

    -0.1100

    20.4

    -0.54%

  • BCC

    1.0400

    77.14

    +1.35%

  • BCE

    -0.3300

    20.97

    -1.57%

  • RIO

    0.0900

    94.56

    +0.1%

  • AZN

    2.0200

    166.58

    +1.21%

  • RYCEF

    -0.3600

    19.31

    -1.86%

  • BP

    -0.2600

    44.15

    -0.59%

  • JRI

    -0.1500

    11.02

    -1.36%

  • VOD

    0.1300

    16.62

    +0.78%

  • CMSD

    -0.0700

    20.3

    -0.34%

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.

U.Siddiqui--DT