The Japan Times - Does "vibe coding" make everyone a programmer?

EUR -
AED 4.381992
AFN 78.750894
ALL 96.772834
AMD 453.127673
ANG 2.135904
AOA 1094.155023
ARS 1723.006224
AUD 1.703048
AWG 2.147741
AZN 2.027312
BAM 1.958039
BBD 2.409237
BDT 146.15714
BGN 2.003807
BHD 0.449939
BIF 3543.827792
BMD 1.193189
BND 1.513334
BOB 8.264659
BRL 6.197065
BSD 1.196143
BTN 110.049154
BWP 15.598819
BYN 3.379033
BYR 23386.513916
BZD 2.405733
CAD 1.613288
CDF 2693.62495
CHF 0.916376
CLF 0.025958
CLP 1024.95004
CNY 8.290757
CNH 8.289248
COP 4358.721191
CRC 591.863639
CUC 1.193189
CUP 31.619521
CVE 110.393555
CZK 24.34441
DJF 213.004295
DKK 7.467153
DOP 75.15697
DZD 154.308073
EGP 56.001272
ERN 17.897842
ETB 185.122907
FJD 2.620781
FKP 0.864978
GBP 0.867162
GEL 3.215635
GGP 0.864978
GHS 13.067272
GIP 0.864978
GMD 87.697079
GNF 10497.500171
GTQ 9.177688
GYD 250.242459
HKD 9.315768
HNL 31.595737
HRK 7.533438
HTG 156.800337
HUF 381.275947
IDR 20028.222449
ILS 3.690338
IMP 0.864978
INR 109.703873
IQD 1563.674821
IRR 50263.107265
ISK 144.99605
JEP 0.864978
JMD 187.688003
JOD 0.845975
JPY 183.732053
KES 154.243589
KGS 104.344067
KHR 4800.801608
KMF 491.594467
KPW 1073.96939
KRW 1718.932363
KWD 0.365955
KYD 0.996727
KZT 600.839544
LAK 25677.437566
LBP 107117.524012
LKR 370.074058
LRD 221.3444
LSL 18.780413
LTL 3.523179
LVL 0.721749
LYD 7.487269
MAD 10.834074
MDL 20.11961
MGA 5321.625216
MKD 61.62671
MMK 2505.752956
MNT 4256.95142
MOP 9.615976
MRU 47.572579
MUR 54.20683
MVR 18.434798
MWK 2072.570214
MXN 20.625111
MYR 4.698727
MZN 76.065949
NAD 18.864464
NGN 1658.366152
NIO 43.187477
NOK 11.432366
NPR 176.101211
NZD 1.969586
OMR 0.458787
PAB 1.196098
PEN 3.989425
PGK 5.083586
PHP 70.333154
PKR 333.88428
PLN 4.210294
PYG 8026.784566
QAR 4.344522
RON 5.097187
RSD 117.389486
RUB 90.086234
RWF 1733.107728
SAR 4.475517
SBD 9.614842
SCR 16.593195
SDG 717.661496
SEK 10.535953
SGD 1.512051
SHP 0.895201
SLE 29.08404
SLL 25020.586042
SOS 681.867426
SRD 45.34538
STD 24696.61331
STN 24.609533
SVC 10.465837
SYP 13196.168479
SZL 18.855865
THB 37.48407
TJS 11.171609
TMT 4.188095
TND 3.373445
TOP 2.872914
TRY 51.903862
TTD 8.118318
TWD 37.534758
TZS 3072.463155
UAH 51.192889
UGX 4254.972804
USD 1.193189
UYU 45.262709
UZS 14550.945781
VES 437.717685
VND 30924.48849
VUV 142.715687
WST 3.23879
XAF 656.694211
XAG 0.011511
XAU 0.000235
XCD 3.224654
XCG 2.155638
XDR 0.816792
XOF 653.27021
XPF 119.331742
YER 284.461217
ZAR 19.03704
ZMK 10740.145808
ZMW 23.653834
ZWL 384.206528
  • SCS

    0.0200

    16.14

    +0.12%

  • RBGPF

    1.3800

    83.78

    +1.65%

  • CMSC

    0.0100

    23.71

    +0.04%

  • NGG

    0.3900

    85.07

    +0.46%

  • RYCEF

    -0.0700

    16.88

    -0.41%

  • RELX

    -1.2100

    36.17

    -3.35%

  • GSK

    0.5600

    50.66

    +1.11%

  • RIO

    1.7600

    95.13

    +1.85%

  • BCE

    0.2200

    25.49

    +0.86%

  • CMSD

    0.0392

    24.09

    +0.16%

  • BCC

    -0.5500

    80.3

    -0.68%

  • AZN

    -0.6300

    92.59

    -0.68%

  • JRI

    -0.0500

    12.94

    -0.39%

  • VOD

    0.1400

    14.71

    +0.95%

  • BTI

    0.0600

    60.22

    +0.1%

  • BP

    0.3400

    38.04

    +0.89%

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.

K.Inoue--JT