The "Vibe Coding" Wall of Shame

Post by wan9yu » Mon, Mar 30, 2026, 2:24 AM UTC

Dig1t wrote: post #46

dgb23 wrote: post #39

Earlier quoted context omitted.

I don’t think that’s the point of showcasing these issues. The specific point is that you cannot prompt your way to reliable software (AKA vibe coding). Just as you cannot reach the same goal by glueing together stackoverflow snippets without understanding them.

I understand that, but the interesting bit is to compare how it performs relative to the average human coder. We can point out specific flaws for eternity, but if it makes 1% fewer mistakes or allows humans to code faster without increasing the number average number of mistakes, then I'd say that that's still providing value. I feel like just enumerating different mistakes that it's made is sort of biased against it…

Post by extrabajs » Mon, Mar 30, 2026, 5:20 AM UTC

crazygringo wrote: post #47

extrabajs wrote: post #44

Earlier quoted context omitted.

A control? This is just a list of incidents, not an experiment.

The "Why this matters" section at the bottom is clearly drawing conclusions as if it were an experiment.

Post by sph » Mon, Mar 30, 2026, 5:42 AM UTC

Post by simonw » Mon, Mar 30, 2026, 6:27 AM UTC

Gud wrote: post #76

simonw wrote: post #54

Earlier quoted context omitted.

You got that exactly the wrong way round. Here's one set of numbers from the CATO institute: https://www.cato.org/policy-analysis/illegal-immigrant-murde... The only way your statement holds up is if you treat the act of existing while undocumented as a crime for this comparison, in which case sure - it's a tautology.

First of all, the link you provided mixes illegal migration with legal migration, a classic trick trying to downplay the effects of illegal immigration. Second, it compares murder rates only, in the state of Texas, a state well known to have extreme amounts of legal guns. You can hardly generalise from this data. Here is some interesting data. https://en.wikipedia.org/wiki/Crime_in_Denmark FWIW I don’t live in the US…

Post by Gud » Mon, Mar 30, 2026, 7:15 AM UTC

simonw wrote: post #77

Gud wrote: post #76

Earlier quoted context omitted.

First of all, the link you provided mixes illegal migration with legal migration, a classic trick trying to downplay the effects of illegal immigration. Second, it compares murder rates only, in the state of Texas, a state well known to have extreme amounts of legal guns. You can hardly generalise from this data. Here is some interesting data. https://en.wikipedia.org/wiki/Crime_in_Denmark FWIW I don’t live in the US…

> First of all, the link you provided mixes illegal migration with legal migration No it doesn't. I chose that article specifically because it provides figures for native-born citizens, legal immigrants and illegal immigrants: > Over the 10-year period from 2013 to 2022, the homicide conviction rate in Texas for illegal immigrants was 2.2 per 100,000, compared to 3.0 per 100,000 for native-born Americans. The homicid…