Comments URL: https://news.ycombinator.com/item?id=48457371

Points: 3

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=48421241

Points: 5

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48378047

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48353689

Points: 4

# Comments: 0

I very recently looked at the codebase of a vibe-coded app made by someone with domain expertise but no software dev experience.

It was very clear to me that he had described it from his POV to an AI, and the AI had implemented features in a manner that technically worked, but made future maintenance or expansion extremely tricky, which is why he was now looking for a dev.

For example, in his data schema, for every item on a menu, instead of simply having an array property like so for ingredients:

    items["latte"]["ingredients"] = ["water", "milk", "sugar", ...]

    items["latte"]["has_milk"] = true
    items["latte"]["has_nutmeg"] = false
    items["latte"]["has_cinnamon"] = false
    items["latte"]["has_sugar"] = true
    ...

I totally get how he ended up where he did though. While describing it to the AI, he probably said something like "store info on each menu item's ingredients, they might have milk or coffee or sugar", and the AI created individual flags for them and he didn't think to question it, because he didn't know what's "right" or "wrong", but then as he kept building the AI stuck with keeping individual flags instead of swapping it out with an array mechanism, and he couldn't have known the correct way to implement it.

Only a dev with experience would know how to describe the system to an AI model to get an output that works well, and how to assess the quality of its output beyond what can be assessed through the basic UI. This wasn't a QA failure, it was a design failure.

Comments URL: https://news.ycombinator.com/item?id=48328331

Points: 35

# Comments: 7

Comments URL: https://news.ycombinator.com/item?id=48215107

Points: 20

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=48164849

Points: 8

# Comments: 1

I tasked Claude to analyze the files and figure out what's going on, and eventually we figured out that each file had a custom metadata header + thumbnail + actual image concatenated. I had it write a python script and was able to recover all the images with their metadata. It's nothing a human couldn't have figured out, but it was definitely WAY faster than doing it myself.

I've also used Claude in the past to figure out how to break into routers with locked down firmware. It's great at suggesting and trying different approaches.

Feels like they're just using LLMs to produce enormous levels of output, without understanding that quantity ≠ quality.

Comments URL: https://news.ycombinator.com/item?id=47948045

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47908349

Points: 2

# Comments: 1

https://www.armbian.com/boards?vendor=xunlong

Currently over 41% of facilities are reliant on mandatory overtime, with controllers frequently working 60-hour weeks with only four days off per month.

Comments URL: https://news.ycombinator.com/item?id=47498217

Points: 33

# Comments: 0

> Replicating work is far more difficult than a lot of original work.

Only if the original work was BS. And what, just because it's harder, we shouldn't do it?

https://en.wikipedia.org/wiki/Wikipedia:Interface_administra...

https://en.wikipedia.org/wiki/Special:ListUsers/interface-ad...