My thought exactly. What a terrible background!

So we are calling the developers as sloppy now just because they use AI? It is entirely possible to use AI and still produce good code - the effort required changes, but so long as it is done by a diligent developer capable of asessing and correcting AI code, it should be fine.

That's my point, diligent use of AI is indistinguishable. And because of bad rep we will see any bad code called out "AI slop".

If they work, does it matter?

Separate from building your own code, ,of course you may have your own standards to apply.

But for apps, well, I never had a chance to see how good or bad the code was before AI was about, so why should I care now, so long as what I paid for does what it says it does (and nothing nefarious..)

Some programmers have ethical concerns around the use of LLMs. It's like saying "my clothes still work, why should it matter if child labour made them?"

I don't know wnything of the ethics of any real meatbag developers that are working on the code or app I install on my phone either. I fail to see how, for pre-packaged code specifically, it being AI or not is a problem; ~ rather, surely all the concerns we have about AI code (hopefully properly developer reviewed.. - which I suspect is where the real problem lies) apply to developer written code also, when it comes to pre-packaged apps.

This seems tenuous. The LLM is not being exploited.

> If they work, does it matter?

The blog post provides something akin to answer to this question:

You see, the main allure of LLMs is that they allow the developer to be more lazy. That’s kind of the whole point! You just prompt, sit back and relax. So it should not surprise you to hear that this attitude is then reflected in everything the vibe-coder touches

As I understand it, one of concerns is that with the lowered barriers there comes a flood of low quality software, vibe coded by very lazy and not very talented people.

This might be actually more of a human problem, but it's a problem nevertheless.

I had no visibility of developer attentiveness or lack thereof, not skill or code quality before AI was around, for any apps I downloaded to my phone.

I fail to see why worrying about AI code quality is any different to worrying about developer code quality when it comes to pre packaged apps.

With code I am writing, some AI generated, my work load has not really decreased, nor have I gotten lazy. My work has changed to a degree, and now involves reviewing and guiding and double checking AI code where I did not have to before, but I am certainly still working just as hard, and accomplishing more with AI's help in spite of the change in workload it brings.

delivering bad AI code because you got lazy is not the AI fault, it's the developers fault.

You can't call people lazy because they use LLMs, just like you can't call people lazy because they travel by train/plane/cars instead of their own feet.

> You can't call people lazy because they use LLMs

I haven't done that at all.

> If they work, does it matter?

If you're using an LLM to write your code, odds are very high it does not work.

maybe, but it's a step or two up from blocking roads?

Stopping traffic on railways isn't much different from stopping traffic on highways, is it?

Depends on how it's done I think: breaking stuff vs sitting on it. And sitting on a highway is also quite visibly claiming the action, that is not clear in this case.

If this is XR, would be very dumb and against their message.

IS it a pure coincidence that yesterday I ran a silly prompt to generate from zero to hero an internet subscription service, for whatever it thought would maximise profit and minimise cost. It was interesting to see just how much of the whole 'thing' it attempted to complete - and what it even thought it needed to complete, but definitely not something to actually attempt to deploy and use.

It setup and created a link fetcher/screenshot service. Exactly like the one described in the huggingface attack reports used to generate output into screenshots that agents then OCR'd back out. Its splashscreen described it as something for developers and AI agents to use.

Gotta be a coincidence, right? ... rite?

They effectively try to do something just like this, but getting it setup close to perfect is very difficult.

It isn't difficult at all. It is difficult to do it without significant cost and inconveniences for the people running the training. That's it.

Is this related to why ChatGPT sometimes links to dead URLs?

Some models weird ass around the houses semi-hallucinated path to simply reading the publicly accessible data?

"vs just opening discussing things, considering tradeoffs from experts multiple disciplines weigh in on and then taking an approach that everyone finds most agreeable."

To be honest I struggle to do this with engineers as is, even without AI being a factor. Everyone likes to claim that their way is the right way to do things and fights for it, instead of stepping back and looking at all the options and gracefully acknowledging were things could be done differently for better results.

as per the other reply you have, could you give a bit more detail re: leaking keys?

When it say's it's sorry but it can't today because it's got a headache and it needs to take a mental health day, then let's think about welfare, or a lobotomy.