quantiq

Not sure why this didn't get more attention, it's a good article. It's weird that people don't have more awareness that AI causes eventual deskilling which leads to worse engineering judgement.

oh dear.

I'm tired boss.

Not even using their own core engine is genuinely bleak.

> I think they said they will discontinue Air

That doesn't exactly inspire confidence that this product will stick around.

Their AI implementations are an absolute mess.

I know because I've tried practically all of their AI product offerings and not a single one feels coherent.

It still suffers the same problems as Junie, which is that their harness is far too bloated.

Yeah, I'm not even sure what this is, or whether or not this is even intended to be a serious project. It just comes across to me as deeply unprofessional. I say this as someone who doesn't even like Vercel and has their own gripes with that bizarrely run company.

The docs say that none of the code has been reviewed or tested properly, so how serious is this for people to run in a production setup where many companies are going are not going to be super enthused that their production environment has been 'vibecoded' in a week? It just reads to me like a not-so-subtle middle finger to the Vercel guys.

On a side note, I find it extremely weird that the current AI era of software development is turning the state of the entire field into a reenactment of Lord of the Flies. Bizarre behavior all around from people who should know better.

We hired some LLM cowboy developer externals that were pushing out a plethora of PRs daily and a large portion of our team's time at one point was dedicated entirely to just doing PR reviews. Eventually we let them go, and the last few months for us has been dedicated to cleaning up vast quantities of unmaintainable LLM code that's entered our codebase.

I think it's still early days, and it's probably the case that a lot of software development teams have yet to realize that a team basically just doing PR reviews is a strong indication that a codebase is very quickly trending away from maintainability. Our team is still heavily using LLMs and coding agents, but our PR backlog recently has been very manageable.

I suspect we'll start seeing a lot of teams realize they're inundated with tech debt as soon as it becomes difficult for even LLMs to maintain their codebases. The "go fast and spit out as much code as humanly possible" trend that I think has infected software development will eventually come back to bite quite a few companies.

Yeah, I'm not putting stock in this at all. The methodology of this survey seems dubious.

This has to be someone working solely on personal projects right? Because I don't know anyone who actually works like this and frequently the code that AI will spit out is actually quite bad.

>The Orchard is a two story affordable housing complex in Santa Ana, California. It serves the area's chronically homeless residents

I think the reason for all of this is actually fairly boring. Someone with a history of mental illness and/or schizophrenia filing fraudulent documents and writing nonsense chatGPT code assuming it is some kind of AGI-singularity-oracle. It wouldn't be the first time I've seen someone with a history of mental illness assume these systems are more capable than what they actually are in reality.

Django is such a lovely framework I can't speak higher praises of it. I'm blessed to still be able to use it in my day to day work. It's maybe not the most flashy framework out there these days but Django and Rails are really the Toyota Corollas and Honda Civics of the web dev world that often go so underappreciated for their unfussy reliability. :)