Vampiero
Realistically though, if you really did hire 5 Tims you would deliver in 1/5th of the time and the software would actually be decent on the first iteration.
It seems to me that consultancy companies actually want inexperienced developers because they can bill their inexperience to the client as they train them to become useful. Awful and, as stated, a major source of mental breakdowns for the Tims who have to put up with their bullshit. And also for the juniors who are always running from fire to fire as they try to fix the clusterfucks they created.
This is not how you should do stuff, but it's how everyone does it. At some point it's just the blind leading the blind, because Tim also has other shit to attend to and can't review every LOC on every PR by himself.
I didn't become a senior by being mentored by other people, btw. I became one because I've always loved doing what I do, and nothing more. The internet and physical books mentored me impersonally. So I'm sure that they can mentor other people just fine, and I don't see why I should waste my time just because my boss is stingy and can only hire a couple of people with my experience or drive to learn outside of work.
And let's be clear -- mentoring and being taught something are two very different things. I'm not anal about the latter. I'm anal because I want to write code, I don't want to tell people that they should learn to fucking read the error messages and google them every 5 seconds.
Though right now I'm being very brutally honest. I'm actually nice and friendly to them in person, and I'm very patient. But that causes me to break every once in a while because I secretly loathe it!
Morality and ethics are just a way to hurt profits.
It's like outsourcing your project to [country where programmers are cheap]. You can't expect quality. Deep down you're actually amazed that the project builds at all. But it doesn't take much to reveal that it's just a facade for a generous serving of spaghetti and bugs.
And refactoring the project into something that won't crumble in 6 months requires more time than just redoing the project from scratch, because the technical debt is obscenely high, because those programmers were awful, and because no one, not even them, understands the code or wants to be the one who has to reverse engineer it.
Except that AI is actually MUCH more expensive!
Those comments also add nothing to the discussion (but they make the person who posts them feel INCREDIBLY smug).
And regardless, your digging into my comment history just to prove your worthless point is proof enough that this community is insufferable -- I wasn't complaining about asking for sources, I was complaining about not being sincere about it.
Not that different from LinkedIn to be honest, when you tie your identity to your HN account.
Most of it is because of ancillary stuff and heavy dependencies.
no worse feeling in the world than hearing a doctor confidently tell you that it's all in your head and that you're wasting their time. Ask me how I know..
No way to know until you painstakingly verify every single assertion that the AI made! The author of this article certainly didn't, and the content was good enough to them.
Trust me, AGI is almost there.
And most are too focused on learning whatever slop the industry wants them to learn, so they don't even know that it exists. We need 500 different object oriented languages to do web applications after all. Can't be bothered with learning a new paradigm if it doesn't pay the bills!
It's the most intuitive language I've ever learned and it has forever changed the way I think about problem solving. It's just logic, so it translates naturally from thought to code. I can go to a wikipedia page on some topic I barely know and write down all true statements on that page. Then I can run queries and discover stuff I didn't know.
That's how I learned music theory, how scales and chords work, how to identify the key of a melody... You can't do that as easily and concisely in any other language.
One day, LLM developers will finally open a book about AI and realize that this is what they've been missing all along.
Well, someone earlier in the thread said to abandon Marxist thought because it's obsolete. So I don't know how to help you!
Anything else, you can just google it because 9/10 there's a SO thread about it, and when there isn't, the documentation is usually good enough. GPT is not going to help you there.
But you can see it in the small things. For example if you ask an intelligent person "how do I install X on docker?" it will search google and then find a tutorial or some resource to reference. Then they will break it down and adapt it to your scenario.
GPT instead will give you... whatever it feels like giving you in that moment. It will not look on the f*n internet to make sure that what it says is correct and up to date. It does not update an internal knowledge base with factual information that it can then reference to produce a coherent plan. It has no concept of truth so it can't use logic.
You can throw as much compute and chain of thought as you want to the problem, it's the architecture itself that is disappointing.
I hope for an AI that can actually reason and doesn't bullshit its users though
>The design of the language in Dockerfile is ad hoc in a bad way. It’s difficult to understand, for me, and easy to make mistakes.
Because that reads like a skill issue to me
There's the machine. Then the VM. Then the container. Then the orchestrator. Then the controller. And it's all so complex that you need even more tools to generate the configuration files for the former tools.
I don't want to write a Kubernetes controller. I don't even know why it should exist.
Basically it's what current LLMs lack. They're good at spewing coherent text but they lack the building blocks of reason, which are made of logic, and which confer the quality of being consistent. A implies B.