898 karma · joined January 13, 2022
That's the real risk here is that we are getting to the point (probably already there for a lot of stuff) where you can just point it to your already existing codebase and tell it your problem and it can basically do it.. I mean I've tested that in practice, sometimes I'll have a clear direction of where I want to go or what I would do.. but I don't really give it any hints of how to solve the problem, and many times it comes up with a similar result or at least one that also works completely fine.
So I think part of the issue is that people like you and me I feel like are going to be so much less needed because an AI can just do it instantly for basically free.
Anyway, I know this is a slight hyperbole.. but it's also not. It kind of sucks to realize that a simple prompt can replicate your work 95% of the time and do it basically instantly.
That doesn't work in a society with such extreme wealth inequality.
I review things that I know are "important".. but I've learned that there are many things that I don't care how it works at this point- they aren't critical in terms of I know it's not going to cascade and break other things (that's where us senior engineers know what to look for).
But there's no way in the hell I can review all the code that is being generated for so many things that just don't need reviewing. They work- that's honestly good enough for a lot of use cases. I review the code that touches sensitive areas and I know aren't very straightforward (which, I would put at only 10%).
Seems obvious why an API would be helpful on that page instead of having the AI attempt to navigate the page, open up a date picker and click all around..
And as others have said, if you are disabled in some way being able to just speak and get something like this done seems pretty life changing.
But you go ahead and be mad about an api...
If I use two LLM's to create some chunk of code and they both do it slightly differently but they both compile and pass appropriate tests.. it honestly doesn't matter if the LLM itself is not deterministic in exactly what it's going to output.
I would also argue- doesn't that make sense? You give two human coders the same task and they are also going to come up with slightly different results.
All I'm saying is it should have been a problem at that point.. not just because it's easy now to do it at a high scale.
I honestly think people on here are very much overstating 'spaghetti code' when AI does it... first, it works correct? The reason I say that if the AI can continue to upgrade code that might not always look 'the prettiest' (to you..) because it doesn't care about what some of us consider to look like clean code. If it can continue to manage, document, and upgrade the code successfully.. does you calling it spaghetti code actually matter? Maybe you have a hard time reading it but the AI certainly doesn't.. I think that's worth consideration.
Every one of us has our own conventions and ideas of what 'clean' code looks like sometimes. And honestly 95% of the time we only thing it's clean if we wrote it ourselves.
Downvoting you isn't enough. How about we stop trying to take advantage of people and extra every dollar from them in every possible way?
Building a gaming PC right now is no longer affordable. I can't even upgrade my hard drives because they have tripled in price. And it's all because of good old capitalism.
That sounds like a you issue.. it's wonderful on the terminal. It's their GUI which needs work (they have been improving, but still not a fan).
I've been using it on multiple computers for months and it's generally rock solid and lovely.
If you sat down and did the math on what it costs someone to pay rent / mortgage, car insurance, health insurance, daycare, schooling, going out to eat and drink, doing anything for entertainment, go to the grocery store.. it's not a debate that the real inflation is significantly higher all the time than what is used to measure the number.
Now I have no need for anyone from a coding perspective.. I can keep up with multiple clients requests with a breeze. I don't have to manage anyone. I type of my phone while I'm on a walk and work gets done for me.
So yeah... it's not good.
That's because AI wrote it to deter other AI from taking it's job
If you already have a mature code base, then it's very easy to get AI to write excellent code. It has a ton of documentation on what you already do, how you do things, functions to use etc.
I read all the changes AI does. I work in small chunks.
>Even if you have an architecture in mind, and even if the agent follows it, sooner or later it will need to be reconsidered
The agent can modify the structure you want to change to 100x faster than you can. That's the beauty of it. We all know how hard it is manually to make architectural changes once you've started to lock into something.
These comments just show me you must not be using AI in the right way, or haven't used it enough to learn "how" to use it. I've been using claude code months now at full speed. You are simply wrong that it doesn't generate good code.
There is a clear MONOPOLY on phones and to even further take away the right to just install something on it is crazy. I already hate Apple for that, but there's no recourse in the monopolistic & capitalistic US and now it's going to be 100% gone.
"it should be fine for Google or Apple to do whatever they want with their OS"
Not when they are a MONOPOLY.
I cannot stand how you and people like you try to justify everything by supply and demand. Also you act like it's some natural law of nature. It's not a law of nature- if you took an economics class you would realize it's try to maximize PROFIT. It's not for the good of the people.
All of these things are a CHOICE that people are making to now completely screw the average person for, again, the needs of big corporations and the top 0.01%.
You sound like you are single no kids and on here with a cushy tech job and be like "those poor people just don't know how to manage their money!"