Yeah! I have two typewriters!

We're monkeys with COMPUTERS!!!

idk ive seen some crazy complicated stuff woven together by people who cant code. I've got a friend who has no job and is trying to make a living off coding while, for 15+ years being totally unable to learn coding. Some of the things they make are surprisingly complex. Tho also, and the person mentioned here may do similarly, they don't ONLY use ai. They use Github alot too. They make nearly nothing themself, but go thru github and basically combine large chunks of code others have made with ai generated code. Somehow they do it well enough to have done things with servers, cryptocurrency, etc... all the while not knowing any coding language.

Claude code can make something that works, but it's kinda over engineered and really struggles to make an elegant solution that maximises code reuse - it's the opposite of DRY.

I'm doing a personal project at the moment and used it for a few days, made good progress but it got to the point where it was just a spaghetti mess of jumbled code, and I deleted it and went back to implementing each component one at a time and then wiring them together manually.

My current workflow is basically never let them work on more than one file at a time, and build the app one component at a time, starting at the ground level and then working in, so for example:

Create base classes that things will extend, Then create an example data model class, iterate on that architecture A LOT until it's really elegant.

Then Ive been getting it to write me a generator - not the actual code for models,

Then (level 3) we start with be UI.layer, so now we make a UI kit the app will use and reuse for different components

Then we make a UI component that will be used in a screen. I'm using flutter as an example so It would be a stateless component

We now write tests for the component

Now we do a screen, and I import each of the components.

It's still very manual, but it's getting better. You are still going to need a human cider, I think forever, but there are two big problems that aren't being addressed because people are just putting their head in the sand and saying nah can't do it, or the clown op in the post who thinks they can do it.

1. Because dogs be clownin, the public perception of programming as a career will be devalued "I'll just make it myself!" Or like my rich engineer uncle said to me when I was doing websites professionally - a 13 year old can just make a website, why would I pay you so much to do it. THAT FUCKING SUCKS. But a similar attitude has existed from people "I'll just hire Indians". This is bullshit, but perception is important and it's going to require you to justify yourself for a lot more work.

2. And this is the flip side good news. These skills you have developed - it's is going to be SO MUCH FUCKING HARDER TO LEARN THEM. When you can just say "hey generate me an app that manages customers and follow ups" and something gets spat out, you aren't going to investigate the grind required to work out basic shit. People will simply not get to the same level they are now.

That logic about how to scaffold and architect an app in a sensible way - USING AI TOOLS - is actually the new skillset. You need to know how to build the app, and then how to efficiently and effectively use the new tools to actually construct it. Then you need to be able to do code review for each change.

Mmmmmm no, Claude definitely is. You have to know what to ask it, but I generated and entire deadman’s switch daemon written in go in like an hour with it, to see if I could.

It is in everyone’s interest to gradually adjust to the notion that technology can now perform tasks once thought to require years of specialized education and experience.

The years of specialized education and experience is not for writing code in and of itself. Anyone with an internet connection can learn to do that in not that long. What takes years to perfect is writing reliable, optimized, secure code, communicating and working efficiently with others, writing code that can be maintained by others long after you leave, knowing the theories behind why code written in a certain way works better than code written in some other way, and knowing the qualitative and quantitative measures to even be able to assess whether one piece of code is "better" than the other. Source: Self-learned programming, started building stuff on my own, and then went through an actual computer science program. You miss so much nuance and underlying theory when you self-learn, which directly translates bad code that's a nightmare to maintain.

Finally, the most important thing you can do with the person that has years of specialized education and experience is you can actually have a conversation with them about their code, ask them to explain in detail how it works and the process they used to write it. Then you can ask them followup questions and request further clarification. Trying to get AI to explain itself is a complete shitshow, and while humans do have a propensity to make shit up to cover their own/their coworkers' asses, AI does that even when it make no sense not to tell the truth because it doesn't really know what "the truth" is and why other people would want it.

Will AI eventually catch up? Almost certainly, but we're nowhere close to that right now. Currently it's less like an actual professional developer and more like someone who knows just enough to copy paste snippets from Stack Overflow and hack them together into a program that manages to compile.

I think the biggest takeaway with AI programming is not that it can suddenly do just as well as someone with years of specialized education and experience, but that we're going to get a lot more shitty software that look professional on the surface, but is a dumpster fire inside.

This industry also spends most of it's money either changing things that don't need to change (we optimized the right click menu to remove this item, mostly to fuck your muscle memory) or to avoid changing things (rather than implementing 2fa, banks have implemented 58372658 distinct algorithms for detecting things that might be fraud).

If you're just talking about enabling small scale innovation you're probably right, but if you're talking about the industry as a whole I think you need to look at what people in industry are actually spending their time on.

it's not code.

Nobody knows. Literally nobody, including him, because he doesn't understand the code!

AI writes shitty code that's full of security holes, and Leo here has probably taken zero steps to further secure his code. He broadcasts his AI written software and its open season for hackers.

Potentially both, but you don't really have to ask to be hacked. Just put something into the public internet and automated scanning tools will start checking your service for popular vulnerabilities.