I was vibe coding a prototype some nights ago. In between, I ran out of my AI budget.

I felt stuck. I didn’t know what the AI had done so far or how to continue. There was nobody to message for a budget increase (it was night).

Luckily I managed to get more budget.

But that left me scared for the future. One day something is gonna fail, and nobody can do anything because the AI providers are also down. Or what if I can no longer afford paying for the frontier?

I have made some modifications to my vibe coding practices since then. I don’t want to live in this future that the author describes.

If it's any consolation, I stay on top of all changes, but when the AI API stops I feel just as stuck.

I understand what I made, the speed just drops to 0.1%. So I just start studying the codebase, planning work for later, ordering thoughts by writing DESIGN.md, adding jobs to the kanban.

It scares me that I don't own the LLM though, but someday I will, it will be local and I'll feel better when I own my means of production again.

Become your own AI provider? At least until Anthropic et al manage to get local AI declared illegal. :)

that's why local AI is so important, and open-weight models

Even in the best case scenario, normies wouldn’t want to build everything themselves.

Aside: When did you start studying for nursing? And have you written about your experience so far?

What would they be building .. just tell Ai create and publish a website for my personal thoughts, solo business, mid-size business, etc and call it something like name124.com. Then boom it's done and live on the internet for them to feed content to it via a personal agent like Muse. If humans are getting paid to publish their thoughts/content on the web for Ai to stay relevant and it's super easy Im bet millions would love to be feeding Ai.

Thank you it's on-going and going well. Ai (chatGPT plus) is helping me learn as I feed it my class notes and notes in general. I then have it create multiple choice quizzes I take via voice while driving or when not driving clicking/choosing the answer. I will write more once I further progress as I started school in mid August.

Good luck!

I work as a professional app developer. And I find this take to be naive.

Most of the time when I review code from AI, there is always something to improve.

It’s either a maintenance issue. e.g., Opus recommended and implemented a fix for a database corruption crash. This was ~400 lines of code with many moving parts. I reviewed, and found out Android Room library already handles this recovery case, and all I needed was a 10 liner PR that catches this exception and ignores it.

The maintenance is not only the burden on the human and LLM. With too many moving parts, it becomes harder and harder to build and verify the correctness of future features. Yes you can write test for this and that, but it didn’t need to exist in the first place.

The second problem is correctness issues. Especially the edge cases. You cannot just manually test out a race condition on a phone! Sometimes it happens! Sometimes it doesn’t! If it leads to a visible signal like a crash, then yes, you can try to reproduce it. But there are a lot of these that are “silent” and would just lead to bad experiences.

We already had a software quality crisis! And I think such views only exacerbate the situation! Quality matters!

And this is not an anti-AI stance. I vibe code personal projects where I don’t even look at the code. But when I use AI as a professional engineer, I act like a professional. Because these products do have an impact on people’s lives.

All true (and thanks for posting a concrete example rather than "LLMS suck"). But my take is that none of this is much different than before times when I had teams of developers creating applications. They would often make similar mistakes which I would either need to catch or which would flush out in the field. Where it seems that LLMs are not excellent is where the person driving it is also the senior domain expert so can immediately spot pitfalls. But typically using humans to develop software this was really not often the case. Those people get promoted so they're no longer cutting the code. Under that scenario (replacing subordinate humans) I find the current models are either on-par or somewhat better (specifically because the models can also act like a peer senior dev, discussing approach options etc).

I agree with you! And I’m not trying to romanticize the past! Humans/me wrote slop too.

I think we are over-indexing on speed of delivery. I think this is a mistake. The alpha is in speed and quality.

Currently, my experience is that human + AI can write software faster and with better quality than either party can do alone.

No where did I say we don’t do agentic dev!

Years of experience doesn’t mean much! I will challenge you on ideas. And the idea you are sharing is dangerous and unprofessional.

Especially at scale. e.g., we process more than 3.5 billion orders annually! This is serious business. Edge cases are common.

> It’s either a maintenance issue. e.g., Opus recommended and implemented a fix for a database corruption crash. This was ~400 lines of code with many moving parts. I reviewed, and found out Android Room library already handles this recovery case, and all I needed was a 10 liner PR that catches this exception and ignores it.

I understand this, but I just can't bring myself to care. I've been doing professional software work for almost two decades. These sorts of improvements/time savers are great without AI. With AI? Whatever. It's fine.

When the underlying lib has an issue, it'll be quicker to debug with the whole thing in context.

So exactly what value are you adding, then?

I take the specifications from the customer and type them into the AI

Well then I just have to ask why can't the customers type them directly into the AI?

One hopes you are better at that than the many others who are doing the same.

I have people skills; I am good at dealing with people.

Funny that none of the commenters got the reference/joke

You do realize that letting the LLM produce more output means that maintenance will be more expensive? I can easily see a world where claude and gpt are producing more tokens to sell you more tokens.

Just the other day I burned through my 5h quota twice in a row because I had opus spawn a review session on a medium sized PR and I don't know what happened but I told it to summarize to me and it said it spent 100M tokens throughout 50 subagent sessions.

And more recently its been recommending that i install this new browser called Aside. I did, and it almost felt like I was installing malware so I Uninstalled it fairly quickly (it also was not a great browser)

I feel like theres collusion somewhere.

Well yeah, that's the name of the game of most software companies. Anthropic has been fairly good up until the last week or so when it started needing more hand holding to not do things it didn't normally do.

This is not as obvious as many naively believe.

It depends on how hard to maintain the code added is, how likely it needs to change in the future, and most importantly on the cost.

If reviewing and manually improving the code takes hours, the cost may already be in the thousands.

That buys you a lot of AI usage, roughly a few months of continuous work.

You have to balance this with the chance that the suboptimal code the AI generated is actually fine and maintainable enough, and also the chance that during further work on that code a model might implement the same optimization on its own.

The models will only get better and inference cost will go down.

I don’t see any reason to think the same thing that happens with all tech won’t happen here.

That's just a straight shooter with upper management written all over him

Enshittification and profit maximalization is around the corner looking for you.