So the keynote mentions that in a perspective you are going to be a "maker of things" rather than a coder. But, nobody is asking, in a perspective, why would anybody use the stuff you "make" rather than using AI directly? All of the notion of apps disappears, in a perspective.
Do you change the oil on your car yourself? No? Why not? Buying the oil, filters and all the tools you need to do it forever would cost less than one oil change at the dealership. Plenty of videos on YouTube you can learn from.
Sure, but changing the oil means buying a bunch of stuff and getting dirty. Replacing your vibe coded garbage app with my vibe coded garbage app is much much easier than changing my oil.
That said, I think this only applies to apps that can be replaced by vibe coded garbage. Anything with a network effect, or anything that requires deep domain knowledge is much safer
> Replacing your vibe coded garbage app with my vibe coded garbage app is much much easier than changing my oil
I am not sure what is it about the HN crowd that makes them so out of touch with what the average Joe is capable of. It's like that Dropbox post top comment all over again.
Don't you think that the only reason you think it's simple is because you're... A professional Software Engineer??
I know for a fact that it has gotten simpler. Which means that the number of people who can do a version of the thing i’ve been doing most of my life got way way way bigger in the last couple years.
Sure, not everybody can do it - i take your point. But the dynamic between can and can’t has changed. Projects I wouldn’t take on because they were too much work for not enough reward have become something I can pop off in a couple hours. People who know nothing about coding but a lot about their specific need can build complex apps in days.
> Which means that the number of people who can do a version of the thing i’ve been doing most of my life got way way way bigger in the last couple years.
Which invariably means that businesses who incorrectly believe that their vibe coded solution will withstand the trials and tribulations of production will be needing even more professional help when it all goes wrong.
Yes people shouldn't discuss until they have tried vibe coding as SaaS. I do this now and it is 10x faster at coding and 1x on any other tasks. So overall maybe 3 months work is done in a month. This means the typical SaaS may be cheaper now but it is not like anyone can vibe code it cheaper than the subscription fee.
> Buying the oil, filters and all the tools you need to do it forever would cost less than one oil change at the dealership.
Are you changing your own oil? The cost of oil alone usually ends up being around 3 DIY changes vs one at the dealer ship. The mobile 1 synthetic I like is currently $92 for a 3-pack of 5qt containers. Which is enough for 3 oil changes with some left over to almost do a 4th. Dealership currently wants $84+tax for change w/free tire rotation. It's cheaper but certainly not "do it forever", and living in an apartment often means risking getting a warning from the landlord for doing auto maintenance in the parking lot since its against the stated rules in the lease.
Drain plug is in a stupid location that I don't often feel like dealing with. I do change the oil myself in all my other machines with much more pleasant for oil change designs, though. So I guess what you are saying is that AI isn't ergonomic enough yet, but will that hold true much longer?
I have been thinking quite a bit about this lately. I am in the process of building my own music software applications. This is actually allowing me to leave MacOS since Ableton was previously the anchor for me. I can now build tools that are more geared towards what I always wanted in Rust much like DHH was talking about in that talk.
I could sell some of my tools I built but I am on the fence about it. As a few others have said, there is still work and taste that goes into those tools that some might not want to put the effort into. However, there will be an increasing number of people who just build bespoke tools for themselves. That's probably ok. There's a market for both.
The most important thing now (and maybe always) is distribution. If anyone can build something then it ultimately comes down to your ability to market, build trust and provide support at 2:30 AM. That's hard to do when you're a one person shop. Software is an ongoing operational commitment if you make it your business.
Because it does take some skills, judgement, taste, knowledge, time and effort to build things. He said it is not very different from directing a team of contractors, and also said that a 10x dev in now 1000x with a tool like this. He also gave the parallel of photography to address this point, that people were forced to be more creative and adapt.
But I assume you didn't use to build anything substantial.
Business people I work with tend to have all kind of ideas in different places, I cannot count all the Trello boards they have abandoned. Users are usually lazy and don't want to fill in data properly, well yeah chatbox with llm is cool interface, but you still have to enforce structure for data so it is useful.
With AI problem is still there "garbage in, garbage out", models are not going to imagine correct data to fill in blanks, in the end if you need someones birthday, someone has to type it in.
Web app I am working on is organised only because we get engineers and quality assurance and we get paid for maintaining application. Data is structured and we can deliver insights because the application enforces structure.
There are far more requirements than AI can deliver on its own.
At least at the current level of AI, it still takes days/weeks/months to make a good app if you have standards. That's not effort everyone will want to do.
If/when agents become reliable enough, there will be no need for web apps, nor phone apps, etc. In fact, DHH got that part right: "your app should have a CLI if you want me to use it." If "English is the best programming language", then English is the best UX. I'm not navigating a silly page and filling out forms and dismissing popups if my agent can book a flight for me with a sentence and a bit of textual back and forth.
I wonder if the web will go away and the Internet will be just bot to bot traffic.
Navigating the web seems archaic in that context. Not only is that the end of Rails, but of frontend, JavaScript, etc. in the long term.
Because it is impossible to change its color. It was/is not uncommon to see custom/dark skinned Windows apps with ugly gray scrollbars looking at you. Even today, only Light and Dark themes are supported, impossible to set a custom color.
"... Custom Draw, the feature found with many of the common controls shipped with Windows. Custom Draw allows an application to completely take over the drawing of a window’s scrollbars, and replace the scrollbar graphics with a completely user defined look."
I believe it would be helpful for those who would want to continue development, contribute to the project.
Pro-AI people now argue that the code is ephemeral nowadays, we should not look at it like we don't look at generated assembly (most of the devs). So in this regard, sharing only the "assembly" doesn't make sense, it's like sharing only the binaries and calling that open source (before LLM days).
I expect a real big-gish project would have possibly hundreds or thousands of such sessions. And personally I've never needed to dig back an old session for reference, only when I'm still actively working on the topic. They don't have a particular structure, whereas the actual code has a lot of structure.
But maybe it would be useful to have the related chats in the actual git commits that introduce the features. This way, if you (or the agent) `git bisect`s an issue, the same context that was used to construct the feature could be used for making the fix as well. I have never tried this approach, but it sounds like it could be useful.
It's slightly annoying that most (all?) harnesses store the chat logs in a db outside the project, and additionally e.g. OpenCode doesn't give the agent a direct way to access the complete current session context. So implementing this currently would be a bit hacky (find session by time? generate random string in context and find the session?).
They mention OpenGL for the bigger targets, but I was wondering how this worked for the ESP32. Turns out they wrote a custom 2D rasterizer specifically for this target, basically a miniature version of a browser layout engine: https://geastack.com/blog-we-taught-a-chip-to-run-css
Each platform has its native bindings. For graphics, you write CSS and HTML canvas API as well as JSX, it renders to native components and their alignments, the canvas API is converted to native surfaces, whatever the platform uses.
It defers to platform defaults, Android compositor, UIKit/AppKit native views or CoreGraphics for the canvas on Apple platforms, GDI/GDI+ on Windows, whatever SDL2 chooses on Linux. If you have a Three.js app, it uses Metal on iOS and macOS, Direct3D 11 (open) and 12 (commercial license) on Windows and XBox.
It's not clear at first glance, but given (1) the apps are written in JavaScript (2) the project has repos for different OS native bindings, my bet is some kind of embedded JavaScript engine that just calls through to OS native widets
If you are product-driven why not go into Product Ownership roles? It certainly will be more satisfying compared to prompt "engineering" clerk "career".
Well, my life is currently both, as I am on the smallest possible tech and product team. To me, extrapolating on having done this since Sonnet 3.5 to now, there will be no tech aspect to the job soon enough. There are many hundreds of billions invested in making that a reality, and they are succeeding.
Until ~9 months ago, I spent most of my time being a "prompt engineer." Today I join a meeting, ten minutes later I receive the transcript. Then, I run a custom skill in my project, and I get Jira epics and stories to triage that are nearly perfect. Then, I run the second skill orchestration skill... some babysitting... and ~85% of the time that is all I need to do. Docs, code, unit and e2e, great UX... all there after every meeting, and basically two commands on my part.
I see two to three to maybe five years before anything I have to offer, in any capacity, is completely cut out of the picture.
I honestly don't understand how everyone is not on this same page. The labs are going to eat it all. The only reason I see for them to talk about "pausing," is because they finally realized that they are going to collapse the entire service economy around themselves at this rate: aka, the USA.
Yeah it’s going to be very rough for any knowledge worker unless the governments decide it isn’t ok for the general public to be allowed to use the tech.
It’s actually rough today with astra and fable, it’s just not been diffused enough. Tech workers like us see the writing on the wall, but a lot of others are blissfully ignorant.
It’s 10 devs with a small ai budget each vs 1 ex-dev now PM with a large ai budget - the choice is quite obvious for any decision maker who counts time and money
But assuming that one ex-dev with a large AI budget is highly profitable, why wouldn’t you convert the other 9 and give large ai budgets as well?
I guess if the company has no opportunities for growth so they only need exactly as much output as one team? But that sounds like a company that’s doomed anyway, regardless of ai.
You need to grow customers or contracts by 10x to fill the new pipeline and that's an impedance mismatch. Easier to let 9 go and hire later, especially since everyone else will be doing the same thing and there'll be a rather large pool of talent.
How you identify talent in this new world is a different kind of a problem which I don't think people figured out still and won't for quite a while.
If an org suddenly has 10x the production capacity for the same price and can’t figure out how to sell it profitably, it is mismanaged and will die. That’s very much the case for a lot of businesses for sure, but there have been filters before (the internet, for instance) and we survived.
I honestly don’t understand comments like this because in my work, this would be a disaster. And before I get the comments about my harness/skills etc, I’ve tried many tools and harnesses and skills and all that earnestly and in good faith. I find use in it for doing the grunt typing labor, but letting it loose in ways described above have only ended in spending much more time cleaning it up than if I just did the work myself.
I hate to sound pretentious, but I wonder if it’s a difference in complexity of work and problems being solved.
I just reviewed this thread, and thanks for an opening to say something I had realized I missed.
> I hate to sound pretentious, but I wonder if it’s a difference in complexity of work and problems being solved.
It is about complexity, at least for me. I am working on b2b SaaS.
There are times where even using LLM assistance, I spend weeks or months working on a tough problem.
However, the <show product get feedback> loop is now nearly entire automated, when it does not involve some actually complex problem, which are most of the meetings.
I code by hand (sigh) and copy paste some snippets once in a while from a web chat LLM. This also means every single line of such snippets gets reviewed and anaylzed. Usually, these are some arcane Win32 API usage where otherwise I'd have to dig into old forums. I don't want to become a prompt engineer so I stay away from "agentic" workflows.
As an engineer, the enjoyment from the process is not less important, or should I say more important, than the enjoyment from shipping a final product.
That's probably the single thing that I found to be biggest difference between those who are very pro AI vs. those more reserved or negative.
A colleague has openly stated that he very much does not care for the process, he just want the product. Where I only care about the product in the sense that I have to, because it's my job and for hobbies I pretty much only care about the process. So an LLM pretty much doesn't make sense, because it help by removing the part I care about. They are good tools for debugging and if you're hopelessly stuck on a detail of some weird and obscure API or configuration.
As an engineer, I know what I'm getting paid to deliver is the work product. I don't have too much attachment to any particular set of tools to get there.
If we follow that logic, I believe it means that you would be quite happy in the Product Owner role, or in the role of a client who outsources the actual development activities. I wouldn't.
reply