I find when I'm in a domain I'm not an expert in I am way more productive with the AI tools. With no knowledge of Java or Spring I was able to have AI build out a server in like 10 minutes, when it would have taken me hours to figure out the docs and deployment etc. But like, if I knew Java and Spring I could have built that same thing in 10 minutes anyways. That's not nothing, but also not generalisable to all of software development, not even close. Plus you miss out on actually learning the thing.
Not at work, elsewhere
Extra productivity at work is not being used at fixing bugs as well.
It works. It's playable. I might put it online some-time when I get a chance.
[EDIT: My involvement apart from the code-skimming mentioned below was mostly play-testing after Claude had "play-tested", and giving it feedback on what to add or change]
My best estimate from having written much simpler games before was that it churned out many months worth of working code in days. I've not written a line of it - just skimmed some code and told it to make a few architectural refactors.
It's absolutely crazy.
The hard part is day to day operations for years with thousands of edge cases, actual human feedback and errors, knocking on 1000 doors etc.
Otherwise you're just doing slot machine coding on crack, where you work and work and work one some amazing thing then it goes nowhere - and now you haven't even learned anything because you didn't code so the sideproject isn't even education anymore.
What's the point of such a project?
No, I'm not interested in monetizing stuff, I make enough money from $dayjob.
> Having actual users, working through edge cases, browser quirks, race conditions, marketing, communication - the real battle testing 5% that's actually 95% of the work that in my view is impossible for the LLM?
Yes, all of those. Obviously an LLM won't make a tiktok ad for me, but it can help with all the other stuff. For example, you mentioned browser quirks. I ran into a bug in safari's OPFS implementation that an LLM was able to help me track down and work around. I also ran into the chrome issue where backdrop effects don't work if any of the element's parents have nonzero transparency, and claude helped me find all the cases where that happened and fix them. Both of these are from working on the app in my bio. It's a language app too, so however many edge cases you think there are, there's more :D
I don't want to give the impression that it was not a lot of work. It was an enormous amount of work. It's just that each step is significantly faster now.
> and now you haven't even learned anything because you didn't code so the sideproject isn't even education anymore.
I read every line. You could pull up the github right now and point to any line of code and I could tell you what it does and why it's there and what will break if you remove or change it.
> What's the point of such a project?
I originally made it because I wanted a tool to help me learn French. It has succeeded in helping my enormously, to the point where I can have short conversations with my french family members now. Others seem to find it useful too.
Yes, this is the central fallacy. The reality is, we've been massively bottlenecked on software productivity ever since the concept of software existed. Only a tiny tiny fraction of all the software that could usefully be written has been. The limitation has always been the pool of developers that could do the work and the friction in getting those people to be able to do it.
What it is confounded by however is the short term effect which I think is absolutely drying up the market for new junior software devs. It's going to take a while for this to work through.
I'm my opinion you are failing to consider other bottlenecks, a la the theory of constraints.
An analogy: Imagine you have a widget factory that requires 3 machines, executed in sequence, to produce one widget.
Now imagine one of those machines gets 2x-5x more efficient. What will you do? Buy more of the faster machines? Of course not! Maybe you'll scale up by buying more of the slower machines (which are now your bottleneck) so they can match the output of the faster one, but that's only if you can acquire the raw material inputs fast enough to make use of them, and also that you can sell the output fast enough to not end up with a massive unsold inventory.
Bringing this back to software engineering: there are other processes in the software development lifecycle besides writing code -- namely gathering requirements, testing with users (getting feedback), and deployment / operations. And human coordination across these processes is hard, and hard to scale with agents.
These other aspects are much harder to scale (for now, at least) with agents. This is the core reason why agentic development will lead to fewer developers -- because you just don't need as many developers to deliver the same amount of development velocity.
The same logic explains (at least in part) why US companies don't simply continue hiring more and more outsourced developers. At a certain point, more raw development velocity isn't helpful because you're limited by other constraints.
On the other hand, agentic development DOES mean a boon to solo developers, who can MUCH more easily scale just themselves. It's much easier to coordinate between the product team, the development team, the ops team, and the customer support team when all the teams are in the same person's head.
First thing I got was “browser not supported” on mobile. Then I visited the website on desktop and tested languages I’m fluent in and found immediate problems with all of them.
The voices in Portuguese are particular inexcusable, using the Portuguese flag with Brazilian voices; the accents are nothing alike and it’s not uncommon for speakers of one to have difficulty understanding the other in verbal communication.
The knowledge assessments were subpar and didn’t seem to do anything; the words it tested almost all started with “a” and several are just the masculine/feminine variants. Then, even after I confirmed I knew every word, it still showed me some of those in the learning process, including incredibly basic ones like “I”, or “the”.
The website is something, and I very much appreciate you appear to be trying to build a service which respects the user, but I wouldn’t in good conscience recommend it to anyone. It feels like you have a particular disdain for Duolingo-style apps (I don’t blame you!) but there is so much more out there to explore in language learning.
> First thing I got was “browser not supported” on mobile.
Yeah, I use some APIs that were only implemented in Safari on iOS 26. Kind of annoying but I use Android so I didn't realize until too late. I should fix it, but it's not a priority given the numerous other things that need improvement (as you noticed!)
> The voices in Portuguese are particular inexcusable, using the Portuguese flag with Brazilian voices; the accents are nothing alike and it’s not uncommon for native speakers of one to have difficulty understanding the other in verbal communication.
That's good feedback, thanks! I only added Portuguese this weekend (https://github.com/yaptown/yap/pull/73) so it's definitely still very alpha (as noted on the website :P )
> The knowledge assessments were subpar and didn’t seem to do anything; the words it tested almost all started with “a” and several are just the masculine/feminine variants.
Thanks, will fix this tonight. The placement test was just added last week (https://github.com/yaptown/yap/pull/72) so there are still some kinks to work out.
> Then, even after I confirmed I knew every word, it still showed me some of those in the learning process, including incredibly basic ones like “I”, or “the”.
Yeah, the logic doesn't really work for people who already know every word. It tries to show words in the following order (descending): probability_of_knowledge * ln(frequency). But if you already know every word, probability_of_knowledge is the same for every word and the ln(frequency) is the only one remaining, meaning you just get the most common words. I'll add a warning to the site for people who are too advanced for the app's dictionary size – as you pointed out, it's not a good UX.
> there is so much more out there to explore in language learning
There is! I usually recommend pimsleur to people. My hope is just for my app to be a useful supplement.
I think your logic goes wrong because you assume that more productivity implies less desire for engineers. But now engineers are maybe 2x or 5x more productive than before. So that makes them more attractive to hire than before. It's not like there was some fixed pool of work to be done and you just had to hire enough to exhaust the pool. It's like if new pickaxes were invented that let your gold miners dig 5x more gold. You'd see an explosion in gold miners, not a reduction. For another example, I spend all my free time coding now because I can do so much now. I get so much more result for the same effort, that it makes sense to put more effort in.