- Durable, 'enterprise grade' software patterns are baked into the runtime and into common, stable libraries that everyone uses
- You can use Ash, which pretty much entirely solves architectural considerations for many types of backends
- The tooling for inspecting and enforcing style (tidewave, credo, dialyzer, Dan's "vibe" ecosystem tools) is far beyond what I see in other ecosystems
- Ecosystem coverage for pretty much everything you need, including numerical software
- Excellent performance escape hatches (NIFs)
And, as has been shown in various benchmarks, agents are quite good at it.
My one problem in practice has been that getting tests right is hard. LLMs need a lot of cajoling to not build flaky tests with all the concurrency, and I find myself spending hours rewriting parts of the test suite once or twice a week.
I have no professional experience in Rust and over 10 years in c++ but to me the decision to use rust in a greenfield project written by agents was obvious.
Do the forms etched into stone by weather over millennia in Moab matter to the wind? Certainly yes, in one sense, but not in the same sense we mean when we say things matter to us, or to animals, or even bacteria.
I think it's just hard to know this for the people working on it. AI radically changed my life. I'm doing at least 10 times more, more ambitious, higher quality work. I've been listening to people around me talking about alignment and the singularity for almost a decade. It's strange to imagine that people live in a world where this isn't and hasn't been happening for a while now. "Over-hyped" is not the word I would use if I take my daily experience as an example, nor when I consider even lower-bound projections.
Not optimizing for that. I derive "10x" more satisfaction, because I'm able to work on more ambitious problems. I'm probably making less money than I would otherwise.
It's actually not a bad comparison. You might feel like you're getting 10x more done with AI but it's going to be 10x more buggy and/or 10x missing the edge cases, in the way AI usually misses the mark. I don't do coke, but I know plenty of people who do, and I would not trust them with anything important.
Not publicly yet, but I work on a programming language, compiler, and runtime that achieves magical (to me) things in a niche field. I would never have attempted something at this scale otherwise, so it's a very 0-to-1 experience subjectively.
That matches my experience. At least on the solo front, there were so many topics I wasn't an expert on, that limited what I could build. Now with AI assistance, the sky is the limit. I don't need to be an expert in frontend, backend, I can just build on my personal expertise in a functional domain, and leverage AI to fill in the gaps. I believe many people will benefit from being to build exactly what they want, without gatekeepers or investment.
I work on self-directed projects that don't make any money, currently. My "day job" (not software development) does not have this '10x' quality, though I imagine it could were I allocating my efforts that way.
I've yet to come across something with vim bindings that lacks a .vimrc where you can map 'jk'. Either way, switching back to ESC is as annoying as it is in the first place.
I did an exhaustive comparison of window managers and settled on using Raycast for simple resizing (full screen, center, mid-size centered, 1/2, 1/3, 2/3 left/right) + FlashSpace[1], which implements simple virtual spaces with instant switching.
You can also use Rectangle or Spectacle or others in place of Raycast.
+1 for FlashSpace. I used to be an i3 user and MacOS workspace management drove me mad. For years we had TotalSpaces, but that is no longer being maintained. With FlashSpace I finally have a great setup.
My solution has been binding a key Hyper+[a-z] for my applications. When used in conjuction with FlashSpace I get a usable setup. I also heavily rely on native MacOS binding Cmd+` (backtick) to cycle the currently focused application, and mission control for the current workspace.
Let me know if this is interesting; I've been considering creating a YouTube-video about this setup.
According to the meter, I used $15k in tokens with my Max plan (along with $5k of Codex tokens) in the last 30 days. That built an entire working and (lightly) optimized language, parser, compiler, runtime toolchain among other things.
If you're running the 4k display at 1440p, I'd agreed. But I run two 4k 60hz displays on a 16" MacBook Pro work laptop at 2880x1440 effective resolution and it looks fine to me. Yes, it doesn't look as good as the Studio Display I have on my personal Mac. But even though I have the MacBook Pro screen right next to the 27" monitors, I just don't notice the difference as I switch between them all day long.
I'm not saying there is no difference. But I suspect how one reacts to it is highly dependent on the person. I wear glasses that aren't perfectly focused for either screen, but they're good enough to get the job done - and mostly importantly, I get to use my two 4k 27" monitors to give me the same effective resolution as a Studio Display at far less money than two Studio Displays.
Ah, thanks so much for this question. I ended up building a tool that agent can use to track 'compounding' in my corpus of .markdown files. Keep iterating and thinking about it, and you may find you can do the same for your process.
reply