I am a huge advocate of this kind of app paradigm:
It’s now really easy to spin a terminal emulator and make cross platform terminal apps that work the same on Windows, macOS and Linux regardless of users terminal. You can also make sure the term sends everything required to make the app “nice”, like mouse hover events.
I started using this paradigm for some of my own company’s apps around 3 months ago because it was neat to allow the app to spawn DWM windows for sub windows, dialogs etc. but the app can also fall back to standard TTY for using over SSH or from within a docker or any other terminal. Also, using your own terminal window gives proper taskbar integration (stacking windows) and you can set your own app name/icon.
(It’s possible to 1-shot this in Python using the prompt “use ghostling as a reference, write a terminal emulator in Python using raylib and libghostty that hosts my app” and the first pass was around half the speed of Ghostty.)
I disagree. First we got everything as HTML/Electron apps, now the trend is everything as TUIs. Cross-platform, better, but still worse somehow.
What falls to the wayside are the actual and real productivity and usability improvements afforded by "real" GUI apps over the last 40-50 years.
Don't get me wrong I'm a huge terminal user and absolutely love the clarity of a terminal and flexibility of a shell. But if I have to "learn" to use a TUI app - and they're not as simple to use as their authors might believe - I might as well learn to use the full GUI app with all the niceties available because of it.
Depends on what you're selling. If you do it right, Google will give you plenty of organic customers who want to buy your product - no ads needed. You can market as much as you want on Meta also without having to pay for ads.
But if you need stronger marketing than that, there will always be willing affiliates.
SEO is not nearly as effective as it used to be. Organic click through rates have been trending way down since AI responses were added to the top of the search results. So this really isn't just a case of "you're holding it wrong".
If you're selling something, you love having the AI talking about your product. The move to AI is not a negative for businesses wanting to reach customers organically - on the contrary.
In CRC8 you interpret the input as coefficients of a polynomial, and take mod `x⁸ + x² + x + 1`.
The problem we solve here is a bit different: You know the coefficients in advance, and want to preprocess the polynomial to make it fast to evaluate.
However, in section "5.9 Injective Polynomial Hashing" we actually study the problem of universal hashing, which is a lot more like CRC8.
I find Astra to be weirdly stupid in the sense you have to force it to spend time on something (fix this architectural issue and refactor), then it’s stupidly smart.
It prioritises getting something working over making something good during the 1-shot phase and outputs maximum slop.
Would be good to include Fable and Opus. Based on the results with Astra vs GLM (not even in the same ballpark), these are probably the realistic alternatives to consider.
Yes, I'd be really interested to see Fable / Opus / Sonnet.
GLM 5.3 Flash Max had an interesting showing. Its Codex version was bad [0], and it completed in 9 minutes. The OpenCode version was much richer [1] and more detailed, completed in 20 minutes. And the OMP version was arguably the most complete [2], completing in 30 minutes.
This is probably the strongest argument for the effect of a harness, and I'd be interested to learn the differences in the prompts and tools between these three.
reply