zlacker

>>meetpa+(OP)
It is baffling how these AI companies, with billions of dollars, cannot build native applications, even with the help of AI. From a UI perspective, these are mostly just chat apps, which are not particularly difficult to code from scratch. Before the usual excuses come about how it is impossible to build a custom UI, consider software that is orders of magnitude more complex, such as raddbg, 10x, Superluminal, Blender, Godot, Unity, and UE5, or any video game with a UI. On top of that, programs like Claude Cowork or Codex should, by design, integrate as deeply with the OS as possible. This requires calling native APIs (e.g., Win32), which is not feasible from Electron.

>>Olympi+EJ
My main take is exactly the opposite. Why not build everything with a simple text interface (shell command) so the models learn to use these tools natively in pretraining. Even TUI like codex-cli or claude code are needless abstractions for such use cases and make full automation hard. You could add as many observability or input layers for humans as you want but the core should be simple calls that are saved in historical and documentation logs. [the headless/noninteractive modes come close, as do the session logs]

>>pama+TP
TUI is easy to train on, but hard to use for users. Part of the reason it’s easier to have LLMs use a bunch of Unix tools for us is that their text interface is tedious and hard to remember. If you’re a top 5% expert in those tools it doesn’t matter as much I guess but most people aren’t.

Even a full-featured TUI like Claude Code is highly limited compared to a visual UI. Conversation branching, selectively applying edits, flipping between files, all are things visual UI does fine that are extremely tedious in TUI.

Overall it comes down to the fact that people have to use TUI and that’s more important than it being easy to train, and there’s a reason we use websites and not terminals for rich applications these days.

>>markba+Wh1
I use headless mode (-p) and keep my named shell histories as journals (so no curses/TUI or GUI). But session management or branching could improve at the tool level and allow seamless integration with completion tools, which could be a simple fast AI looking at recent sessions or even be visual, say for navigating and extending a particular complex branch of a past session. It is not too hard to work with such shell-based flows within Emacs for me, but it would be nice if there was some standardization effort on the tool fronts and some additional care for future automation. I dont want my AI clicking buttons if it can be precise instead. And I certainly want multithreading. I think of AI more as an OS; it needs a shell more than it needs windows at this point in time.