[jumploops]

It's not that I'm unimpressed by the results, it's that I think I'm saving time by pushing the agent along remotely, but the reality is that my messages to the agent(s) end up being a lot shorter, which inevitably leaves more up for interpretation.

Don't get me wrong, I still use Codex (and sometimes Claude Code) remotely every day, and am overall excited for this release, it's just that the benefit wasn't as high as I had initially hoped.

Part of this is due to the models getting better (no need to prod along with "continue"), and part of this is the nature of how I use my phone (short bursts of attention).

But again, maybe I'm just old and prefer big screens with a keyboard.

[satvikpendem]

Just...write longer messages. Maybe it is age but I've written huge forum such as on HN all from my phone often with multiple tabs open to source various links for foot notes. When I type for an LLM, I will type a lot too if needed and will often even type a little, wait to think, then continue, over the course of like 15 minutes even, so that the intention of the prompt is correct since that saves much more time and produces better results than shorter messages.

I think you just need to type more rather than feeling constricted, as it's actually a form of liberation, to produce (or have an AI produce, whatever) something from wherever you are rather than needing to sit down on a laptop where you're gonna be waiting around anyway.

What tunnel setup do you use by the way? I'm on Android so it's kind of annoying all the LLM remote coding apps are iOS only.

[jumploops]

Oh, I agree completely. I avoid loose language, revise my wording, and usually write prompts that require scrolling on mobile.

It isn’t so much that I feel restricted, I guess it’s that mobile wasn’t as big of a game changer as it was ~6 months ago.

My bandwidth feels more restricted by my own cognitive capacity (usually due to do context switching), rather than the limits of the model itself, and the mobile interface makes that worse.

I’ve recently found myself reserving larger tasks for “keyboard time” and reverting my thinking back to notes (in mobile), which I’ll then formulate to the LLM at some future time.

> What tunnel setup do you use by the way?

I “vibecoded” an agentic runtime that operates my machine generally (including TUIs like Codex/Claude Code), which I connect through a custom proxy and mobile app (both also vibecoded).

I previously tried Cloudflare Tunnels and an SSH setup, but it all felt a bit hacky.

Unfortunately the app is iOS only, but I could open source it and you’d probably be able to make an Android clone quickly (:

[satvikpendem]

That could be cool, no issues with Claude Code not working in third party harnesses or their recent changes about different (more expensive) billing for programmatic usage? I guess I generally use OpenAI models which don't care.

[buu700]

For me personally, I haven't really found that length per se is what makes something harder to write on mobile vs desktop, but more the level of "complexity". If it's just a matter of banging out a bunch of straightforward linear text, I'll often reach for my phone before my laptop. Mobile swipe typing is actually pretty productive for that sort of thing, in my experience.

Where it starts to become a pain is when the task demands a lot of formatting, symbols/punctuation, uncommon words, non-linear writing/editing, or referencing of outside information. The more I have to multitask, and the less I can just stay in a flow and churn out effectively a stream of consciousness, the more constraining a mobile device is going to feel. But for lots of things it's surprisingly great; sometimes I'll intentionally do the heavy lifting on a longer document from my phone and then handle editing/formatting/proofreading from my laptop.

Anyway, I set up Tailscale and aRDP a few months ago (as well as Termius, but have gravitated more toward aRDP in practice), and it's been a pretty substantial efficiency boost. On one hand, I've sort of experienced the same thing as the parent — not necessarily longer, but more complex prompts often have me putting down the phone and grabbing my laptop. On the other hand, lots of prompts are totally fine from mobile. There are also entire categories of tasks where every few hours I just need to sanity check the current diff, latest commits, and Codex output, then resend some variation of "please continue" from my prompt history and maybe answer some follow-up questions; mobile is perfect for that.

[satvikpendem]

For prompting an LLM specifically, what sort of formatting do you need, as you can just throw a stream of consciousness to it and it'll parse it just fine? For looking up other stuff, sure, but it's not too hard to open up new tabs in the mobile browser. I find it way more useful to be able to make stuff on the go rather than having to sit down every time.

Does the tunnel setup feel clunky to use? That's the main thing that stops me.

[buu700]

I guess it depends on the prompt, but code blocks, lists, block quotes, and horizontal lines all come to mind. Not that formatting is a huge deal (particularly in Markdown), but it's just one of many small things that adds to the feeling that I'll have an easier time producing a given body of text with a full mouse and keyboard.

Another thing I didn't mention is copying to the clipboard, which kind of sucks on mobile in general, but is particularly a hassle within RDP. If I'm going to need to copy a bunch of terminal output, snippets of files from VS Code, maybe some browser console errors, etc., I generally don't bother attempting to put that prompt together from my phone.

Tailscale is fairly polished and seamless to use for creating the actual tunnel to the dev machine. The RDP part may be a bit hacky, but it does everything I need and works well enough that at this point I haven't invested time in trying out alternatives. Using a full Linux desktop from a 6" smartphone is inherently going to be clunky, but the flip side is it's 100% batteries-included. You'll never have to rely on some app to reimplement end-to-end support for your entire dev workflow, because it's already a direct interface to your actual dev box.

aRDP deserves a lot of credit for how practical this is. It's clear that a lot of care was taken to map mobile interaction metaphors to desktop UIs in a way that was as natural as could reasonably be done. For what it is, the UI/UX is surprisingly smooth.

I also tested the new ChatGPT feature. Not a full RDP replacement, but it'll be a super handy companion UI after Plan mode is fully supported.

[lmwnshn]

I've been coding on Android for a few months, mostly while walking around outside or showering. I'm on a mix of Tailscale + Termux + ssh server + tmux + codex CLI, Tailscale is great.

I think you may be able to optimize your workflow more by drafting your prompt in ChatGPT first; get it to expand out the intent for you. Doing that has made phone coding a lot more tolerable for me.

I like to think that I've given phone coding a fair shot (and I continue to do it), but I agree with the other poster that there's something about the lack of a keyboard that really gets to me :) I wish I knew what it was.

[satvikpendem]

I was thinking about this, don't you think having everything in a terminal on a phone screen is a bit clunky to type in? Ideally I'd want it to be a clone of the official iOS apps from these AI companies with good mobile features like copy paste, smooth scroll, etc. Looks like the article's ChatGPT Codex functionality is in Android as well.

[kanzure]

It's a lot easier to write long messages on a phone with something like Whisper.

[satvikpendem]

I'm not sure about others but I can't coherently voice my thoughts through speech alone as I'd want to think and revise the message, so I generally don't use voice transcription with AI.

[kanzure]

I haven't found that to be an issue. Just say what revisions you want. Once you're done, paste it into an LLM to clean it up into a usable prompt.

[satvikpendem]

That sounds more annoying than just typing it myself. I guess if you're on a walk you can just talk into your earbuds and the coding agent will parse everything automatically though.