Live data from Hacker News

The Codex App

openai.com

371–380 of 671 posts

Re: The Codex App

#371
post #369
post #367

I had been procrastinating putting in the effort to find a decent web designer to redesign our company’s website because I couldn’t stomach the hours I would need to put in to educate them about our messaging and to slowly go around and around iteratively to get the design nailed. Last week, I decided to try building the site myself using Codex (the terminal one). I chose Astro as the framework because I wanted to le…

PS: Yes, I spent several hours on the weekend getting Codex to add animations, sound effects, and a mini game to our home page hero graphic. That was fun. I look forward to the creativity that people unleash with tools like this in the coming months.

Link to the site?

Re: The Codex App

#372
post #284

People's mileage may vary, but in my instance, this was so bad that I actually got angry while trying to use it. It's slow and stupid. It does not do proper research. It does not follow instructions. It randomly decides to stop being agentic, and instead just dumps the code for me to paste. It has the extremely annoying habit of just doing stuff without understanding what I meant, making a mess, then claiming everyth…

I'm not taking OpenAI's side here but have you reviewed what claude did?

I only use claude through the chat ui because it’s faster and it gives me more control. I read most of it and the code is almost always better than what I would do, simply because lazy ass me likes to take shortcuts way too often.

Re: The Codex App

#373
post #205

Earlier quoted context omitted.

I don't know why any frontier model lab can't ship a mobile app that doesn't use a cloud VM but is able to connect to your laptop/server and work against local files on there when on the same network (e.g.: on TailScale). Or even better act as a remote control for a harness running on that remote device, so you couldn't seamlessly switch between phone and laptop/server.

I'm also so baffled by this. I had to write my own app to be able to do seamless handoff between my laptop/desktop/phone and it works for me ( https://github.com/kzahel/yepanywhere - nice web interface for claude using their SDK, MIT, E2E relay included, no tailscale required) but I'm so baffled why this isn't first priority. Why all these desktop apps?

This looks awesome! And incredibly polished. Exactly the approach I take to vibebin-- I may have to integrate yep anywhere into it (if that's ok) as an additional webui!

https://github.com/jgbrwn/vibebin

Although I would need it to listen on 0.0.0.0 instead of localhost because I use LXC containers so caddy on the host proxies to the container 10.x address. Hopefully yep has a startup flag for that. I saw that you can specify the port but didn't see listening address mentioned.

Re: The Codex App

#374

Earlier quoted context omitted.

This is another common excuse. You don't need to use microsoft's or apple's or google's shit UI frameworks. E.g. see https://filepilot.tech/ You can just write all the rendering yourself using metal/gl/dx. if you didn't want to write the rendering yourself there are plenty of libraries like skia, flutter's renderer, nanovg, etc

> You don't need to use microsoft's or apple's or google's shit UI frameworks. E.g. see https://filepilot.tech/ That's only for Windows though, it seems? Maybe the whole "just write all the rendering yourself using metal/gl/dx" is slightly harder than you think.

I mean, every cross-platform commercial DAW manages to do it? Bitwig, Renoise, Reaper, even VCV.

Re: The Codex App

#375

Earlier quoted context omitted.

The situation for Desktop development is nasty. Microsoft had so many halfassed frameworks and nobody knows which one to use. It’s probably the de facto platform on Windows IS Electron, and Microsoft use them often, too. On MacOS is much better. But most of the team either ended up with locked in Mac-only or go cross platform with Electron.

This is another common excuse. You don't need to use microsoft's or apple's or google's shit UI frameworks. E.g. see https://filepilot.tech/ You can just write all the rendering yourself using metal/gl/dx. if you didn't want to write the rendering yourself there are plenty of libraries like skia, flutter's renderer, nanovg, etc

I'd love to see some opensource projects actually do a good job of this. Its a lot of work, especially if you want:

- Good cross platform support (missing in filepilot)

- Want applications to feel native everywhere. For example, all the obscure keyboard shortcuts for moving around a text input box on mac and windows should work. iOS and Android should use their native keyboards. IME needs to work. Etc

- Accessibility support for people who are blind and low vision. (Screen readers, font scaling, etc)

- Ergonomic language bindings

Hitting these features is more or less a requirement if you want to unseat electron.

I think this would be a wonderful project for a person or a small, dedicated team to take on. Its easier than it ever used to be thanks to improvements in font rendering, cross platform graphics libraries (like webgpu, vulcan, etc) and improvements in layout engines (Clay). And how much users have dropped their standards for UI consistency ever since electron got popular and microsoft gave up having a consistent UI toolkit in windows.

There are a few examples of teams doing this in house (eg Zed). But we need a good opensource project.

Re: The Codex App

#376
post #288

Earlier quoted context omitted.

Moral of your story. Each and everyone of us is able to write their own story, and come up with their own 'Moral'. Settling for less (if AI is a productivity booster, which is debatable) doesn't equal being screwed. There is wisdom in reaching your 'enough' point.

If you look at the current hiring trends and how much longer it is taking developers to get jobs these days, a mid level ticket taker is definitely screwed between a flooded market, layoffs and AI. By definition, this is the worse AI coding will ever be and it’s pretty good now.

> By definition, this is the worse AI coding will ever be

This may be true, but it's not necessarily true, and certainly not by definition. For example, formal verification by deductive methods has improved over the past four decades, and yet, by the most important measures, it's got worse. That's because the size of software it can be used to verify affordably has grown, but significantly slower than the growth in the size of the average software project. I.e. it can be used on a smaller portion of software than it could be used on decades ago.

Perhaps ironically, some people believe that the solution to this problem is AI coding agents that will write correctness proofs, but that is based on the hope that their fate will be different, i.e. that their improvement will outpace the growth in software size.

Indeed, it's possible that AI coding will make some kinds of software so cheap that their value will drop to close to zero, and the primary software creation activity by professionals will shift precisely to those programs that agents can't (yet) write.

Re: The Codex App

#377
post #363

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, Blende…

It’s just irrelevant for most users. These companies are getting more adoption than they can handle, no matter how clunky their desktop apps are. They’re optimizing for experimentation. Not performance.

More adoption? I don't think so... It feels to me that these models && tools are getting more verbose/consuming more tokens to compensate for a decrease in usage. I know my usage of these tools has fallen off a cliff as it become glaringly obvious they're useful in very limited scopes.

I think most people start off overusing these tools, then they find the few small things that genuinely improve their workflows which tend to be isolated and small tasks.

Moltbot et al, to me, seems like a psyop by these companies to get token consumption back to levels that justify the investments they need. The clock is ticking, they need more money.

I'd put my money on token prices doubling to tripling over the next 12-24 months.

Re: The Codex App

#378
No access via paid API? C’mon guys. Big enterprise consume codex and Claude via vertex and azure foundry, because it’s already available on their contracts.

And they don’t mind the usage cost. Please let me spend 5k monthly on this.

Re: The Codex App

#379

Earlier quoted context omitted.

This is another common excuse. You don't need to use microsoft's or apple's or google's shit UI frameworks. E.g. see https://filepilot.tech/ You can just write all the rendering yourself using metal/gl/dx. if you didn't want to write the rendering yourself there are plenty of libraries like skia, flutter's renderer, nanovg, etc

I'd love to see some opensource projects actually do a good job of this. Its a lot of work, especially if you want: - Good cross platform support (missing in filepilot) - Want applications to feel native everywhere. For example, all the obscure keyboard shortcuts for moving around a text input box on mac and windows should work. iOS and Android should use their native keyboards. IME needs to work. Etc - Accessibility…

But Electron doesn’t hit that bar even

Re: The Codex App

#380
post #251

Earlier quoted context omitted.

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 hist…

It would be cool if I didn't have to worry about whether I was "in" or "out" of the AI TUI. Right now, I need at least two terminals open: One running my shell, that I use to issue shell commands, and one running Claude, where I can't. It would be nice if it could just be my shell, and when I wanted to invoke claude, I'd just type: c Do this programming task for me. Right in the shell.

isn't that what Simon Willison's `llm` does?

edit: [link](https://github.com/simonw/llm)

Post reply on HN