Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Codex App

openai.com

Post reply on HN
Print view View original

501–510 of 671 posts

Re: The Codex App

#501

Post by 72deluxe »

OlympicMarmoto wrote: post #220

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…

I used wxWidgets to build a native GUI for Windows + Mac 10+ years ago and implemented all GUI-drawing (it was an audio signal processor control software so included meters, faders, knobs, audio spectrum and I even incorporated Horde3D OpenGL interface for visualising an arena [sadly never fully finished to full potential as my modelling abilities in Blender simply wasn't good enough]). I wrote that, and another guy wrote the network library in C that sent signals to the network devices, and received them. I responded to the incoming network info to draw appropriate parts of the UI like meters/scopes at 50ms minimum.

The fact that we did this as a 1-man team for the GUI and that I can still compile it today (if I had the code) against wxWidgets, to then run on macOS and Windows simply shows the lazy nature of (most/all?) desktop apps by big companies these days.

I utterly detest using them, but it seems customers think an app that takes 5 seconds to launch with a spinning whirly wheel and horizontal gradient animation over list views for 5+ seconds before content is loaded is perfectly acceptable. Quality with a capital K!

Re: The Codex App

#502

Post by theknarf »

gloosx wrote: post #451
OlympicMarmoto wrote: post #220

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…

>This requires calling native APIs (e.g., Win32), which is not feasible from Electron. Who told you that? You can write entire C libraries and call them from Electron just fine. Browser is a native application after all. All this "native applications" debate boils down to the UI implementation strategy. Maintaining three separate UI stacks (WinUI, SwiftUI, GTK/Qt) is dramatically more expensive and slower to iterate…

React Native is able to build abstractions on top of both Android and iOS that uses native UI. Microsoft even have a package for doing a "React Native" for Windows: https://github.com/microsoft/react-native-windows

It's weird that we don't have a unified "React Native Desktop" that would build upon the react-native-windows package and add similar backends for MacOS and Linux. That way we could be building native apps while keeping the stuff developers like from React.

Re: The Codex App

#503

Post by Bishonen88 »

ProofHouse wrote: post #480
Bishonen88 wrote: post #479

Crazy free tier. I reckon I used ~2 weeks of the claude $20 subscription within an hour. Spawned like 12 semi big tasks and I still didn't see no warnings.

Not totally understanding this. Crazy free tier but that it used a crazy amount of tokens that cost you? Sry just trynna see what you’re saying

My bad then. I meant that it's "Crazy Good" as in that the free tier gave me a tremendous amount of tokens.

What I didn't realize though, is that the limit doesn't reset each 5 hours as is the case for claude. I hit the limit of the free tier about 2 hours in, and while I was expecting to be able to continue later today, it alerts me that I can continue in a week.

So my hype for the amount of tokens one gets compared to claude was a bit too eager. Hitting the limit and having to wait a week probably means that we get a comparable token amount vs the $20 claude plan. I wonder how much more I'd get when buying the $20 plus package. The pricing page doesn't make that clear (since there was no free plan before yesterday I guess): https://developers.openai.com/codex/pricing/

Re: The Codex App

#505

Post by pregnenolone »

jarek-foksa wrote: post #282
OlympicMarmoto wrote: post #265

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

Customers simply don't care. I don't recall a single complain about RAM or disk usage of my Electron-based app to be reported in the past 10 years. You will be outcompeted if you waste your time reinventing the wheel and optimizing for stuff that doesn't matter. There is some market for highly optimized apps like e.g. Sublime Text, but you can clearly see that the companies behind them are struggling.

> Customers simply don't care. I don't recall a single complain about RAM or disk usage of my Electron-based app to be reported in the past 10 years.

Nothing is worse than reading something like this. A good software developer cares. It’s wrong to assume customers don't care simply because they don't know what's going on under the hood. Considering the downsides and the resulting side effects (latency, more CPU and RAM consumption, fans spinning etc.), they definitely do care. For example, Microsoft has been using React components in their UI, thinking customers wouldn’t care, but as we have been seeing lately, they do care.

Re: The Codex App

#506

Post by jtrn »

prodigycorp wrote: post #466
stitched2gethr wrote: post #452

Earlier quoted context omitted.

Perhaps if he was able to get Claude Code to do what he wanted in less time, and with a better experience, then maybe that's not a skill he (or the rest of us) want to develop.

Sure, that's fine. I wrote my comment for the people who don't get angry at an AI agents after using them for the first time within five hours of their release. For those who aren't interested in portending doom for OpenAI. (I have elaborate setups for Codex/Claude btw, there's no fanboying in this space.) Some things aren't common sense yet so I'm trying my part to make them so.

Feelings are information with just as much, or more, value as biased intellectualizing.

Ask Linus Torvalds.

Re: The Codex App

#507

Post by FooBarWidget »

nine_k wrote: post #487
tombert wrote: post #427

Earlier quoted context omitted.

I guess it shows how geriatric I am with desktop app development these days, but does no one use Qt anymore? Wasn't the dream for that to be a portable and native platform to write GUI apps? Presumably that could abstract away which bullshit Microsoft framework they came out with this week. I haven't touched desktop application programming in a very long time and I have no desire to ever do so again after trying to l…

Qt means C++. I'll take Typescript over C++ for a GUI task any day. Qt is also pretty memory-hungry; maybe rich declarative (QML) skinnable adaptable UIs with full a11y support, etc just require some RAM no matter what. And it also looks a wee bit "non-native" to purists, except on Windows, where the art of uniform native look is lost. Also, if you ever plan extensions / plugin support, you already basically have it…

I don't get this HN worship of Qt. Have you ever used Qt apps on macOS? They don't feel native at all. They feel sort-of native-emulating in the same way wxWidgets apps on macOS feel: they use native controls but all the little details including design language are off.

I'm not saying this is a huge problem for me even if it bothers me personally. But if you're here on HN advocating native over Electron, then it seems logical to me that you would care about being truly native instead of merely "using native controls while feeling off".

This is even before getting to the point that Qt isn't truly native. They just draw controls in a style that looks native, they don't actually use native controls. wxWidgets uses native controls but they don't behave better despite that.

Re: The Codex App

#508

Post by pregnenolone »

Yeroc wrote: post #391
fnord77 wrote: post #350

Earlier quoted context omitted.

Java swing is way underrated despite being very complex. It baffles me why this just sort of withered on the vine. (I was a swing developer for several years)

The web sucked all the oxygen out of the room.

It really was Oracle’s fault – they neglected deployment for too long. Deploying Java applications was simply too painful, and neither JLink nor JPackage existed.

Re: The Codex App

#509

Post by prodigycorp »

tomashubelbauer wrote: post #500
prodigycorp wrote: post #382

Earlier quoted context omitted.

If you're using 5.2 high, with all due respect, this has to be a skill issue. If you're using 5.2 Codex high — use 5.2 high. gpt-5.2 is slow, yes (ok, keeping it real, it's excruciatingly slow). But it's not the moronic caricature you're saying it is. If you need it to be up to date with your version of a framework, then ask it to use the context7 mcp server. Expecting training data to be up to date is unreasonable f…

I am using GPT-5.2 Codex with reasoning set to high via OpenCode and Codex and when I ask it to fix an E2E test it tells me that it fixed it and prints a command I can run to test the changes, instead of checking whether it fixed the test and looping until it did. This is just one example of how lazy/stupid the model is. It _is_ a skill issue, on the model's part.

i refuse to defend the 5.2-codex models. They are awful.

Re: The Codex App

#510

Post by adammarples »

prodigycorp wrote: post #382
jtrn wrote: 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…

If you're using 5.2 high, with all due respect, this has to be a skill issue. If you're using 5.2 Codex high — use 5.2 high. gpt-5.2 is slow, yes (ok, keeping it real, it's excruciatingly slow). But it's not the moronic caricature you're saying it is. If you need it to be up to date with your version of a framework, then ask it to use the context7 mcp server. Expecting training data to be up to date is unreasonable f…

How would a person interpret the latest version of flowbite?
Post reply on HN