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

571–580 of 671 posts

Re: The Codex App

#571

Post by mazswojejzony »

why_at wrote: post #222
nycdatasci wrote: post #77

The landing page for the demo game "Voxel Velocity" mentions " start" at the bottom, but actually changes selection. One would think that after 7mm tokens and use of a QA agent, they would catch something like this.

It's also interesting how the functionality of the game barely changes between 60k tokens, 800k tokens, and 7MM tokens. It seems like the additional tokens made the game look more finished, but it plays almost exactly the same in all of them. I wonder what it was doing with all those tokens?

Sadly, my own small game-dev adventures look similar: I can implement the core mechanics fairly quickly, but polishing the game takes ages.

UPDATE: without AI usage at all (just to clarify).

Re: The Codex App

#572

Post by sheepscreek »

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…

It’s less that and more - we’re still figuring out the best interface to use them.

For coding, interacting with the agent is best done via chat, especially if you’re trying to run teams of agents, then you’re not going to be looking at code all the time. The agent will summarize the changes, you will click on the diffs, approve them and move on. So it’s a very different experience from being the only one coding.

Edit:

Here’s a hot take -

A quick note on SwiftUI, it’s a piece of garbage that’s so hard to use that native devs despise it. So far no AI has been able to one shot it for me.

Blender most likely uses immediate mode - which is more resource intensive and less efficient than a stateful object oriented interface. But Zed uses a similar approach with (I think) success.

Then think about this, pre-AI, Google with all its billions, used web interfaces in all its desktop product GUIs :)

Apple, with all of its billions, created XCode which is inferior to every other IDE I have ever used. They still haven’t learned from Visual Studio. Microsoft is bad at a lot of things but developer tooling isn’t one of them.

All that to say, even if you knew what you wanted, taking that vision to reality is a difficult challenge. At least with AI, they could create a 100 different prototypes cheaply and pick the best direction based on that. That they should do, and they probably aren’t.

Re: The Codex App

#573

Post by eloisant »

gbalduzzi wrote: post #462
gloosx wrote: post #451

Earlier quoted context omitted.

>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…

It baffles me how much the discourse over native apps rarely takes this into consideration. You reduce development effort by a third, it is ok to debate whether a company so big should invest into a better product anyway but it is pretty clear why they are doing this

The real question is how much better are native apps compared to Electron apps.

Yes that would take much disk space, but it takes 50Mb or 500Mb isn't noticeable for most users. Same goes for memory, there is a gain for sure but unless you open your system monitor you wouldn't know.

So even if it's something the company could afford, is it even worth it?

Also it's not just about cost but opportunity cost. If a feature takes longer to implement natively compared to Electron, that can cause costly delays.

Re: The Codex App

#574

Post by Closi »

vintagedave wrote: post #526
gloosx wrote: post #451

Earlier quoted context omitted.

>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…

> If "just build it natively" were actually easier, faster, or cheaper at scale, everyone would do just that Value prop of product quality aside, isn't the AI claim that it helps you be more productive? I would expect that OpenAI would run multiple frontends and that they'd use Codex to do it. Ie are they using their own AI (I would assume it's semi-vibe-coded) to just get out a new product or using AI to create a ne…

It's about consistency - you want to build an app that looks and functions the same on all platforms as much as possible. Regardless of if you are hand-coding or vibe-coding 3 entirely separate software stacks, getting everything consistent is going to be a challenge and subtle inconsistencies will sneak in.

It comes back to fundamental programming guidelines like DRY (Don't Repeat Yourself) - if you have three separate implementations in different languages for everything, changes will be come harder and you will move slower. These golden guidelines still stand in a vibe-code world.

Re: The Codex App

#575

Post by bopbopbop7 »

saint_fiasco wrote: post #473
gowld wrote: post #401

Earlier quoted context omitted.

I disagree. There is a tier of people who can't vibe code what you've vibe coded, but also might not trust your app (especially the bank one). There is still a real gap here to be filled by professional work or fakers.

Professionals are doing what I am doing, only inside companies. They make custom software that solves ultra-specific problems of that one company. I don't quite understand the obsession with shipping fancy enterprise b2b saas solutions. That was the correct paradigm for back when developing custom code was expensive. Now it is cheap. Why pay for Salesforce when you only use 1% of Salesforce's features? Just vibe code…

Let me know when Stacy from HR vibe codes her own salesforce alternative, sounds very cool!

Re: The Codex App

#576

Post by auggierose »

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…

Despite being an Electron app, it doesn't work on Intel macs...

Re: The Codex App

#577

Post by Anonyneko »

tombert wrote: post #427
namelosw wrote: post #255

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.

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…

One reason why I personally never bothered is the licensing of some of its important parts, which is a choice of either GPL or commercial. Which is fair, but too bothersome for some use-cases (e.g. mobile apps which are inherently GPL-unfriendly). Electron and the likes are typically MIT/BSD/etc licensed.

Re: The Codex App

#578

Post by AdamN »

pimterry wrote: post #512
AdamN wrote: post #496

Earlier quoted context omitted.

The gap here is that the company has the money and native apps are so clearly better. With an interactive app a company like OpenAI could really tweak the experience for Android and iOS which have different UX philosophies and featuresets in order to give the best experience possible. It's really a no brainer imho.

> the company has the money It's not about money. It's not a tradeoff in cost vs quality - it's a tradeoff in development speed. Shipping N separate native versions requires more development time for any given change: you must implement everything (at least every UI) N times, which drastically increases the design & planning & coordination required vs just building and shipping one implementation. Do you want to move…

Yeah that's why startups often pick iOS first, get product-market fit, and then do Android. The fallacy that abstractions tout is that Android and iOS are the same.

They are not.

A good iOS app is not 1:1 equivalent to what a good Android app would be for the same goal. Treating them as such just gives users a lowest common denominator product.

Re: The Codex App

#579

Post by adam_patarino »

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…

AI has more training on web apps I think the real answer is that these guys are told they need to ship in 2 months and have a huge team of web devs

Re: The Codex App

#580

Post by ponector »

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.

Because there is no point in reporting such complains. Just a waste of time.
Post reply on HN