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

321–330 of 671 posts

Re: The Codex App

#321

Post by dworks »

Somewhat underwhelmed. I consider agents to be a sidetrack. The key insight from the Recursive Language Models paper is that requirements, implementation plans, and other types of core information should not be part of context but exist as immutable objects that can be referenced as a source of truth. In practice this just means creating an .md file per stage (spec, analysis, implementation plan, implementation summary, verification and test plan, manual qa plan, global state reference doc).

I created this using PLANS.md and it basically replicates a kanban/scrum process with gated approvals per stage, locked artifacts when it moves to next stage, etc. It works very well and it doesnt need a UI. Sure, I could have several agents running at the same time, but I believe manual QA is key to keeping the codebase clean, so time spent on this today means that future requirements can be implemented 10x faster than with a messy codebase.

Re: The Codex App

#322

Post by measurablefunc »

bopbopbop7 wrote: post #304
measurablefunc wrote: post #261

Earlier quoted context omitted.

What does the bootcamp have to do w/ anything? He is using AI slop to make money, that's all that matters in a socio-economic system wherein everyone & everything must make profits to persist. Edit: found another example from coinbase: https://x.com/0xEricBrown/status/2018082458143699035 . Edit: I'm not going to keep addressing your comment if you keep editing it. You asked for an example & I found two very easily. I…

Your first example is just a twitter post of a guy asking for a developer to review his vibe coded bot. Nothing shipped. The second example is twitter post of a crypto bro asking people to build something using his crypto API. Nothing shipped. Literally nothing shipped, just twitter posts of people selling a coding bootcamp and crypto.

You should make a note & revisit this in a few days to figure out whether your assessment was correct or not. I've already wasted enough time here so good luck.

Re: The Codex App

#323

Post by scotty79 »

uxhacker wrote: post #295
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…

Why would widgets and buttons be better than a console, and or voice?

Because you see stuff before you decide what to invoke?

Re: The Codex App

#324

Post by OlympicMarmoto »

embedding-shape wrote: post #306
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

> 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.

The proof that rendering is not _that_ hard because the flutter team did it when they switched off skia (although technically they still use skia for text rendering, I'll admit that text rendering and layout is hard)

Re: The Codex App

#325

Post by saadn92 »

mritchie712 wrote: post #116
IMTDb wrote: post #37

Earlier quoted context omitted.

Maybe a dumb question on my side; but if you are using a GUI like emdash with Claude Code, are you getting the full claude code harness under the hood or are you "just" leveraging the model ?

yeah, I wanted a better terminal for operating many TUI agent's at once and none of these worked because they all want to own the agent. I ended up building a terminal[0] with Tauri and xterm that works exactly how I want. 0 - screenshot: https://x.com/thisritchie/status/2016861571897606504?s=20

looks like we both did haha: https://github.com/saadnvd1/aTerm

Re: The Codex App

#326

Post by measurablefunc »

romainhuet wrote: post #294
measurablefunc wrote: post #248

Earlier quoted context omitted.

Their goal is to ship as fast as possible b/c they don't care about what you care about. Their objective is to gather as much data as possible & electron is good enough for that.

I work at OpenAI, and I get the concern. From our side, this was a careful tradeoff: Electron lets us iterate faster and makes it possible to bring the Codex app to Windows and Linux very soon. That doesn’t mean performance or UX don’t matter—we’re actively paying attention to both. Would genuinely love your thoughts if you try it. Early users have been surprised by how native it feels!

I use Google's antigravity so I personally have no problem w/ electron applications. At the end of the day UI performance is not a bottleneck for me.

Re: The Codex App

#327

Post by adastra22 »

belfthrow wrote: post #310
zem wrote: post #305

Earlier quoted context omitted.

"native" is used for different things, from "use the platform's default gui toolkit" to "compile to a machine code binary". the former is a bit of a mess, but the latter is strictly better than wrapping a web view and shipping an entire chrome fork to display and interpret it. just write something in qt and forget about native look and feel, and the performance gain will be enough to greatly improve the user experien…

Should just use javafx or swing. Take a leaf out of intellij which while it as it's own performance problems (although not from the fact of the ui framework) has a fantastic ui across Mac / windows / nix

I can’t tell if this word salad is sarcasm or genuine.

Re: The Codex App

#328

Post by adastra22 »

dheera wrote: post #292
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.

This. Even Linux is nasty. Qt and GTK are both horrible messes to use. It would be nice if someone made a way to write desktop apps in JavaScript with a consistent, cross-platform modern UI (i.e. swipe to refresh, tabs, beautiful toggle switches, not microscopic check boxes) but without resorting to rendering everything inside a bloated WebKit browser.

That’s what React Native is. But JavaScript is the problem.

Re: The Codex App

#329

Post by AloysB »

raw_anon_1111 wrote: post #297
AloysB wrote: 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.

I am really not convinced yet.

From all the data I have seen, the software industry is poised for a lot more growth in the foreseeable future.

I wonder if we are experiencing a local minima, on a longer upward trend.

Those that do find a job in a few days aren't online to write about it, so based on what is online we are lead to believe that it's all doom and gloom.

We also come out of a silly growth period where anyone who could sort a list and build a button in React would get hired.

My point is not that AI-coding is to be avoided at all costs, it's more about taming the fear-mongering of "you must use AI or will fall behind". I believe it's unfounded - use it as much or as little as you feel the need to.

P.S.: I do think that for juniors it's currently harder and require intentional efforts to land that first job - but that is the case in many other industries. It's not impossible, but it won't come on a silver plate like it did 5-7 years ago.

Re: The Codex App

#330

Post by stevejb »

ryandrake wrote: post #278
pama wrote: 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.

Most AI agents have a 'bash mode' and, you can use Warp terminal which is terminal first, but easy to activate the AI from the terminal. For example, if you mangle a jq command, it will use AI to suggest the right way to do it.
Post reply on HN