Live data from Hacker News

The Codex App

openai.com

661–670 of 671 posts

Re: The Codex App

#661
post #28

How about us, Linux users? This is Mac only. Do they plan to support CLI version with all the features they are adding to desktop app?

Hi! Romain here, I work at OpenAI. The team actually built the Codex app in Electron so we can support both Windows and Linux very soon. Stay tuned!

Would it be tricky to make an Intel Mac build?

Re: The Codex App

#662

Earlier quoted context omitted.

Agree, another improvement i'd like along the lines or renames is lsp suggestions for method names, enums, functions, etc The llm should be able to autocomplete given lsp available symbols, this way it would avoid far less hallucinated methods

Claude, at least, already supports LSP servers though. https://code.claude.com/docs/en/plugins-reference#lsp-server...

It's for diag and lookups. It doesn't look like it's doing edits with it.

opencode is only diags, if I am not mistaken.

Re: The Codex App

#663
post #104

Earlier quoted context omitted.

Usage like this is becoming a rarity. Most people are editing significantly less and "agent interfaces" are slowly taking the focus.

"most" people aren't even using AI yet Of those that are, most are not vibe coding, so an editor is still required at many points

Obviously, in this context, "most people" refers to people who are using AI.

Re: The Codex App

#664

Earlier quoted context omitted.

-p

Oh wow, nice. Does it remember context from run to run?

Just tested and yes, but it's a little tricky so your `c` script will have to manage session IDs:

1. Start a new session and provide a random UUID:

    claude -p "The secret word is potato" --session-id 550e8400-e29b-41d4-a716-446655440000
    
    > I see you've shared a secret word. I'll keep that in mind — the secret word is **potato**.
    > Is there something I can help you with today?
2. Use the -r/--resume flag with the same UUID for follow up messages:

    claude -p "What is the secret word?" -r 550e8400-e29b-41d4-a716-446655440000
    
    > The secret word is **potato**.

Re: The Codex App

#665

Earlier quoted context omitted.

Hi! Romain here, I work at OpenAI. The team actually built the Codex app in Electron so we can support both Windows and Linux very soon. Stay tuned!

Do you plan to release a build for Mac Intel?

You can try this script https://github.com/Miscend/codex-rebuilder

Re: The Codex App

#666
post #28

How about us, Linux users? This is Mac only. Do they plan to support CLI version with all the features they are adding to desktop app?

not only is it mac only, it appears to be arm only as well. App won't launch on my intel mac

there a non official script to get it running on intel https://github.com/Miscend/codex-rebuilder

Re: The Codex App

#667

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...

You can try this script, it should work https://github.com/Miscend/codex-rebuilder

Re: The Codex App

#668

cool, another mac app, fuck windows users i guess

The OS is objectively broken (needs a MS account, ads and everything) so why go out of one's way to make that choice and then act all surprised?

Re: The Codex App

#669
post #542

Earlier quoted context omitted.

And GTK4 is even very usable from Rust too. It’s not a bad development experience, but these companies probably find 100 webdevs for every system programmer.

Come on GUI apps are not systems programming, what's with this title inflation.

I didn't want to call it backend, because it's not that. Maybe desktop programmer? Anyway, if you're doing GUI in Rust or similar, you're at least handling memory and syscalls, which is closer to systems programming, I'd say.

Re: The Codex App

#670
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…

I try to make it a point to acknowledge when I am wrong. And after some time, and maybe after the release of Codex 5.3, the Codex App is a VERY good agentic coder.

I stand by my initial impression, so far as the claim that it did piss me off, but I completely retract my prediction that Codex/OpenAI is going down the Nokia death spiral based on the performance of the current Codex App paired with the Codex 5.3 model.

I think a combination of the new model version, and me having maximum bad luck in my first test (it truly didn’t do that great), made me come to the wrong conclusion. Codex App is actually pretty good. Thanks for pushing back.

Post reply on HN