Live data from Hacker News

Codex for almost everything

openai.com

111–120 of 600 posts

Re: Codex for almost everything

#111

There seems a fair enthusiasm in the UI of these to hide code from coders. Like the prompt interaction is the true source and the actual code is some sort of annoying intermediate runtime inconvenience to cover up. I get that productivity can be improved with a lot of this for non developers, just not sure using 'code' as the term is the right one or not.

Yes, the code is still important. For example, I had tasked Codex to implement function calling in a programming language, and it decided the way to do this was to spin up a brand new sub interpreter on each function call, load a standard library into it, execute the code, destroy the interpreter, and then continue -- despite an already partial and much more efficient solution was already there but in comments. The AI solution "worked", passed all the tests the AI wrote for it, but it was still very very wrong. I had to look at the code to understand it did this. To get it right, you have to either I guess indicate how to implement it, which requires a degree of expertise beyond prompting.

Re: Codex for almost everything

#112
post #59

Earlier quoted context omitted.

> Or at "do my taxes"? codex did my taxes this year (well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough)

> well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough You can't seriously believe laymen will try to implement their own tax calculators.

of course not.

what I believe is that laymen will put all their tax docs into codex and tell it to 'do their taxes' and the tool will decide to implement the calculator, do the taxes and present only the final numbers. the layman won't even know there was a calculator implemented.

Re: Codex for almost everything

#115
post #37

> Computer use is initially available on macOS, Does anyone know of a good option that works on Wayland Linux?

Codex-cli / OpenClaw. If you need a browser use Playwright-mcp. I can't see why I'd want an agent to click around Gnome or Ubuntu desktop but maybe that's just me?

I think the killer feature in this release is the background GUI use.

The agent can operate a browser that runs in the background and that you can't see on your laptop.

This would be immensely useful when working with multiple worktrees. You can prompt the agent to comprehensively QA test features after implementing them.

Re: Codex for almost everything

#116
post #99

Confusingly, Codex their agentic programming thing and codex their GUI which only works on Mac and Windows have the same name. I think the latter is technically "Codex For Desktop", which is what this article is referring to.

It’s marginally better than Microsoft naming things.

You mean you're not excited to use Copilot Chat in the Microsoft 365 Copilot App??

(This is the real, official name for the AI button in Office)

Re: Codex for almost everything

#117
post #59

Earlier quoted context omitted.

> Or at "do my taxes"? codex did my taxes this year (well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough)

If your prompt was more complex than "do my taxes", then this is irrelevant.

it was many hours of working with codex, guidance and comparing to known-good outputs from previous years, but a sufficiently smart model would be able to just do it without any steering; it'd still take hours, but my input wouldn't be necessary. a harness for getting this done probably exists today, gastown perhaps or something that the frontier labs are sitting on.

Re: Codex for almost everything

#118

There seems a fair enthusiasm in the UI of these to hide code from coders. Like the prompt interaction is the true source and the actual code is some sort of annoying intermediate runtime inconvenience to cover up. I get that productivity can be improved with a lot of this for non developers, just not sure using 'code' as the term is the right one or not.

Yes, the code is still important. For example, I had tasked Codex to implement function calling in a programming language, and it decided the way to do this was to spin up a brand new sub interpreter on each function call, load a standard library into it, execute the code, destroy the interpreter, and then continue -- despite an already partial and much more efficient solution was already there but in comments. The A…

Yep, all models today still need prompting that requires some expertise. Same with context management, it also needs both domain expertise as well as knowing generally how these models work.

Re: Codex for almost everything

#119

Earlier quoted context omitted.

really struggling to understand where this is coming from, agents haven't really improved much over using the existing models. anything an agent can do, is mostly the model itself. maybe the technology itself isn't mature yet.

My view is different. Agent products have access to tools and to write and run code. This makes them much more useful than raw models.

Yes, I think they unlock a whole new level of capability when they have a r/w file system (memory), code execution and the web.

Re: Codex for almost everything

#120
post #112

Earlier quoted context omitted.

> well it actually implemented a normalization pipeline and a tax computing engine which then did the taxes, but close enough You can't seriously believe laymen will try to implement their own tax calculators.

of course not. what I believe is that laymen will put all their tax docs into codex and tell it to 'do their taxes' and the tool will decide to implement the calculator, do the taxes and present only the final numbers. the layman won't even know there was a calculator implemented.

Yeah, good luck trusting the output!
Post reply on HN