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

Codex for almost everything

openai.com

Post reply on HN
Print view View original

491–500 of 600 posts

Re: Codex for almost everything

#491

Post by unsupp0rted »

CuriouslyC wrote: post #362
unsupp0rted wrote: post #289

Earlier quoted context omitted.

I can get about 20 ~ 40 minutes of my 5-hour limit using Codex 5.4 medium to say write a patch script in typescript for a Firebase + BigQuery app. That's including about 10 minutes of first writing a planning.md doc with 5.2 High. A couple weeks ago I'd get roughly 2~3 hours. And a month before that I couldn't break the 5-hour limit.

They were running a 2x rate limit promo last month.

Theoretically yes. In practice even a few weeks before it ended, the actual rate limit was down to what it was before the promo. And now I'm getting roughly 0.25x of what I got before the promo.

Re: Codex for almost everything

#492

Post by suddenlybananas »

cameronh90 wrote: post #142
William_BB wrote: post #132

Earlier quoted context omitted.

> The idea that code is something sacred and only devs can somehow do it is dying, and I personally love it, as I am watching it enable so many of my friends and family who have no idea how to code. People on HN are seriously delusional. AI removed the need to know the syntax. Your grandma does not know JS but can one shot a React app. Great! Software engineering is not and has never been about the syntax or one shot…

I wonder how good AI is at playing Factorio. That’s the closest thing I’ve ever done to programming without the syntax.

https://arxiv.org/abs/2503.09617

Re: Codex for almost everything

#493

Post by duskdozer »

soco wrote: post #486
shevy-java wrote: post #472

Earlier quoted context omitted.

> I'm so glad I switched to Linux more than a decade ago. At least on the PC there will still be an open source ecosystem for a long time to come, it may have less features but I'm willing to accept that. Wait until age verification is mandatory everywhere. :) I can already see that happening, e. g. to access financial transactions or government apps, one needs to verify the id, and that will not work without age ver…

There's always the zero knowledge proof tech alternative, but I don't have the feeling we are moving in that direction - it's not the most profitable business is it.

No, nor is it most amenable to mass surveillance.

Re: Codex for almost everything

#494

Post by Oarch »

"You've hit the message limit, upgrade to Plus for more".

Ok. I upgrade.

"You've hit the message limit, upgrade to Plus for more".

Hmm. They've charged me. There's no meaningful support. I just got scammed, didn't I...

Re: Codex for almost everything

#495

Post by fredericgalline »

tvmalsv wrote: post #13

My monthly subscription for Claude is up in a week, is there any compelling reason to switch to Codex (for coding/bug fixing of low/medium difficulty apps)? Or is it pretty much a wash at this point?

I've been switching between both depending on which one is having a good week — and that's the honest answer for most people right now.

But the real issue I ran into wasn't which model is better. It's that every time I switched, I lost weeks of accumulated context. The AI didn't know my project's conventions anymore, didn't remember the architecture decisions, didn't know what was tried and rejected.

What helped me was separating the project context from the tool. Keep the conventions, rules, and decisions in plain files in the repo. Both Claude Code and Codex can read them at session start. Then the question becomes "which model is sharper this week" instead of "can I afford to lose my context."

The answer to your question: it's mostly a wash on capability. The real cost of switching is the context you don't realize you're rebuilding.

Re: Codex for almost everything

#496

Post by Razengan »

woeirua wrote: post #194

Just reading the comments here it's amazing how many people seemingly don't know that Claude Desktop and Cowork basically already does all of this. Codex isn't pioneering these features, it's mostly just catching up.

Codex has better UX/UI, but Claude is still way ahead in sheer schizophrenia: https://i.imgur.com/jYawPDY.png

Opus 4.6 has had many "oops you're right!" gaffes and other annoyances that I let my Claude subscription expire yesterday.

Codex has been more consistent and helpful, but it too is still not quite at the point where you can blindly trust it without verifying the output.

Re: Codex for almost everything

#497

Post by yard2010 »

whattheheckheck wrote: post #411
_the_inflator wrote: post #339

Earlier quoted context omitted.

I knew a guy who did 6510 and 68000 assembler for many years and had a hard time using higher order languages as well as DSLs. “Only assembler is real code. Everything else is phony, bloat for what can be done way better with a fraction of the C++ memory footprint.” Well that guy was me and while I still consider HOLs as weird abstractions, they are immensely useful and necessary as well as the best option for the ti…

A cross join is a for loop

As a child I couldn't understand why I have to talk in a cryptic language and can't just write a for loop when working with DBs. In hindsight it was a valuable lesson that implementation details matter even though I wouldn't want them to.

Re: Codex for almost everything

#500

Post by xpe »

embirico wrote: post #229
incognito124 wrote: post #35

I swear OpenAI has 2-3 unannounced releases ready to go at any time just so they can steal some thunder from their competitors when they announce something

(I work at OpenAI) Heya, in reality it's more much organic than that. We build stuff, ship it internally, then work crazy hard to quickly ship it externally. When we put something out on a given day, it's usually been in the works and scheduled for a while. One concrete example: to set up a launch like today, where press, influencers, etc, all came out at 10a PT. That's all coordinated well in advance!

We cannot trust identity like we used to here on HN (even pre-LLM-AI I thought we seemed naive.) Unfortunately, we live in a world or anyone or any AI can claim almost anything plausible sounding.

Where do we go from here? (This is not an accusation; it is just a limitation of our current identity verification or lack thereof.)

Post reply on HN