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

Unrolling the Codex agent loop

openai.com

Post reply on HN
Print view View original

131–140 of 220 posts

Re: Unrolling the Codex agent loop

#131

Post by pxc »

rmunn wrote: post #128
fragmede wrote: post #85

Earlier quoted context omitted.

If the software is, say, Audacity, who's target market isn't specifically software developers, sure, but seeing as how Claude code's target market has a lot of people who can read code and write software (some of them for a living!) it becomes material. Especially when CC has numerous bugs that have gone unaddressed for months that people in their target market could fix . I mean, I have my own beliefs as to why they…

> ... numerous bugs that have gone unaddressed for months that people in their target market could fix . THIS. I get so annoyed when there's a longstanding bug that I know how to fix, the fix would be easy for me, but I'm not given the access I need in order to fix it. For example, I use Docker Desktop on Linux rather than native Docker, because other team members (on Windows) use it, and there were some quirks in ho…

> I get so annoyed when there's a longstanding bug that I know how to fix, the fix would be easy for me, but I'm not given the access I need in order to fix it.

This exact frustration (in his case, with a printer driver) is responsible for provoking RMS to kick off the free software movement.

Re: Unrolling the Codex agent loop

#132

Post by pxc »

stavros wrote: post #89
redox99 wrote: post #60

Earlier quoted context omitted.

For some reason a lot of people are unaware that Claude Code is proprietary.

Can't really fault them when this exists: https://github.com/anthropics/claude-code

Using GitHub as an issue tracker for proprietary software should be prohibited. Not that it would, these days.

Codeberg at least has some integrity around such things.

Re: Unrolling the Codex agent loop

#133

Post by arthurcolle »

fragmede wrote: post #85
atonse wrote: post #68

Earlier quoted context omitted.

Probably because it doesn’t matter most of the time?

If the software is, say, Audacity, who's target market isn't specifically software developers, sure, but seeing as how Claude code's target market has a lot of people who can read code and write software (some of them for a living!) it becomes material. Especially when CC has numerous bugs that have gone unaddressed for months that people in their target market could fix . I mean, I have my own beliefs as to why they…

They are turning it into a distributed system that you'll have to pay to access. Anyone can see this. CLI is easy to make and easy to support, but you have to invest in the underlying infrastructure to really have this pay off.

Especially if they want to get into enterprise VPCs and "build and manage organizational intelligence"

Re: Unrolling the Codex agent loop

#134

Post by energy123 »

daxfohl wrote: post #76

I like it but wonder why it seems so slow compared to the chatgpt web interface. I still find myself more productive copying and pasting from chat much of the time. You get virtually instant feedback, and it feels far more natural when you're tossing around ideas, seeing what different approaches look like, trying to understand the details, etc. Going back to codex feels like you're waiting a lot longer for it to do…

xhigh reasoning effort for 5.2 Thinking is not available for ChatGPT Plus subscribers in the web interface.

Re: Unrolling the Codex agent loop

#135

Post by karmasimida »

written-beyond wrote: post #9

Has anyone seriously used codex cli? I was using LLMs for code gen usually through the vscode codex extension, Gemini cli and Claude Code cli. The performance of all 3 of them is utter dog shit, Gemini cli just randomly breaks and starts spamming content trying to reorient itself after a while. However, I decided to try codex cli after hearing they rebuilt it from the ground up and used rust(instead of JS, not implyi…

Codex’s only caveat is too slow.

This is the biggest UX killer，unfortunately

Re: Unrolling the Codex agent loop

#136

Post by edmundsauto »

appplication wrote: post #61
postalcoder wrote: post #56

The best part about this blog post is that none of it is a surprise – Codex CLI is open source. It's nice to be able to go through the internals without having to reverse engineer it. Their communication is exceptional, too. Eric Traut (of Pyright fame) is all over the issues and PRs. https://github.com/openai/codex

I appreciate the sentiment but I’m giving OpenAI 0 credit for anything open source, given their founding charter and how readily it was abandoned when it became clear the work could be financially exploited.

By this measure, they shouldn’t even try to do good things in small pockets and probably should just optimize for profits!

Fortunately, many other people can deal with nuance.

Re: Unrolling the Codex agent loop

#137

Post by consumer451 »

behnamoh wrote: post #127
mi_lk wrote: post #73

Earlier quoted context omitted.

Same. If you're already using a proprietary model might as well just double down

until Microsoft buys it and enshits it.

This is a fun thought experiment. I believe that we are now at the $5 Uber (2014) phase of LLMs. Where will it go from here?

How much will a synthetic mid-level dev (Opus 4.5) cost in 2028, after the VC subsidies are gone? I would imagine as much as possible? Dynamic pricing?

Will the SOTA model labs even sell API keys to anyone other than partners/whales? Why even that? They are the personalized app devs and hosts!

Man, this is the golden age of building. Not everyone can do it yet, and every project you can imagine is greatly subsidized. How long will that last?

Re: Unrolling the Codex agent loop

#138

Post by EnPissant »

nubg wrote: post #122
icelancer wrote: post #72

Earlier quoted context omitted.

Their compaction endpoint is far and away the best in the industry. Claude's has to be dead last.

Help me understand, how is a compaction endpoint not just a Prompt + json_dump of the message history? I would understand if the prompt was the secret sauce, but you make it sound like there is more to a compaction system than just a clever prompt?

Maybe it's a model fine tuned for compaction?

Re: Unrolling the Codex agent loop

#139

Post by copperx »

behnamoh wrote: post #47
copperx wrote: post #29

Earlier quoted context omitted.

When you say CC is it Codex CLI or Claude Code?

claude code

If I understand correctly, you're using CC with an OpenAI API key, right?

CC doesn't support it natively, so I'm assuming is some sort of mod, and it still outclasses Opus? That's interesting.

Do you mind sharing what tool/mod you are using?

Re: Unrolling the Codex agent loop

#140

Post by copperx »

behnamoh wrote: post #49
wahnfrieden wrote: post #39

Earlier quoted context omitted.

No, the codex harness is also optimized for the codex models. Highly recommend using first-party OpenAI harnesses for codex.

I used that too, but CC currently has features like hooks that codex team has refused to add far too many times.

Hmm, this seems promising?

https://github.com/openai/codex/pull/9796

Post reply on HN