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

A Research Preview of Codex

openai.com

Post reply on HN
Print view View original

441–450 of 487 posts

Re: A Research Preview of Codex

#441

Post by dragonwriter »

Wowfunhappy wrote: post #436
lispisok wrote: post #192

Earlier quoted context omitted.

As much as I support community developed software and "free as in freedom", "Open Source" got completely perverted into tricking people to work for free for huge financial benefits for others. Your comment is just one example of that. For that reason all my silly little side projects are now in private repos. I dont care the chance somebody builds a business around them is slim to none. Dont think putting a license w…

So let's say your side project improves your life by 5 happiness points. You have two options: --- OPTION A - Keep your project private. • You get five happiness points. --- OPTION B - Make your project public. • Other individuals may get a small number of happiness points. • A megacorp might turn your project into a major product without compensating you and get a million happiness points. • You get five happiness p…

This assumes that none of the effects of making a project public or private have any impact on the output of your personal utility function, which may be true for you personally, but certainly cannot validly be assumed to be generally true.

Re: A Research Preview of Codex

#442

Post by hmottestad »

fcoury wrote: post #410
solresol wrote: post #357

I'm not sure what's wrong with me, but I just wasted several hours wrestling codex to make it behave. Here's my workflow that keeps failing: - it writes some code. It looks good a first glance - I push it to github - automated tests on github show that there's a problem - go back to codex and ask it to fix it - it does stuff. It looks good again. Now what do I do? If I ask it to push again to github, then it will oft…

I upgraded to Pro just because of Codex and I am really not impressed. Granted, I am using rust so that may be the issue (or skill issue on my end too). One of the things I am constantly struggling with is that the containers they use are having issues to fetch anything from the internet: error: failed to get `anyhow` as a dependency of package `yawl-core v0.1.0 (/wor kspace/yawl/core)` Caused by: download of config.…

You can specify a startup script for your environment in the Edit -> adbvaned section. The code placed there will run before they cut off the internet access. Also worth noting that it uses a proxy stored in $http_proxy.

Took me an few hours today to figure out how to install maven and have it download all the dependencies. Spent an hour trying to figure out why sudo apt-get update was failing, it was because I was was using sudo!

Re: A Research Preview of Codex

#443

Post by ajkjk »

eru wrote: post #391
ajkjk wrote: post #91

Earlier quoted context omitted.

Hopefully nobody lets legal touch anything without the ability to run the code to test it, plus code reviews. So probably not.

I'm not sure what you are on about? You can make arbitrary teams, like legal, make PRs. You would still have the proper owners of the project agree whether they take the PRs. Either by human review and/or by any other review process they set up.

I am on about the fact that you are imagining something working in a way that it does not work in practice.

You have two choices:

1. A developer makes a PR. They build the app and run it themselves to make sure it works, does what they intended, and nothing unexpected happens, and report on their testing in the PR. There's also a suite of automated tests. Between these you are confident that you can rubber-stamp it without touching the change yourself. But this requires them being able to run the code and intelligently think about it themselves, which AI cannot do.

2. A non-developer uses an LLM to make a PR. The change passes the tests, but you have no other validation about it because it was done by a bot that can't think about how the app actually works. As reviewer you have to pull down the change to run and validate it yourself. Now you are doing the same amount of work as before, except that instead of you telling the LLM to make the change, someone else did.

The only difference is maybe that the activation energy for doing the work was avoided. Which, fine, is non-negligible. But let's not pretend like in the latter case legal "made the change". They did the 1% upfront work of asking the LLM to find where the change goes, and left you the other 99% of actually shepherding it through. The only changes that will work for at all are, like, updating copy/strings/icons---and honestly, at my last job at least, we already let legal (and product, etc) do stuff like that. I suppose the LLM might save them having to figure out how to use Git, at least.

You might imagine there's some software out there where the automated tests are so thorough that you can trust a code change to not break anything if it passes the tests. I have personally never seen such a thing. And in practice many tests validate against strings and other small feature-level details, meaning that the kinds of code changes that other orgs are making are going to be touching the tests as well, so human verification is still required.

Re: A Research Preview of Codex

#444

Post by voidspark »

brookst wrote: post #426
KaiserPro wrote: post #248

Earlier quoted context omitted.

> AI have shown to most capable in what we consider creative jobs no it creates shit thats close enough for people who are in a rush and dont care. ie, you need artwork for shit on temu, boom job done. You want to make a poster for a bake sale, boom job done. Need some free music that sounds close enough to be swifty, but not enough to get sued, great. But as an expression of creativity, most people cant get it to do…

Serious deja vu to the late 70’s and early 80’s when “real musicians” said exactly the same thing about synthesizers and drum machines.

Those are instruments played and sequenced by humans. Meaningless comparison.

Re: A Research Preview of Codex

#445

Post by KaiserPro »

brookst wrote: post #426
KaiserPro wrote: post #248

Earlier quoted context omitted.

> AI have shown to most capable in what we consider creative jobs no it creates shit thats close enough for people who are in a rush and dont care. ie, you need artwork for shit on temu, boom job done. You want to make a poster for a bake sale, boom job done. Need some free music that sounds close enough to be swifty, but not enough to get sued, great. But as an expression of creativity, most people cant get it to do…

Serious deja vu to the late 70’s and early 80’s when “real musicians” said exactly the same thing about synthesizers and drum machines.

Look, in the hands of a skilled artist, generative fill is really useful.

In the same way that the synth is superstitious is banging.

Sampling, when in the hands of a legend is also spectacular, see the prodigy and a break down of the samples they used. (or any half decent hiphop band)

Then you get akon who just sped up a single sample put a beat on it and shat out some halfarsed shit.

Re: A Research Preview of Codex

#446

Post by surgical_fire »

brookst wrote: post #425
lispisok wrote: post #192

Earlier quoted context omitted.

As much as I support community developed software and "free as in freedom", "Open Source" got completely perverted into tricking people to work for free for huge financial benefits for others. Your comment is just one example of that. For that reason all my silly little side projects are now in private repos. I dont care the chance somebody builds a business around them is slim to none. Dont think putting a license w…

Protect you from what? What harm is there to you if someone uses some of your code to build a business, as compared to not doing so? How are you worse off? I’ve never understood this mentality. It seems very zero sum and kind of anti social. I’ve built a couple of businesses, and there’s always economic or technical precedent. I honestly don’t mind paying it forward if someone can benefit from side projects I enjoyed…

> What harm is there to you if someone uses some of your code to build a business, as compared to not doing so? How are you worse off?

This someone might be someone I dislike. It would cause me some mild annoyance that they benefited from my effort.

Re: A Research Preview of Codex

#447

Post by surgical_fire »

johnjwang wrote: post #80

Some engineers on my team at Assembled and I have been a part of the alpha test of Codex, and I'll say it's been quite impressive. We’ve long used local agents like Cursor and Claude Code, so we didn’t expect too much. But Codex shines in a few areas: Parallel task execution: You can batch dozens of small edits (refactors, tests, boilerplate) and run them concurrently without context juggling. It's super nice to run…

What kind of Junior devs are you people hiring that you still need to do a lot of work to get it production ready?

I work with Junior devs. They are Junior in that they have to be pointed in the direction they must work, and would be out of their depth in guiding the implementation of major features. But simple code changes are pretty fine.

LLMs are useful, I kind of like them as code assistants, but they are very far of being even a Junior dev in terms of actually performing work.

Re: A Research Preview of Codex

#448

Post by mullingitover »

lispisok wrote: post #439
Wowfunhappy wrote: post #436

Earlier quoted context omitted.

So let's say your side project improves your life by 5 happiness points. You have two options: --- OPTION A - Keep your project private. • You get five happiness points. --- OPTION B - Make your project public. • Other individuals may get a small number of happiness points. • A megacorp might turn your project into a major product without compensating you and get a million happiness points. • You get five happiness p…

You really dont see why somebody wouldnt like a megacorp to take their hard work, use it to make a billion dollars, dont see a cent themselves, while struggling to buy a house in this very unaffordable housing market? https://knowyourmeme.com/memes/total-happiness-in-the-world-...

Google, Microsoft, Meta, IBM, Red Hat, etc. are huge players in open source, they probably contribute significantly more hours of work in building and maintaining major open source projects than the hobbyists.

Not that hobbyists don't contribute, but these models are certainly being trained on the work of salaried engineers as much as their trained on hobbyists' spare time projects.

Re: A Research Preview of Codex

#449

Post by genewitch »

virgildotcodes wrote: post #435
roflyear wrote: post #419

Earlier quoted context omitted.

"After a couple of million suggestions and a few dozen repetitions of the overall process" How much of it is brute force?

Are we maybe moving the goalposts here? How much of human creativity is brute force?

Marble sculptures, that's what I came up with.

Re: A Research Preview of Codex

#450

Post by kristianp »

Snuggly73 wrote: post #137
ofirpress wrote: post #125

[I'm one of the co-creators of SWE-bench] The team managed to improve on the already very strong o3 results on SWE-bench, but it's interesting that we're just seeing an improvement of a few percentage points. I wonder if getting to 85% from 75% on Verified is going to take as long as it took to get from 20% to 75%.

I can be completely off base, but it feels to me like benchmaxxing is going on with swe-bench. Look at the results from multi swe bench - https://multi-swe-bench.github.io/#/ swe polybench - https://amazon-science.github.io/SWE-PolyBench/ Kotlin bench - https://firebender.com/leaderboard

Maybe a lot of the difference we see between peoples comments about how useful AI is for their coding, is a function of what language they're using. Python coders may love it, Go coders not much at all.
Post reply on HN