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

151–160 of 487 posts

Re: A Research Preview of Codex

#151

Post by DGAP »

criddell wrote: post #112
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…

If you aren't hiring junior engineers to do these kinds of things, where do you think the senior engineers you need in the future will come from? My kid recently graduated from a very good school with a degree in computer science and what she's told me about the job market is scary. It seems that, relatively speaking, there's a lot of postings for senior engineers and very little for new grads. My employer has hired…

There aren't going to be senior engineers in the future.

Re: A Research Preview of Codex

#152

Post by asdev »

alvis wrote: post #35

I used to work for a bank and the legal team used to ping us to make tiny changes to the app for compliance related issues. Now they can fix themselves. I think they’d be very proud and happy

I promise you the legal team is not pushing any code changes

Re: A Research Preview of Codex

#153

Post by HappMacDonald »

rfoo wrote: post #108
fourside wrote: post #89

Earlier quoted context omitted.

> You still need to do a lot of work to get it production ready, but it's as if you have an infinite number of junior engineers at your disposal now all working on different things. One issue with junior devs is that because they’re not fully autonomous, you have to spend a non trivial amount of time guiding them and reviewing their code. Even if I had easy access to a lot of them, pretty quickly that overhead would…

You don't need to be nice to your virtual junior devs. Saves quite a lot time too. As long as I spend less time reviewing and guiding than doing it myself it's a win for me. I don't have any fun doing these things and I'd rather yelling at a bunch of "agents". For those who enjoy doing bunch of small edits I guess it's the opposite.

I'm definitely wary of the concept of dismissing courtesy when working with AI agents, because I certainly don't want to lose that habit when I turn around and have to interact with humans again.

Re: A Research Preview of Codex

#155

Post by _bin_ »

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…

I believe cursor now supports parallel tasks, no? I haven't done much with it personally but I have buddies who have.

If you want one idiot's perspective, please hyper-focus on model quality. The barrier right now is not tooling, it's the fact that models are not good enough for a large amount of work. More importantly, they're still closer to interns than junior devs: you must give them a ton of guidance, constant feedback, and a very stern eye for them to do even pretty simple tasks.

I'd like to see something with an o1-preview/pro level of quality that isn't insanely expensive, particularly since a lot of programming isn't about syntax (which most SotA modls have down pat) but about understanding the underlying concepts, an area in which they remain weak.

Atp I really don't care if the tooling sucks. Just give me really, really good mdoels that don't cost a kidney.

Re: A Research Preview of Codex

#156

Post by _bin_ »

criddell wrote: post #112
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…

If you aren't hiring junior engineers to do these kinds of things, where do you think the senior engineers you need in the future will come from? My kid recently graduated from a very good school with a degree in computer science and what she's told me about the job market is scary. It seems that, relatively speaking, there's a lot of postings for senior engineers and very little for new grads. My employer has hired…

This is a bit of a game theory problem. "Training senior engineers" is an expensive and thankless task: you bear essentially all the cost, and most of the total benefit accrues to others as a positive externality. Griping at companies that they should undertake to provide this positive externality isn't really a constructive solution.

I think some people are betting on the fact that AI can replace junior devs in 2-5 years and seniors in 10-20, when the old ones are largely gone. But that's sort of beside the point as far as most corporate decision-making.

Re: A Research Preview of Codex

#157

Post by asdev »

is the point of this to actually assign tasks to an AI to complete end to end? Every task I do with AI requires atleast some bit of hand holding, sometimes reprompting etc. So I don't see why I would want to run tasks in parallel, I don't think it would increase throughput. Curious if others have better experiences with this

Re: A Research Preview of Codex

#158

Post by lurking_swe »

piskov wrote: post #128
bionhoward wrote: post #121

What about privacy, training opt out? What about using it for AI / developing models that compete with our new overlords? Seems like using this is just asking to get rug pulled for competing with em when they release something that competes with your thing. Am I just an old who’s crowing about nothing? It’s ok for them to tell us we own outputs we can’t use to compete with em?

What the video: there is an explicit switch at one of the steps about (not) allowing to train on your repo.

That’s nice. And we trust that it does what it says because…? The AI company (openai, anthropic, etc) pinky promised? Have we seen their source code? How do you know they don’t train?

Facebook has been caught in recent DOJ hearings breaking the law with how they run their business, just as one example. They claimed under oath, previously, to not be doing X, and then years later there was proof they did exactly that.

https://youtu.be/7ZzxxLqWKOE?si=_FD2gikJkSH1V96r

A companies “word” means nothing imo. None of this makes sense if i’m being honest. Unless you personally have a negotiated contract with the provider, and can somehow be certain they are doing what they claim, and can later sue for damages, all of this is just crossing your fingers and hoping for the best.

Re: A Research Preview of Codex

#159

Post by tough »

ai-christianson wrote: post #149
tough wrote: post #139

Earlier quoted context omitted.

automated visual fuzzy-testing with some self-reinforcement loops There's already library's for QA testing and VLM's can give critique on a series of screenshots automated by a playwright script per branch

Cool. Putting vision in the loop is a great idea. Ambitious idea, but I like it.

SmolVLM, Gemma, LlaVa, in case you wanna play with some of the ones i've tried.

https://huggingface.co/blog/smolvlm

recently both llama.cpp and ollama got better support for them too, which makes this kind of integration with local/self-hosted models now more attainable/less expensive

Re: A Research Preview of Codex

#160

Post by tough »

lurking_swe wrote: post #158
piskov wrote: post #128

Earlier quoted context omitted.

What the video: there is an explicit switch at one of the steps about (not) allowing to train on your repo.

That’s nice. And we trust that it does what it says because…? The AI company (openai, anthropic, etc) pinky promised? Have we seen their source code? How do you know they don’t train? Facebook has been caught in recent DOJ hearings breaking the law with how they run their business, just as one example. They claimed under oath, previously, to not be doing X, and then years later there was proof they did exactly that.…

On the other hand you can enable explicit sharing of your data and get a few million free tokens daily
Post reply on HN