Most active commenters
  • KaiserPro(3)
  • rowanG077(3)

←back to thread

A Research Preview of Codex

(openai.com)
511 points meetpateltech | 12 comments | 16 May 25 15:02 UTC | HN request time: 2.182s | source | bottom
Show context
johnjwang ◴[16 May 25 16:27 UTC] No.44007301[source]▶
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 a bunch of tasks at the same time (something that's really hard to do in Cursor, Cline, etc.)

It kind of feels like a junior engineer on steroids, you just need to point it at a file or function, specify the change, and it scaffolds out most of a PR. 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.

Model quality is good, but hard to say it's that much better than other models. In side-by-side tests with Cursor + Gemini 2.5-pro, naming, style and logic are relatively indistinguishable, so quality meets our bar but doesn’t yet exceed it.

replies(15): >>44007420 #>>44007425 #>>44007552 #>>44007565 #>>44007575 #>>44007870 #>>44008106 #>>44008575 #>>44008809 #>>44009066 #>>44009783 #>>44010245 #>>44012131 #>>44014948 #>>44016788 #
hintymad ◴[16 May 25 19:38 UTC] No.44009066[source]▶
It looks we are in this interesting cycle: millions of engineers contribute to open-source on github. The best of our minds use the code to develop powerful models to replace exactly these engineers. In fact, the more code a group contributes to github, the easier it is for the companies to replace this group. Case in point, frontend engineers are impacted most so far.

Does this mean people will be less incentivized to contribute to open source as time goes by?

P.S., I think the current trend is a wakeup call to us software engineers. We thought we were doing highly creative work, but in reality we spend a lot of time doing the basic job of knowledge workers: retrieving knowledge and interpolating some basic and highly predictable variations. Unfortunately, the current AI is really good at replacing this type of work.

My optimistic view is that in long term we will have invent or expand into more interesting work, but I'm not sure how long we will have to wait. The current generation of software engineers may suffer high supply but low demand of our profession for years to come.

replies(7): >>44009132 #>>44009257 #>>44009278 #>>44009984 #>>44010148 #>>44011796 #>>44051842 #
Daishiman ◴[16 May 25 19:44 UTC] No.44009132[source]▶
> P.S., I think the current trend is a wakeup call to us software engineers. We thought we were doing highly creative work, but in reality we spend a lot of time doing the basic job of knowledge workers: retrieving knowledge and interpolating some basic and highly predictable variations. Unfortunately, the current AI is really good at replacing this type of work.

Most of the waking hours of most creative work have this type of drudgery. Professional painters and designers spend most of their time replicating ideas that are well fleshed-out. Musicians spend most of their time rehearsing existing compositions.

There is a point to be made that these repetitive tasks are a prerequisite to come up with creative ideas.

replies(1): >>44009350 #
rowanG077 ◴[16 May 25 20:07 UTC] No.44009350[source]▶
I disagree. AI have shown to most capable in what we consider creative jobs. Music creation, voice acting, text/story writing, art creation, video creation and more.
replies(2): >>44009527 #>>44009986 #
1. KaiserPro ◴[16 May 25 21:37 UTC] No.44009986[source]▶
> 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 that.

Its currently slightly more configurable clipart.

replies(2): >>44010422 #>>44014848 #
2. rowanG077 ◴[16 May 25 22:42 UTC] No.44010422[source]▶
> AI creates novel algorithms beating thousands of googlers.

Random HNer on an AI post one day later

> Its currently slightly more configurable clipart.

It's so ridiculous at this point that I can just laugh about this.

replies(3): >>44010949 #>>44011723 #>>44012680 #
3. ◴[17 May 25 00:14 UTC] No.44010949[source]▶
4. voidspark ◴[17 May 25 03:01 UTC] No.44011723[source]▶
Comparing music and algorithms is nonsense.

AI music is disposable generic soulless trash, even if it is technically correct, in accordance with the rules and conventions of music theory. AI generates Muzak. Totally generic and derivative.

There is no AI equivalent to Kurt Cobain, or James Brown, or Tori Amos.

replies(1): >>44018691 #
5. KaiserPro ◴[17 May 25 07:31 UTC] No.44012680[source]▶
Two people from different backgrounds have differing opinions on different systems.

This just in, the response was also to an entirely different context.

> rowanG077: Holy shit look how different the opinions are! LOL HN is so wild.

6. brookst ◴[17 May 25 15:04 UTC] No.44014848[source]▶
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.
replies(4): >>44014896 #>>44016132 #>>44016623 #>>44029911 #
7. krapp ◴[17 May 25 15:10 UTC] No.44014896[source]▶
The difference, of course, being that synthesizers and drum machines are instruments that require actual skill and talent and can be used to express the unique musical style of an artist, whereas AI requires neither skill nor talent, and it cannot generate anything with actual artistic direction, intent or innovation, much less a unique creative style.

AI is never going to give the world a modern Kraftwerk or Silver Apples or Brian Eno. The best an AI "artist" can do is have the machine mimic them.

replies(1): >>44022014 #
8. voidspark ◴[17 May 25 18:38 UTC] No.44016132[source]▶
Those are instruments played and sequenced by humans. Meaningless comparison.
9. KaiserPro ◴[17 May 25 20:05 UTC] No.44016623[source]▶
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.

10. rowanG077 ◴[18 May 25 03:02 UTC] No.44018691{3}[source]▶
There is no AI equivalent to Kurt Cobain or any other artists because 99% of what they are is not at all about their musical skill but all about marketing. There are thousands of musicians just as skilled if not more than Kurt Cobain or James Brown yet who don't have their fame. I also have no doubt an AI will outperform most musicians in short order in the foreseeable future. The step from making no music at all, to making acceptable music is gigantic compared to making acceptable music to making great music.
replies(2): >>44018747 #>>44018756 #
11. brookst ◴[18 May 25 15:18 UTC] No.44022014{3}[source]▶
Still the same thing. The argument then was that synths weren’t “real instruments” and that sequencers meant people weren’t “real musicians”.

AI relies on prompting. In the hands of a skilled artist it is just another tool. In the hands of an amateur hack, it is no different than giving a drum kit to a 4 year old.

The tool is not the art. It never was.

12. tom_m ◴[19 May 25 13:50 UTC] No.44029911[source]▶
They were right in many cases. You can choose to pick out the small percentage of musicians who were successful there or you can recognize the many that were never known.

You can do the same for photography.

People keep lowering expectations or demands on quality because things get easier and humans always prefer the easy option.