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

131–140 of 487 posts

Re: A Research Preview of Codex

#131

Post by tough »

jiocrag wrote: post #92
tough wrote: post #34

so i just upgraded to pro plan but yet https://chatgpt.com/codex doesnt work for me and asks me to -try chatgpt pro- and shows me the upsell modal, even if already on the higher tier sigh

same here. Paying for Pro ($200) but the "try it" link just leads to the Pro sign up page, where it says I'm already on Pro. Hyper intelligent coding agents, but can't make their website work.

> Hyper intelligent coding agents, but can't make their website work.

I know right

also no human to contact on support... tempted to cancel the sub lol i'll give them 24h

Re: A Research Preview of Codex

#132

Post by tough »

tptacek wrote: post #103
fabmilo wrote: post #88

Earlier quoted context omitted.

more excited about the rust impl than the typescript one.

Besides packaging of their releases, what possible difference could that make in this problem domain?

I just think it's nice to have open source code to reference so maybe he meant just in that -educational- way, certainly more to learn from the rust one than the TS one for most folks? even if the problem-space doesn't require system-level safety code indeed

Re: A Research Preview of Codex

#133

Post by tough »

piskov wrote: post #130
fear91 wrote: post #97

Earlier quoted context omitted.

Same here, paying for Pro but I just get redirected to vanilla version...

> will be rolling ≠ available now to all pro users

ok but I baited the hook and now am waiting.

Every -big- release they gatekeep something to pro I pay for it like every 3 months, then cancel after the high

when will i learn

Re: A Research Preview of Codex

#134

Post by aorobin »

strangescript wrote: post #90
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…

it feels like openai are at a ceiling with their models, codex1 seems to be another RLHF derivative from the same base model. You can see this in their own self reported o3-high comparison where at 8 tries they converge at the same accuracy. It also seems very telling they have not mentioned o4-high benchmarks at all. o4-mini exists, so logically there is an o4 full model right?

Seems likely that they are waiting to release o4 full results until the gpt-5 release later this year, presumably because gpt-5 is bundled with a roughly o4 level reasoning capability, and they want gpt-5 to feel like a significant release.

Re: A Research Preview of Codex

#135

Post by ai-christianson »

nadis wrote: post #127

In the preview video, I appreciated Katy Shi's comment on "I think this is a reflection of where engineering work has moved over the past where a lot of my time now is spent reviewing code rather than writing it." Preview video from Open AI: https://www.youtube.com/watch?v=hhdpnbfH6NU&t=878s As I think about what "AI-native" or just the future of building software loos like, its interesting to me that - right now - d…

> rather than looking at simulations

You mean like automated test suites?

Re: A Research Preview of Codex

#136

Post by ai-christianson »

runako wrote: post #123
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…

> Parallel task execution: You can batch dozens of small edits (refactors, tests, boilerplate) and run them concurrently without context juggling. This is also part of a recent update to Zed. I typically use Zed with my own Claude API key.

Is Zed managing the containerized dev environments, or creating multiple worktrees or anything like that? Or are they all sharing the same work tree?

Re: A Research Preview of Codex

#137

Post by Snuggly73 »

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

Re: A Research Preview of Codex

#138

Post by runako »

ai-christianson wrote: post #136
runako wrote: post #123

Earlier quoted context omitted.

> Parallel task execution: You can batch dozens of small edits (refactors, tests, boilerplate) and run them concurrently without context juggling. This is also part of a recent update to Zed. I typically use Zed with my own Claude API key.

Is Zed managing the containerized dev environments, or creating multiple worktrees or anything like that? Or are they all sharing the same work tree?

As far as I know, they are sharing a single work tree. So I suppose that could get messy by default.

That said, it might be possible to tell each agent to create a branch and do work there? I haven't tried that.

I haven't seen anything about Zed using containers, but again you might be able to tell each agent to use some container tooling you have in place since it can run commands if you give it permission.

Re: A Research Preview of Codex

#139

Post by tough »

ai-christianson wrote: post #135
nadis wrote: post #127

In the preview video, I appreciated Katy Shi's comment on "I think this is a reflection of where engineering work has moved over the past where a lot of my time now is spent reviewing code rather than writing it." Preview video from Open AI: https://www.youtube.com/watch?v=hhdpnbfH6NU&t=878s As I think about what "AI-native" or just the future of building software loos like, its interesting to me that - right now - d…

> rather than looking at simulations You mean like automated test suites?

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

Re: A Research Preview of Codex

#140

Post by nluken »

ramoz wrote: post #64
skovati wrote: post #40

I'm curious how many ICs are truly excited about these advancements in coding agents. It seems to me the general trend is we become more like PMs managing agents and reviewing PRs, all for the sake of productivity gains. I imagine many engineers are like myself in that they got into programming because they liked tinkering and hacking and implementation details, all of which are likely to be abstracted over in this n…

I see it differently. Like a kid with legos. We had to tinker piece by piece to build a miniature castle. Over many hours. Now I can tinker concept by concept, and build much larger castles, much faster. Like waving a wand, seeing my thoughts come to fruition in near real time. No vanity lost in my opinion. Possibly more to be gained.

I think there's a disconnect between what you and the person you're replying to are defining as "tinkering". Your conception of it seems more focused on the end product when, to use your analogy, the original comment seems unconcerned with the size of castles.

If you derive enjoyment from actually assembling the castle, you lose out on that by using the wand that makes it happen instantly. Sure wand's castles may be larger, but you don't put a Lego castle together for the finished product.

Post reply on HN