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

GPT-5-Codex

openai.com

Post reply on HN
Print view View original

131–140 of 144 posts

Re: GPT-5-Codex

#131

Post by haarts »

supermatt wrote: post #130

I thought i would give this AI assisted coding another go, so have subscribed to ChatGPT to try out this new codex, but it just seems soooooo slooooow. I just don't see how this can be considered productive - I am waiting 20 minutes staring at it "thinking" while it does trivial tasks on a virtually bare repo. I guess for async agents its not such a big deal if they are slow as molasses, as you can run dozens of them…

What I see most engineers do is parallelize. Have multiple agents work at the same time. It takes some time getting used to, but I think they are on to something.

There's even an article I read about this the other week, but I can't seem to find it ATM.

Re: GPT-5-Codex

#132

Post by malyk »

haarts wrote: post #131
supermatt wrote: post #130

I thought i would give this AI assisted coding another go, so have subscribed to ChatGPT to try out this new codex, but it just seems soooooo slooooow. I just don't see how this can be considered productive - I am waiting 20 minutes staring at it "thinking" while it does trivial tasks on a virtually bare repo. I guess for async agents its not such a big deal if they are slow as molasses, as you can run dozens of them…

What I see most engineers do is parallelize. Have multiple agents work at the same time. It takes some time getting used to, but I think they are on to something. There's even an article I read about this the other week, but I can't seem to find it ATM.

Right. The idea here is to kick of 3-8 or something tasks. They finish as you finish writing the next prompt. Then you go and review/test/merge the code from the first task, then another task finishes and you review/test/merge that code.

The challenge is that you have to be working on multiple work streams at once because so far Codex isn't great at not doing work you are doing in another task even if you tell it something like "class X will have a function that returns y"...it will go write that function most times.

I've found it really good for integration work between frontend and backend features where you can iterate on both simultaneously if the code isn't in the same codebase.

Also, for Codex this works best in the web ui because it actually uses branches, opens prs, etc. I think (though could be wrong) that locally with the CLI or IDE extension you might have to manually great git worktrees, etc.

Re: GPT-5-Codex

#133

Post by maximamas »

malyk wrote: post #132
haarts wrote: post #131

Earlier quoted context omitted.

What I see most engineers do is parallelize. Have multiple agents work at the same time. It takes some time getting used to, but I think they are on to something. There's even an article I read about this the other week, but I can't seem to find it ATM.

Right. The idea here is to kick of 3-8 or something tasks. They finish as you finish writing the next prompt. Then you go and review/test/merge the code from the first task, then another task finishes and you review/test/merge that code. The challenge is that you have to be working on multiple work streams at once because so far Codex isn't great at not doing work you are doing in another task even if you tell it som…

Yeah I try to keep it away from overlapping it's work as much as possible. Using plan mode in claude or just telling codex to build a plan, that is structured in a parallelized way for multiple agents usually helps delegate tasks to be handled at the same time. Typically: app code, infra, and data layer are the main three, but obviously depends on the project.

If I ever find my self just waiting, then it always gives me an opportunity to respond to messages, emails, or update tickets. Won't be long now until the agents are doing that as well...

Re: GPT-5-Codex

#134

Post by supermatt »

haarts wrote: post #131
supermatt wrote: post #130

I thought i would give this AI assisted coding another go, so have subscribed to ChatGPT to try out this new codex, but it just seems soooooo slooooow. I just don't see how this can be considered productive - I am waiting 20 minutes staring at it "thinking" while it does trivial tasks on a virtually bare repo. I guess for async agents its not such a big deal if they are slow as molasses, as you can run dozens of them…

What I see most engineers do is parallelize. Have multiple agents work at the same time. It takes some time getting used to, but I think they are on to something. There's even an article I read about this the other week, but I can't seem to find it ATM.

I can understand how you can parallelize tasks when there is some structure - but how do you get to that initially structured state where each agent isn't recreating the world to conflict with every other agent?

When i use that approach I end up merging one PR, then have to prod the others to fix themselves - resolving conflicts, removing duplicate code, etc - so it ends up slower than just running one agent at a time.

Like i said - maybe this is a problem on a bare repo? But if so, how are people vibe coding from scratch and calling themselves productive? I just don't get it.

Re: GPT-5-Codex

#135

Post by hayd »

king_magic wrote: post #129
SyrupThinker wrote: post #103

Earlier quoted context omitted.

Please tell me you are not running a NodeJS release that hasn't been supported for at least 3 years... Optional chaining was added in v14 (2020), and it sure looks like that is the issue here.

Brand new, clean install of npm. Poor code + doc hygiene is the problem here.

The question is which version of node, not npm.

Re: GPT-5-Codex

#136

Post by animegolem »

Turskarama wrote: post #60
jumploops wrote: post #30

Earlier quoted context omitted.

Yes, given a similarly sparse prompt, Claude Code seems to perform "better" because it eagerly does things you don't necessarily know to ask GPT-5 may underwhelm with the same sparse prompt, as it seems to do exactly what's asked, not more You can still "fully vibe" with GPT-5, but the pattern works better in two steps: 1. Plan (iterate on high-level spec/PRD, split into actions) 2. Build (work through plans) Splitti…

The best of both worlds would surely be for the LLM to write what you've asked, but also write comments about other things it could have done so you can consider those extra bits when you check the output.

I've found if you prompt a persona with these expectations GPT is pretty good at honoring it.

Re: GPT-5-Codex

#137

Post by dns_snek »

theshrike79 wrote: post #96
klipklop wrote: post #36

From my observation of the past 2 weeks is that Claude Code is getting dramatically worse and super low usage quota's while OpenAI Codex is getting great and has a very generous usage quota in comparison. For people that have not tried it in say ~1 month, give Codex CLI a try.

Does it still go "your project is using git, let me just YOLO stuff" on first startup? My essentials for any coding agent are proper whitelists for allowed commands (you can run uv run , but rm requires approval every time) and customisable slash commands. I can live without hooks and subagents.

> proper whitelists for allowed commands (you can run uv run , but rm requires approval every time)

This is a nearly impossible problem to solve.

uv run rm *

Sandboxing and limiting its blast radius is the only reliable solution. For more inspiration: https://gtfobins.github.io/

Re: GPT-5-Codex

#138

Post by groby_b »

artemisart wrote: post #54
groby_b wrote: post #47

Earlier quoted context omitted.

Small suggestion on refactors into packages: Move the files manually. Just tell codex "they used to be in different locations, fix it up so it builds". It seems that the concept of file moving isn't something Codex (and other clis) handle well yet. (Same goes for removing. I've ~never seen success in tracking moves and removes in the git commit if I ask for one)

Does refactoring mean moving things around for people? Why don't you use your IDE for this, it already handles fixing imports (or use find-replace) and it's faster and deterministic.

Not always, but since OP mentioned it was "deleting and rewriting" files - that's how the CLI agents usually "move" files.

And sure, you can use an IDE, but that's harder to do if you live in vibe land. (We really need to understand that for some things, we have perfectly fine non-AI answers, but that's not the world as it is right now. Mechanical refactors, move + import fixes, autocomplete - all of those do not require an LLM. We're not great at drawing that line yet)

Re: GPT-5-Codex

#140

Post by holoduke »

gosasan wrote: post #125

I’ve been using Claude Code ($20/month) for about two weeks now, and with one of the token usage monitors I can handle most of what I need. I also have the $20/month ChatGPT plan. I know I could try Codex CLI, but I’ve been hesitant since I’ve seen people suddenly hit the limit and get locked out for a week. The problem is that there’s no way to check usage. So I’m wondering if this update improves token usage manage…

Same setup as your. Started with codex 2 days ago on a large 3d engine project. Spend at least 20 hours prompting. One time I received a message. Try again in 4 minutes. I generally let Gemini create a prompt and then paste it inside codex. For example is asked gemeni to make a plan for a subdivided lod terrain render with shadow map functionality etc. It took codex almost an hour to execute it. Did an alright job. Quite impressed.
Post reply on HN