[HN Gopher] The Codex App
___________________________________________________________________
The Codex App
Author : meetpateltech
Score : 430 points
Date : 2026-02-02 18:02 UTC (4 hours ago)
(HTM) web link (openai.com)
(TXT) w3m dump (openai.com)
| drcongo wrote:
| > We're also excited to show more people what's now possible with
| Codex . For a limited time we're including Codex with ChatGPT
| Free and Go, and we're doubling the rate limits on Plus, Pro,
| Business, Enterprise, and Edu plans.
|
| Translated from Marketingspeak, this is presumably "we're also
| desperate for some people to actually use it because everyone
| shrugged and went back to Claude Code when we released it".
| embedding-shape wrote:
| I dunno, feels like the models have different weak/strong
| points, sometimes I can sit with Claude Code for an hour with
| some issue, try it with Codex and have it solved in five
| minutes, and also the opposite happens. I tend to use Codex
| mostly when I care more about correctness and not missing
| anything, Claude when it's more important I do it fast and I
| know exactly what it needs to do, Codex seems to require less
| hand-holding. Of course, just anecdotal.
| sigbottle wrote:
| GPT models definitely seem stronger when they "get it" and in
| the types of problems they "get", while claude seems more
| holistic but not "as smart" as some of the spikes GPT can
| get.
| MattDamonSpace wrote:
| They also claim 2x usage from December (though 2x a tiny amount
| is still a tiny amount)
| alansaber wrote:
| Yeah this is clearly just a marketing re-release but if they've
| executed well i'm happy to try it
| SunshineTheCat wrote:
| This does look like it would simplify some aspects of using Codex
| on Mac, however, when I first saw the headline I thought this was
| going to be a phone app. And that started running a whole list of
| ideas through my brain... :(
|
| But overall, looks very nice and I'm looking forward to giving it
| a try.
| tomashubelbauer wrote:
| I don't know why any frontier model lab can't ship a mobile app
| that doesn't use a cloud VM but is able to connect to your
| laptop/server and work against local files on there when on the
| same network (e.g.: on TailScale). Or even better act as a
| remote control for a harness running on that remote device, so
| you couldn't seamlessly switch between phone and laptop/server.
| kzahel wrote:
| I'm also so baffled by this. I had to write my own app to be
| able to do seamless handoff between my laptop/desktop/phone
| and it works for me (https://github.com/kzahel/yepanywhere -
| nice web interface for claude using their SDK, MIT, E2E relay
| included, no tailscale required) but I'm so baffled why this
| isn't first priority. Why all these desktop apps?
| geooff_ wrote:
| Having dictation and worktree support built in is nice. Currently
| there is a whole ecosystem of tools implementing similar
| functionality for Claude Code. The automations look cool too!
| strongpigeon wrote:
| Genuinely excited to try this out. I've started using Codex much
| more heavily in the past two months and honestly, it's been
| shockingly good. Not perfect mind you, but it keeps impressing me
| with what it's able to "get". It often gets stuff wrong, and at
| times runs with faulty assumptions, but overall it's no worse
| than having average L3-L4 engs at your disposal.
|
| That being said, the app is stuck at the launch screen, with
| "Loading projects..." taking forever...
|
| Edit: A lot of links to documentation aren't working yet. E.g.:
| https://developers.openai.com/codex/guides/environments. My
| current setup involves having a bunch of different environments
| in their own VMs using Tart and using VS Code Remote for each of
| them. I'm not married to that setup, but I'm curious how it
| handles multiple environments.
|
| Edit 2: Link is working now. Looks like I might have to tweak my
| setup to have port offsets instead of running VMs.
| SunshineTheCat wrote:
| Same here. From my experience, codex usually knocks
| backend/highly "logical?" tasks out of the park while fairly
| basic front-end/UI tasks it stumbles over at times.
|
| But overall it does seem to be consistently improving. Looking
| to see how this makes it easier to work with.
| xiphias2 wrote:
| Cool, looks like I'll stay on Cursor. All alternatives come out
| buggy, they care a lot about developer experience.
|
| BTW OpenAI should think a bit about polishing their main apps
| instead of trying to come out with new ones while the originals
| are still buggy.
| embirico wrote:
| (I work on Codex) One detail you might appreciate is that we
| built the app with a ton of code sharing with the CLI (as
| core agent harness) and the VSCode extension (UI layer), so
| that as we improve any of those, we polish them all.
| thefounder wrote:
| Any reason to switch from vscode with codex to this app? To
| me it looks like this app is more for non-developers but
| maybe I'm missing something
| romainhuet wrote:
| Good question! VS Code is still a great place for deep,
| hands-on coding with the Codex IDE extension.
|
| We built the Codex app to make it easier to run and
| supervise multiple agents across projects, let longer-
| running tasks execute in parallel, and keep a higher-
| level view of what's happening. Would love to hear your
| feedback!
| naiv wrote:
| ok , 'projects' but this would make a lot more sense if
| we could connect remotely to the projects which works
| without a problem using the IDE plugin, so right now I
| don't see any advantage of using this
| theLiminator wrote:
| Any chance you'll enable remote development on a self-
| hosted machine with this app?
|
| Ie. I think the codex webapp on a self-hosted machine would
| be great. This is impotant when you need a beefier machine
| (with potentially a GPU).
| strongpigeon wrote:
| Interested in this as well.
| naiv wrote:
| Working remotely with the app would truly be great
| tomjen3 wrote:
| Awesome. Any chance we will see a phone app?
|
| I know coding on a phone sounds stupid, but with an agent
| it's mostly approvals and small comments.
| strongpigeon wrote:
| The ChatGPT app on iOS has a Codex page, though it only
| seems to be for the "cloud" version.
| dkundel wrote:
| Hey thank you for calling out the broken link. That should be
| fixed now. Will make sure to track down the other broken links.
| We'll track down why loading is taking a while for you. Should
| definitely be snappier.
| wahnfrieden wrote:
| Is this the only announcement for Apple platform devs?
|
| I thought Codex team tweeted about something coming for Xcode
| users - but maybe it just meant devs who are Apple users, not
| devs working on Apple platform apps...
| raw_anon_1111 wrote:
| I have the $20 a month subscription for ChatGPT and the
| $200/year subscription to Claude (company reimbursed).
|
| I have yet to hit usage limits with Codex. I continuously reach
| it with Claude. I use them both the same way - hands on the
| wheel and very interactive, small changes and tell them both to
| update a file to keep up with what's done and what to do as I
| test.
|
| Codex gets caught in a loop more often trying to fix an issue.
| I tell it to summarize the issue, what it's tried and then I
| throw Claude at it.
|
| Claude can usually fix it. Once it is fixed, I tell Claude to
| note in the same file and then go back to Codex
| motbus3 wrote:
| I will say that doing small modifications or asking a bunch
| of stuff fills the context the same in my observations. It
| depends on your codebase and the rest of stuff you use (sub
| agents, skills, etc)
|
| I was once minimising the changes and trying to take the max
| of it. I did an uncountable numbers of tests and and
| variations. Didn't really matter much if I told it to do it
| all or change one line. I feel Claude code tries to fill the
| context as fast as possible anyway
|
| I am not sure how worth Claude is right now. I still prefer
| that rather than codex, but I am starting to feel that's just
| a bias
| girvo wrote:
| I don't think it's bias: I have no love for any of these
| tools, but in every evaluation we've done at work, Opus 4.5
| continually comes out ahead in real world performance
|
| Codex and Gemini are both good, but slower and less "smart"
| when it comes to our code base
| strongpigeon wrote:
| The trick to reach the usage limit is to run many agents in
| parallel. Not that it's an explicit goal of mine but I keep
| thinking of this blog post [0] and then try to get Codex to
| do as much for me as possible in parallel
|
| [0]: http://theoryofconstraints.blogspot.com/2007/06/toc-
| stories-...
| raw_anon_1111 wrote:
| Telling a bunch of agents to do stuff is like treating it
| as a senior developer who you trust to take an ambiguous
| business requirement and letting them use their best
| judgment and them asking you if they have a question .
|
| But doing that with AI feels like hiring an outsourcing
| firm for a project and they come back with an unmaintable
| mess that's hard to reason through 5 weeks later.
|
| I very much micro manage my AI agents and test and validate
| its output. I treat it like a mid level ticket taker code
| monkey.
| strongpigeon wrote:
| I fully believe that if I didn't review its output and
| ask it to clean it up it would become unmaintainable real
| quick. The trick I've found though is to be detailed
| enough in the design from both a technical and non-
| technical level, sometimes iterating a few time on it
| with the agent before telling it to go for it (which can
| easily take 30 minutes)
|
| That's how I used to deal with L4, except codex codes
| much faster (but sometimes in the wrong direction)
| raw_anon_1111 wrote:
| It's funny over the years I went from
|
| 1. I like being hands on keyboard and picking up a slice
| of work I can do by myself with a clean interface that
| others can use - a ticket taking code monkey.
|
| 2. I like being a team lead /architect where my vision
| can be larger than what I can do in 40 hours a week even
| if I hate the communication and coordination overhead of
| dealing with two or three other people
|
| 3. I love being able to do large projects by myself
| including dealing with the customer where the AI can do
| the grunt work I use to have to depend on ticket taking
| code monkeys to do.
|
| Moral of the story: if you are a ticket taking "I codez
| real gud" developer - you are going to be screwed no
| matter how many b trees you can reverse on the whiteboard
| AloysB wrote:
| Moral of _your_ story.
|
| Each and everyone of us is able to write their own story,
| and come up with their own 'Moral'.
|
| Settling for less (if AI is a productivity booster, which
| is debatable) doesn't equal being screwed. There is
| wisdom in reaching your 'enough' point.
| bonesss wrote:
| My experience with good outsourcing firms is that they
| come back with heavily-documented solutions that are 95%
| of what you actually wanted, leaving you uncomfortably
| wondering if doing it yourself woulda been better.
|
| I'm not fully sure what's worse, something close to
| garbage with a short shelf life anyone can see, or
| something so close to usable that it can _fully_ bite me
| in the ass...
| petesergeant wrote:
| I have a found Codex to be an exceptional code-reviewer of
| Claude's work.
| 650REDHAIR wrote:
| I hit the Claude limit within an hour.
|
| Most of my tokens are used arguing with the hallucinations.
|
| I've given up on it.
| TuxSH wrote:
| In my case I've had it (Opus Thinking in CC) hit 80% of the
| 5-hour limit and 100% of the context window with one single
| tricky prompt, only to end up with worthless output.
|
| Codex at least 'knows' to give up in half the time and
| 1/10th of the limits when that happens.
| hnsr wrote:
| Do you use Claude Code, or do you use the models from some
| other tool?
|
| I find it quite hard to hit the limits with Claude Code,
| but I have several colleagues complaining a lot about
| hitting limits and they use Cursor. Recently they also seem
| to be dealing with poor results (context rot?) a lot, which
| I haven't really encountered yet.
|
| I wonder if Claude Code is doing something smart/special
| theshrike79 wrote:
| I don't want to be That Guy, but if you're "arguing with
| hallucinations" with an AI Agent in 2026 you're either
| holding it wrong or you're working on something highly
| nonstandard.
| Areibman wrote:
| Your goal should be to run agents all the time, all in
| parallel. If you're not hitting limits, you're massively
| underutilizing the VC intelligence subsidy
|
| https://hyperengineering.bottlenecklabs.com/p/the-
| infinite-m...
| samuelstros wrote:
| It's basically what Emdash (https://www.emdash.sh/), Conductor
| (https://www.conductor.build/) & CO have been building but as
| first class product from OpenAI.
|
| Begs the question if Anthropic will follow up with a first-class
| Claude Code "multi agent" (git worktree) app themselves.
| FanaHOVA wrote:
| https://code.claude.com/docs/en/desktop
| samuelstros wrote:
| oh i didn't know that claude code has a desktop app already
| mcintyre1994 wrote:
| It isn't its own app, but it's built in to their desktop,
| mobile and web apps.
| esafak wrote:
| And it uses worktrees.
| IMTDb wrote:
| Maybe a dumb question on my side; but if you are using a GUI
| like emdash with Claude Code, are you getting the full claude
| code harness under the hood or are you "just" leveraging the
| model ?
| arnestrickmann wrote:
| Emdash is inducing CC, Codex, etc. natively. Therefore users
| are getting the raw version of each agent.
| atestu wrote:
| I can answer for Conductor: you're getting the full Claude
| Code, it's just a GUI wrapper on top of CC. It makes it easy
| to create worktrees (1 click) and manage them.
| heystefan wrote:
| I don't think this is true. Try running `/skills` or
| `/context` in both and you'll see.
| mritchie712 wrote:
| yeah, I wanted a better terminal for operating many TUI
| agent's at once and none of these worked because they all
| want to own the agent.
|
| I ended up building a terminal[0] with Tauri and xterm that
| works exactly how I want.
|
| 0 - screenshot:
| https://x.com/thisritchie/status/2016861571897606504?s=20
| asdev wrote:
| They have Claude Code web in research preview
| desireco42 wrote:
| I never heard of Emdash before and I am following on AI tools
| closely. It just shows you how much noise there is and how hard
| is to promote the apps. Emdash looks solid. I almost went to
| build something similar because I wasn't aware of it.
| another_twist wrote:
| I am not sure if multi agent approach is what it is hyped up to
| be. As long we are working on parallel work streams with
| defined contracts (say an agreed upon API def that backend
| implements and frontend uses), I'd assume that running
| independent agent coding sessions is faster and in fact more
| desirable so that neither side bends the code to comply with
| under specified contracts.
| sepositus wrote:
| Usually I find the hype is centered around creating software
| no one cares about. If you're creating a prototype for dozens
| of investors to demo - I seriously doubt you'd take the
| "mainstream" approach.
| miroljub wrote:
| Given the prevalence of Opencode and its ability to use any model
| and provider I don't see reason why would anyone bother with
| random vendors half-assed tools.
| TZubiri wrote:
| Are you calling OpenAI a random vendor?
|
| That's like calling Coca Cola a random beverage vendor
| spiderice wrote:
| For starters, money. There is no better value out there that
| I'm aware of than Claude Code Max. Claude Code also just works
| way better than Opencode, in my experience. Though I know there
| are those that have experienced the exact opposite.
| minimaxir wrote:
| The inclusion of a live vibe-coded game on the webpage is fun,
| except the game barely works and it's odd they didn't attempt
| _any_ polish /QA for what is ostensibly a PR announcement. It
| just adds more fuel to the fire to the argument that vibecoding
| results in AI slop.
| alansaber wrote:
| To be fair the premise is that they 1 shotted it. I'd just be
| suspicious if it were any better (the POC is that is just about
| works)
| guywithahat wrote:
| I agree, if it had been polished I would have not trusted the
| demo at all, the fact it shows what you can potentially
| expect from a one-shot is cooler.
| surrTurr wrote:
| - looks like OpenAIs answer to Claude Code Desktop / Cowork
|
| - workspace agent runner apps (like Conductor) get more and more
| obsolete
|
| - "vibe working" is becoming a thing - people use folder based
| agents to do their work (not just coding)
|
| - new workflows seem to be evolving into folder based workspaces,
| where agents can self-configure MCP servers and skills + memory
| files and instructions
|
| kinda interested to see if openai has the ideas & shipping power
| to compete with anthropic going forward; anthropic does not only
| have an edge over openai because of how op their models are at
| coding, but also because they innovate on workflows and ai
| tooling standards; openai so far has only followed in adoption
| (mcp, skills, now codex desktop) but rarely pushed the SOTA
| themselves.
| OkGoDoIt wrote:
| Also interesting that they are both only for macOS. I'm feeling
| a bit left out on the Windows and Linux side, but this seems
| like an ongoing trend.
| surrTurr wrote:
| my guess is that openai/anthropic employees work on macOS and
| mostly vibe code these new applications (be it Atlas browser
| or now Codex Desktop); i wouldn't be surprised if Codex
| Desktop was built in a month or less;
|
| linux / windows requires extra testing as well as some
| adjustments to the software stack (e.g. liquid glass only
| works on mac); to get the thing out the door ASAP, they
| release macos first.
| abshkbh wrote:
| We did train Codex models natively on Windows -
| https://openai.com/index/introducing-gpt-5-2-codex/ (and even
| 5.1-codex-max)
| hdjrudni wrote:
| I appreciate this (as a Windows user) but I'm also curious
| how necessary this was.
|
| Like I notice in Codex in PhpStorm it uses Get-Whatever
| style PowerShell commands but firstly, I have a perfectly
| working Git-Bash installed that's like 98% compatible with
| Linux and Mac. Could it not use that instead of being
| retrained on Windows-centric commands?
|
| But better yet, probably 95% of the commands it actually
| needs to run are like cat and ripgrep. Can't you just
| bundle the top 20 commands, make them OS-agnostic and train
| on that?
|
| The last tiny bit of the puzzle I would think is the stuff
| that actually is OS-specific, but I don't know what that
| would be. Maybe some differences in file systems,
| sandboxing, networking.
| scottyah wrote:
| A lot of companies that use Windows are likely to use
| Microsoft Office products, and they were all basically forced
| to sign a non-compete where they can't run other models- just
| copilot.
| RazerWazer wrote:
| I'm so sick and tired of the macOS elitism in the AI/LLM
| world.
| solomatov wrote:
| Is it open source? Do they disclose which framework they use for
| the GUI? Is it Electron or Tauri?
| surrTurr wrote:
| lol ofc not
|
| looks like the same framework they used to build chatgpt
| desktop (electron)
|
| edit - from another comment:
|
| > Hi! Romain here, I work on Codex at OpenAI. We totally hear
| you. The team actually built the app in Electron specifically
| so we can support Windows and Linux as well. We shipped macOS
| first, but Windows is coming very soon. Appreciate you calling
| this out. Stay tuned!
| xiphias2 wrote:
| I guess the next it was meant to happen...I tried Google's
| Antigravity and found it quite buggy.
|
| May give a go at this and Claude Code desktop as well, but Cursor
| guys are still working the hardest to keep themselves alive.
| fanyangxyz33 wrote:
| I really look forward to using this. I tried Codex first time
| yesterday and it was able to complete a task (i.e. drawing
| Penrose tilings) that Claude Code previously failed at. Also a
| little overwhelmed by all the new features that this app brings.
| I feel that I'm behind all the fancy new tools.
| joe8756438 wrote:
| Is there any marked difference or benefit over Claude Code?
| RA_Fisher wrote:
| It's possible to run up to 4 agents at once vs. Claude Code's
| single thread. Sometimes I'll find meaningful quality
| differences between what agents produce.
| joe8756438 wrote:
| Interesting. Has anyone found running multiple parallel
| agents useful in practice?
| esafak wrote:
| You'd save time compared with running them in serial
| obviously?
| xGrill wrote:
| Is this not just a skinned version of Goose:
| https://block.github.io/goose/
| cobolexpert wrote:
| In the end this and all other 89372304 AI projects are just
| OpenAPI/Anthropic API wrappers, but at least one has 1st party
| support which maybe gives it a slight advantage?
| falloutx wrote:
| they are all copies of each other. Did you expect them to build
| something completely new? Software Development is stuck in an
| AI hole where we only build AI features.
| simianwords wrote:
| I really want to like the native Mac app aesthetic but I kinda
| hate it. It screams minimalist but also clearly tells me it's not
| meant for a power user. That ruggedness and sensitivity is
| missing.
| asdev wrote:
| Built an open source lightweight version of this that works with
| any cli agent: https://github.com/built-by-as/FleetCode
| FergusArgyll wrote:
| > and we're doubling the rate limits on Plus, Pro, Business,
| Enterprise, and Edu plans.
|
| I love competition
| mdrzn wrote:
| Maybe it's because I'm not used to the flow, but I prefer to work
| directly on the machine where I'm logged in via ssh, instead of
| working "somewhere in a git tree", and then have to
| deploy/test/etc.
|
| Once this app (or a similar app by Anthropic) will allow me to
| have the same level of "orchestration" but on a remote machine,
| I'll test it.
| vzaliva wrote:
| How about us, Linux users? This is Mac only. Do they plan to
| support CLI version with all the features they are adding to
| desktop app?
| romainhuet wrote:
| Hi! Romain here, I work at OpenAI. The team actually built the
| Codex app in Electron so we can support both Windows and Linux
| very soon. Stay tuned!
| kurtis_reed wrote:
| Let me guess, you use MacOS yourself?
| goniszewski wrote:
| Guess MacOS gives you pass for early-access stuff, right? /s
|
| From a developer's perspective it makes sense, though. You can
| test experimental stuff where configurations are almost the
| same in terms of OS and underlying hardware, so no weird, edge-
| case bugs at this stage.
| wutwutwat wrote:
| not only is it mac only, it appears to be arm only as well. App
| won't launch on my intel mac
| Rudybega wrote:
| Yeah, I'm having the same issue. Disappointing limitations.
| barbazoo wrote:
| > "Localize my app and add the option to change units"
|
| To me this still feels like the wrong way to interact with a
| coding agent. Does this lead people to success? I've never seen
| it not go off the rails in some way unless you provide clear
| boundaries as to what the scope of the expected change is. It's
| gonna write code if you don't even want it to yet, it's gonna
| write the test first or the logic first, whichever you don't want
| it to do. It'll be much too verbose or much too hacky, etc.
| barbazoo wrote:
| And then
|
| > gh-address-comments address comments
|
| Inspiring stuff. I would love to be the one writing GH comments
| here. /s
|
| But maybe there's a complementary gh-leave-comments to have it
| review PRs for you too.
| pests wrote:
| I've had no issues with prompts like that. I use Cursor with
| their plan mode, so I get a nice markdown file to iterate on or
| edit myself before it actually does anything.
| the_sleaze_ wrote:
| 100%
|
| First phase: Plan. Mandatory to complete, as well as get AI
| feedback from a separate context or model. Iterate until
| complete.
|
| Only then move on to the Second Phase: make edits.
|
| Better planning == Better execution
| hobofan wrote:
| Until a few days ago (when I switched to Codex), I would
| have agreed. My workflow was "thoroughly written issues" ->
| plan -> implement. Without the plan step, there is a high
| likelyhood that Claude Code (both normal or with GLM-4.7)
| or Cursor drift off in a wrong direction.
|
| With Codex, I increasingly can skip the plan step, and it
| just toils along until it has finished the issue. It can be
| more "lazy" at times and ask before going ahead more often,
| but usually in a reasonable scope (and sometimes at points
| where I think other services would have gone ahead on a
| wrong tangent and burnt more tokens of their more limited
| usage).
|
| I wouldn't be surprised that with the next 1-2 model
| iterations a plan step won't be worth the effort anymore,
| given a good enough initial written issue.
| pests wrote:
| I still use tons of non-plan mode edits with cursor too.
| The example prompt above I'd plan it out first just to
| make sure it does it in a way I want since I personally
| know there are tons of ways to implement it. But for
| simple changes or when I don't want a plan on purpose I
| just use a normal agent.
| rdn wrote:
| The better models can handle that prompt assuming there is an
| existing clean codebase and the scope of the task is not too
| large. The existing code can act as an implicit boundary.
|
| Weaker models give your experience, or when using a 100% LLM
| codebase I think it can end up in a hall of mirrors.
|
| Now I have an idea to try, have a 2nd LLM processing pass that
| normalizes the vibe-code to some personal style and standard to
| break it out of the Stack Overflow snippet maze it can get
| itself in.
| aed wrote:
| I typically bounce between Claude Code and Codex for the same
| project, and generally enjoy using both to check each other.
|
| One cool thing about this: upon installing it immediately found
| all previous projects I've used with Codex and has those projects
| in the sidebar with all of the "threads" (sessions) I've had with
| Codex on these projects!
| ngrilly wrote:
| Currently using opencode with Codex 5.2 and wondering why I
| should switch.
| oneneptune wrote:
| I'm a Claude Code user primarily. The best UI based orchestrator
| I've used is Zenflow by Zencoder.ai -- I am in no way affiliated
| with them, but their UI / tool can connect to any model or
| service you have. They offer their own model but I've not used
| it.
|
| What I like is that the sessions are highly configurable from
| their plan.md which translates a md document into a process. So
| you can tweak and add steps. This is similar to some of the other
| workflow tools I've seen around hooks and such -- but presented
| in a way that is easy for me to use. I also like that it can
| update the plan.md as it goes to dynamically add steps and even
| add "hooks" as needed based on the problem.
| sepositus wrote:
| Always sounds so interesting and then I do a search only to
| found out it's another product trying to sell you your 20th "AI
| credit package." I really don't see how these apps will last
| that long. I pay for the big three already - and no I don't
| want to cancel them just so I can use your product.
| cactusplant7374 wrote:
| Aren't there 500+ aggregator services?
| sergiotapia wrote:
| No Linux support? :(
| oompydoompy74 wrote:
| Looks like they forgot the part of the code editor where you
| can... edit code. Claude Code in Zed is about the most optimal
| experience I can imagine. I want the agent on the side and a code
| editor in the middle.
| elAhmo wrote:
| Usage like this is becoming a rarity. Most people are editing
| significantly less and "agent interfaces" are slowly taking the
| focus.
| verdverm wrote:
| "most" people aren't even using AI yet
|
| Of those that are, most are not vibe coding, so an editor is
| still required at many points
| ativzzz wrote:
| For greenfield apps you can vibecode it. For existing complex
| apps, where existing products where customers pay us a lot of
| money for working software, understanding the changes and
| context surrounding them in the code is critical or else
| nobody knows how the system works anymore and maintenance and
| support becomes impossible.
| hmate9 wrote:
| That's not really a negative for me as I can easily jump into
| vscode where I already have my workspace for coding set up
| exactly as I like it. This being a completely separate app just
| to get the agentic work right is a good direction imo
| falloutx wrote:
| Yeah but its annoying to find the file the agent just edited
| without any IDE/editor integration, you have to add that
| command which opens the file in vscode after editing.
| layer8 wrote:
| It would be nice to have an integrated development
| environment.
| hdjrudni wrote:
| How dare you want your IDE to be integrated!
| mellosouls wrote:
| Mac only. _Again_.
|
| Apple is great but this is OpenAI devs showing their disconnect
| from the mainstream. Its complacent at best, contemptuous at
| worst.
|
| SamA or somebody really needs to give the product managers here a
| kick up the arse.
| dkundel wrote:
| Windows is almost ready. It's already running but we are
| solving a few more things before the release to make sure it
| works well.
| romainhuet wrote:
| Hi! Romain here, I work on Codex at OpenAI. We totally hear
| you. The team actually built the app in Electron specifically
| so we can support Windows and Linux as well. We shipped macOS
| first, but Windows is coming very soon. Appreciate you calling
| this out. Stay tuned!
| embirico wrote:
| Only thing i'd add re windows is it's taking us some time to
| get really solid sandboxing working on Windows, where there
| are fewer OS-level primitives for it. There's some more at
| https://developers.openai.com/codex/windows and we'd love
| help with testing and feedback to make it robust.
| Oras wrote:
| Curios why electron not native?
|
| Wouldn't native give better performance and more system
| integration?
| ForHackernews wrote:
| When you're a trillion dollar company that burns more coal
| than Bangladesh in order to harness a hyperintelligent
| Machine God to serve your whims, you don't have the
| resources to maintain native clients for three separate
| targets.
| rolymath wrote:
| He literally says why electron in his comment that you are
| replying to
| Oras wrote:
| Going cross platform doesn't sound the main reason (or I
| hope not). For a company that size, is it really hard to
| hire specialised small team?! It would be a good show
| case for their Codex too
| piskov wrote:
| They presumably use codex to build this. LLMs output is
| non-deterministic. Harder to keep the same logic across.
|
| Would I love to see swiftui on macos, wpf/winui om
| windows, whatever qt hell it is on linux? Sure. But it is
| what it is.
|
| I am glad the codex-cli is rust and native. Because
| claude code and opencode are not: react, solidjs and what
| have you for a tree layer.
|
| --
|
| Then again, if codex builds codex, let it cook and port
| if AI is great. Otherwise, it's claim chowder
| ativzzz wrote:
| It is hard because this product will likely be obsolete
| next year based on how quickly AI is changing and
| evolving. Speed is king when you're on the frontier
| anonymous908213 wrote:
| Electron? Why can't Codex write, or at least translate, your
| application to native code instead of using a multi-hundred-
| mb browser wrapper to display text? Is this the future of
| software engineering Codex is promising me?
| tptacek wrote:
| If you were going to release a product for developers as soon
| as it was ready for developers to try, such that you could only
| launch on one platform and then follow up later with the rest,
| macOS is the obvious choice. There's nothing contemptuous about
| that.
| mellosouls wrote:
| Kudos to the OpenAI reps for responding to my comment and doing
| so politely.
|
| My ire was provoked by this following on from the Windows
| ChatGPT app that was just a container for the webpage compared
| to the earlier bells and whistles Mac app. Perceptions are
| built on those sorts of decisions.
| justkez wrote:
| Genuinely curious if people would just let this rip with no
| obvious isolation?
|
| I'm aware Mac OS has some isolation/sandboxes but without running
| codex via docker I wouldn't be running codex.
|
| (Appreciate there are still risks)
| davidcann wrote:
| Shameless plug, but you can sandbox codex cli without a
| container using my macOS app: https://multitui.com
| nkohari wrote:
| This is a really nice tool! (Also, I love the old school
| animated GIFs in the site's footer.)
| embirico wrote:
| (I work on Codex) We have a robust sandbox for macOS and Linux.
| Not quite yet for Windows, but working on that! Docs:
| https://developers.openai.com/codex/security
| realityfactchex wrote:
| I wouldn't trust it. I'm moving to always running AI coding in
| a full VM.
| daviding wrote:
| This looks interesting and I use Codex a fair bit already in
| vscode etc, but I'm having trouble leaving a 'code editor with
| AI' to an environment that sort of looks like it puts the code as
| a hidden secondary artefact. I guess the key thing is the multi
| agent spinning plates part.
| embirico wrote:
| (I work on Codex) I think for us the big unlock was GPT-5.2 and
| GPT-5.2-Codex, where we found ourselves needing to make many
| fewer manual edits.
| daviding wrote:
| I find that the case too. For more complex things my future
| ask would be something that perhaps formalized
| verification/testing into the AI dev cycle? My confidence in
| not needing to see code is directly proportional in my level
| of comfort in test coverage (even if quite high level
| UI/integration mechanisms rather than 1 != 0 unit stuff)
| austinhutch wrote:
| I'm managing context with codex inside VSCode using different
| threads. I'm trying to figure out if there are use cases where
| I'd rather be in this app.
| kblissett wrote:
| Does this support users who access Codex via Azure OpenAI API
| keys?
| robmn wrote:
| This is so garbage. OpenAI is never catching up.
| eamag wrote:
| > For a limited time, Codex will also be available to ChatGPT
| Free and Go users to help build more with agents. We're also
| doubling rate limits for existing Codex users across all paid
| plans during this period.
|
| Is there more information about it? For how long and what are the
| limits?
| wahnfrieden wrote:
| no
| allpratik wrote:
| They are probably providing it for free for 1 month.
| thefounder wrote:
| How is this better than vscode with the codex extension?
| e1g wrote:
| Wow, this is nearly an exact copy of Codex Monitor[1]: voice
| mode, project + threads/agents, git panel, PR button, terminal
| drawer, IDE integrations, local/worktree/cloud edits, archiving
| threads, etc.
|
| [1] https://github.com/Dimillian/CodexMonitor
| laborcontract wrote:
| Codex Monitor seems like an Antigravity Agent Manager clone. It
| came out after, too.
|
| Bunch of the features u listed were already in the codex
| extension too. False outrage it its finest.
| e1g wrote:
| I have both Codex Monitor and this new Codex app open side by
| side right now; aside from the theme, I struggle to tell them
| apart. Antigravity's Agent Manager is _obviously_ different,
| but these two are twins.
| laborcontract wrote:
| I have a very hard time getting worked up over this. There
| are a ton of entrants in this category, they all generally
| look the same. Cribbing features seems par for the course.
| verdverm wrote:
| Antigravity is a white labeled $2B pork of Windsurf, so it
| really starts there, but maybe someone knows what windsurf
| derived from to keep the chain going?
| FergusArgyll wrote:
| cursor?
| verdverm wrote:
| from what I can tell, the people behind windsurf were at
| it first
| Oras wrote:
| I've been using codex regularly and it's pretty good at model
| extra high with pretty generous context.
|
| From the video, I can see how this app would be useful in:
|
| - Creating branches without having to open another terminal, or
| creating a new branch before the session.
|
| - Seeing diff in the same app.
|
| - working on multiple sessions at once without switching CLI
|
| - I quite like the "address the comments", I can see how this
| would be valuable
|
| I will give it a try for sure
| nycdatasci wrote:
| The landing page for the demo game "Voxel Velocity" mentions
| "<Enter> start" at the bottom, but <Enter> actually changes
| selection. One would think that after 7mm tokens and use of a QA
| agent, they would catch something like this.
| anematode wrote:
| It's interesting, isn't it? On the one hand the game is quite
| impressive. Although it doesn't have anything particularly
| _novel_ (and it shouldn 't, given the prompt), it still would
| have taken me several days, probably a week, working nonstop.
| On the other hand, there's plenty of paper cuts.
|
| I think these subtle issues are just harder to provide a
| "harness" for, like a compiler or rigorous test suite that lets
| the LLM converge toward a good (if sometimes inelegant)
| solution. Probably a finer-tuned QA agent would have changed
| the final result.
| why_at wrote:
| It's also interesting how the functionality of the game barely
| changes between 60k tokens, 800k tokens, and 7MM tokens. It
| seems like the additional tokens made the game look more
| finished, but it plays almost exactly the same in all of them.
|
| I wonder what it was doing with all those tokens?
| freeqaz wrote:
| Does anybody know when Codex is going to roll out subagent
| support? That has been an absolute game changer in Claude Code.
| It lets me run with a single session for so much longer and chip
| away at much more complex tasks. This was my biggest pain point
| when I used Codex last week.
| laborcontract wrote:
| It's already out.
| turblety wrote:
| Can you explain how to use it? I've tried asking it to do
| "create 3 files using multiple sub agents" and other similar
| wording. It never works.
|
| Is it in the main Codex build? There doesn't seem to be an
| experiment for it.
|
| https://github.com/openai/codex/issues/2604
| nr378 wrote:
| Looks like another Claude App/Cowork-type competitor with
| slightly different tradeoffs (Cowork just calls Claude Code in a
| VM, this just calls Codex CLI with OS sandboxing).
|
| Here's the Codex tech stack in case anyone was interested like
| me.
|
| Framework: Electron 40.0.0
|
| Frontend:
|
| - React 19.2.0
|
| - Jotai (state management)
|
| - TanStack React Form
|
| - Vite (bundler)
|
| - TypeScript
|
| Backend/Main Process:
|
| - Node.js
|
| - better-sqlite3 (local database)
|
| - node-pty (terminal emulation)
|
| - Zod (validation)
|
| - Immer (immutable state)
|
| Build & Dev:
|
| - pnpm (package manager)
|
| - Electron Forge
|
| - Vitest (testing)
|
| - ESLint + Prettier
|
| Native/macOS:
|
| - Sparkle (auto-updates)
|
| - Squirrel (installer)
|
| - electron-liquid-glass (macOS vibrancy effects)
|
| - Sentry (error tracking)
| dcre wrote:
| The use of the name Codex and the focus on diffs and worktrees
| suggests this is still more dev-focused than Cowork.
| epolanski wrote:
| They have the same stack of a boot camper, quite telling.
| elpakal wrote:
| > this just calls Codex CLI with OS sandboxing
|
| The git and terminal views are a big plus for me. I usually
| have those open and active in addition to my codex CLI
| sessions.
|
| Excited to try skills, too.
| another_twist wrote:
| Is the integration with Sentry native or via MCP ?
| hdjrudni wrote:
| What does Sentry via MCP even mean? You want the LLM to call
| Sentry itself whenever it encounters an error?
| lacoolj wrote:
| OpenAI, ChatGPT, Codex
|
| So many of the things that pioneered the way for the truly good
| (Claude, Gemini) to evolve. I am thankful for what they have
| done.
|
| But the quality is gone, and they are now in catch-up mode. This
| is clear, not just from the quality of GPT-5.x outputs, but from
| this article.
|
| They launch something new, flashy, should get the attention of
| all of us. And yet, they only launch to Apple devices?
|
| Then, there are typos in the article. Again. I can't believe they
| would be sloppy about this with so much on the line. EDIT: since
| I know someone will ask, couple of examples - "7MM Tokens",
| "...this prompt initial prompt..."
|
| And why are they not giving the full prompt used for these
| examples? "...that we've summarized for clarity" but we want to
| see the actual prompt. How unclear do we need to make our prompts
| to get to the level that you're showing us? Slight red flag
| there.
|
| Anyway, good luck to them, and I hope it improves! Happy to try
| it out when it does, or at the very least, when it exists for a
| platform I own.
| rirze wrote:
| Not sure when you last evaluated the tools, but I strongly
| prefer Codex to Claude Code and Gemini.
|
| Codex gets complex tasks right and I don't keep hitting usage
| limits constantly. (this is comparing the 20$ ChatGPT to the
| 200$ Claude Pro Max plans fwiw)
|
| The tooling around ChatGPT and Codex is less, but their models
| are far more dependable imo than Antropic's at this very
| moment.
| touristtam wrote:
| I am not sure how those TUI are going to fare against multi
| providers ones like opencode.
| girvo wrote:
| I don't hit Codex limits because it's so much _slower_ , is
| what I've found personally.
| deepfriedbits wrote:
| I can't speak to the typos, but launching first for MacOS not
| something new for OpenAI. They did the same with their
| dedicated desktop client.
| halflings wrote:
| The main thing I noticed in the video is that they have
| _heavily_ sped up all the code generation sections... seems to
| be on 5x speed or more. (because people got used to how fast
| _and_ good Sonnet, and especially Gemini 3.0 Flash, are)
| lvl155 wrote:
| Bugs me they treat MacOS as first class. Do people actually
| develop on a Mac in 2026? Why not just start with Linux?
| foreigner wrote:
| Can't build iOS apps on anything else sadly.
| resfirestar wrote:
| I mean if they were targeting "software engineers" in general
| then Windows would be the obvious choice in 2026 as much as in
| 2006. But these early releases are all about the SF bubble
| where Mac is very much dominant.
| lvl155 wrote:
| Really? I frankly don't know anyone who's not on Linux. If
| you do any AI/ML you basically find yourself on a Linux box
| eventually. Perhaps I live in a bubble.
| poolnoodle wrote:
| These paid offerings geared toward software development must be a
| hell of a lot "smarter" than the regular chatbots. The amount of
| nonsense and bad or outright wrong code Gemini and ChatGPT throw
| at me lately is off the charts. I feel like they are getting
| dumber.
| zitterbewegung wrote:
| I don't understand why we are getting these software products
| that want to have vendor lock in when the underlying system
| isn't being improved. I prefer Claude code right now because
| it's a better product . Gemini just has a weird context window
| that poisons the rest of the code generated (when online)
| ChatGPT Codex vs Claude I feel that Claude is a better product
| and I don't use enough tokens to for Claude Pro at $100 and
| just have a regular ChatGPT subscription for productivity tasks
| .
| nkohari wrote:
| > I don't understand why we are getting these software
| products that want to have vendor lock in when the underlying
| system isn't being improved.
|
| I think it's clear now that the pace of model improvements is
| asymptotic (or at least it's reached a local maxima) and the
| model itself provides no moat. (Every few weeks last year,
| the perception of "the best model" changed, based on
| basically nothing other than random vibes and hearsay.)
|
| As a result, the labs are starting to focus on vertical
| integration (that is, building up the product stack) to
| deepen their moat.
| anematode wrote:
| > I think it's clear now that the pace of model
| improvements is asymptotic
|
| As much as I wish it were, I don't think this is clear at
| all... it's only been a couple months since Opus 4.5, after
| all, which many developers state was a major change
| compared to previous models.
| nkohari wrote:
| Like I said, lots of vibes and hearsay! :)
|
| The models are definitely continuing to improve; it's
| more of a question of whether we're reaching diminishing
| returns. It might make sense to spend $X billion to train
| a new model that's 100% better, but it makes much less
| sense to spend $X0 billion to train a new model that's
| 10% better. (Numbers all made up, obviously.)
| mceachen wrote:
| It's the inconsistency that gets me. Very similar tasks,
| similar complexity, same code base, same prompting:
|
| Session A knocks it out of the park. Chef's kiss.
|
| Session B just does some random vandalism.
| ghosty141 wrote:
| Yes they are, the fact that the agents have full access to your
| local project files makes a gigantic difference.
|
| They do *very* well at things like: "Explain what this class
| does" or "Find the biggest pain points of the project
| architecture".
|
| No comparison to regular ChatGPT when it comes to software
| development. I suggest trying it out, and not by saying
| "implement game" but rather try it by giving it clear scoped
| tasks where the AI doesn't have to think or
| abstract/generalize. So as some kind of code-monkey.
| luke_walsh wrote:
| I'm excited to try this out, it seems like it would solve a lot
| of my workflow issues. I hope there is the ability to review/edit
| research docs and plans it generates and not just code.
| jauntywundrkind wrote:
| Does the Codex app host MCP Apps?
| _rwo wrote:
| seems like I need to update my toolset for the 3rd time this week
| submeta wrote:
| > Work with multiple agents in parallel
|
| But you can already do that, in the terminal. Open your favourite
| terminal, use splits or tmux and spin up as many claude code or
| codex instances as you want. In parallel. I do it constantly. For
| all kinds of tasks, not only coding.
| esafak wrote:
| But they don't communicate. These do.
| macmac_mac wrote:
| i've been using ai vibe coding tools since Copilot was basically
| spicy autocomplete, and this feels like the next obvious step:
| less "help me type" and more "please do this while I watch
| nervously." The agent model sounds powerful, but in practice it's
| still a lot of supervision, retries, and quiet hope it doesn't
| hallucinate itself into a refactor I didn't ask for.
| prmph wrote:
| So if the agent struggles even when you are working with it,
| how will it be better working alone? This is why I never let
| the agent work by themselves. I'm very opinionated about my
| code.
|
| Does it somehow gain some superpower from being left alone?
| samstokes wrote:
| Bit of a buried lede:
|
| > For a limited time we're including Codex with ChatGPT Free
|
| Is this the first free frontier coding agent? (I know there have
| been OSS coding agents for years, but not Codex/Claude Code.)
| jsight wrote:
| That depends on whether Gemini CLI counts. I've had generally
| bad experiences with it, but it is free for at least some
| usage.
| falloutx wrote:
| Google also has aistudio.google.com which is Lovable
| competitor and its free for unlimited use. That seems to work
| so much better than gemini CLI even on similar tasks
| blueaquilae wrote:
| This is an ode to opencode and how openai, very strangely, is
| just porting layout and feature of real open-source.
|
| So much valuation, so much intern competetion and shenanigans
| than the creatives left.
| rubslopes wrote:
| To me, the obvious next step for these companies is to integrate
| their products with web hosting. At this point, the remaining
| hurdle for non-developers is deploying their creations to the
| cloud with built-in monetization.
| jimmy76615 wrote:
| Just tell it to use your gcp/aws account using the cli, makes
| it infinitely powerful in terms of deployment. (Also, while I
| might miss some parts of programming that I have given to AI, I
| certainly don't miss working with clouds).
| wiether wrote:
| > Just tell it to use your gcp/aws account using the cli
|
| Please don't.
|
| People burning through their tokens allowance on Claude Code
| is one thing.
|
| People having their agent unknowingly provisioning thousands
| of $ of cloud resources is something completely different.
| theshrike79 wrote:
| This is also on the cloud providers for not giving us good
| tools to manage costs.
| trunnell wrote:
| How about, "tell the agent to write instructions for cloud
| deployment with a cost estimate"
| johnpaulkiser wrote:
| interestingly opencode's first product was an IaC platform...
| seems to be where this is all going.
| falloutx wrote:
| I dont think these are made for non-devs, Lovable and other
| which are built for non-devs already provide hosting.
| iamnotarobottho wrote:
| and specifically, the big companies, in a way that people
| notice. Claude Artifacts, AI Studio, etc. all kinda suck. If
| you have used Manus or connected your own CF, GCP, AWS, etc.
| you see how easy it could be if one of the big guys wanted it
| to be (or could get out of their own way).
|
| the big boys probably don't want people who don't know sec
| deploying on their infra lol.
| halflings wrote:
| Deploying from Antigravity is as easy as say connecting the
| Firebase MCP [1] and asking it "deploy my app to firebase".
|
| [1] https://firebase.google.com/docs/ai-assistance/mcp-server
| anthonypasq wrote:
| Replit already does this
| desireco42 wrote:
| It keeps offering me to "Get Plus" even though I am signed and
| already have a Plus plan.
|
| Codex really grown on me lately. I re-signed to try it out on a
| project I have and it turned out to be really great addition to
| my toolkit.
|
| It isn't always perfect and it's cli (how I mostly use it) isn't
| as sophisticated as OpenCode which is my default.
|
| I am happy with this app, I am using Superset, terminal app which
| suprisingly is well positioned to help you if you work in cli
| like I do. But like I said, new desktop app seems like a solid
| addition.
| shevy-java wrote:
| No.
|
| I am glad to not depend on AI. It would annoy me to no ends how
| it tries to assimilate everything. It's like systemd on roids in
| this aspect. It will swallow up more and more tasks. Granted, in
| a way this is saying "then it was not necessary to have this
| things anymore now that AI solves it all", but I am skeptical of
| "the praised land" here. Skynet was not trusted back in 1982 or
| so. I don't trust AI either.
| dsiegel2275 wrote:
| Good luck.
| FeteCommuniste wrote:
| I'm the same way but I've got the gloomy sense that folks like
| us are about to be swept aside by the flood if we don't
| "adapt."
|
| I got invites to seven AI-centered meetings late last week.
| deepfriedbits wrote:
| Same. And indeed, it's here. The genie is not going back into
| the bottle, so we have to learn how to live in this new
| world.
|
| Eric Schmidt has spoken a lot recently about how it's one of
| the biggest advances in human history and it's hard to
| disagree with him, even if some aspects make me anxious.
| anonymous908213 wrote:
| One of the biggest advances in human history, and yet the
| owners of the technology with access to an unlimited number
| of "agents" using frontier models still can't release a
| desktop chat application without using Electron to bring in
| several hundred mb of bloat for displaying text. Someone's
| going to have to explain this one to me because the math is
| not mathing.
| reddalo wrote:
| Exactly. If AI really worked, they would've released a
| native app. And it wouldn't take much to also get a
| Windows and a Linux native app, wouldn't it?
|
| Apparently, the Codex app itself is proof that AI is not
| that good at doing what people think it does.
| bonesss wrote:
| How come if I download code from GitHub, rename some stuff,
| and republish it under another license I'm a bad guy, but
| if I ask ChatGFY to do it for me I'm a 10x Chad? ...
| someone is gonna figure that part out in court. I remember
| what code SCO used to make hay, and I know what side the
| MPAA, RIAA, Google, and NVidia Are gonna be on at the end
| of the day.
|
| Replacing workers with things you can't beat, sue,
| intimidate, or cajole? Someone is gonna do _something_ to
| make that not cool in MBA land. I think if one of my
| employees LL-MessedUp something, and I were upset, watching
| that same person stealing my money haplessly turn to an LLM
| for help might land me in jail.
|
| I kinda love LLMs, I've always struggled to write emails
| without calling people names. There's some clear coding
| tooling utility. But some of this current hype wave is
| _insano-balls_ from a business perspective. Pets.com X
| here's-my-ssh-keys. Just wild.
| rendleflag wrote:
| I feel the same way about using the Internet or books to code.
| I'd rather just have the source code so that I'm not dependent
| on anything other then my own brain.
| marstall wrote:
| i wonder if the skills will divide a bit. That there will be
| those who still program by hand - and this will be a needed
| skill, though AI will be a part of their daily toolset to a
| greater or lesser degree.
|
| Then there will be the AI wranglers who act almost like DevOps
| engineers for the AI - producing software in a different way
| ...
| ghosty141 wrote:
| I think a lot of AI talk doesn't explain where it shines the
| brightest (imo): Write the code you don't want to write.
|
| I've recently had an issue "add VNC authentication" which
| covers adding vnc password auth to our inhouse vnc server at
| work.
|
| This is not hard, but just a bit of tedious work getting the
| plumbing done, adding some UI for the settings, fiddle with
| some bits according to the spec.
|
| But it's (at least to me) not very enjoyable, there is nothing
| to learn, nothing new to discover, no much creativity necessary
| etc. and this is where Codex comes in. As long as you give it
| clearly scoped tasks in an environment where it can use
| existing structures and convetions, it will deliver. In this
| case it implemented 85% of the feature perfectly and I only had
| to tweak minor things like refactor 1-2 functions. Obviously I
| read and understood and checked everything it wrote, that is an
| absolute must for serious work.
|
| So my point is, use AI as the "code monkey". I believe most
| developers enjoy the creative aspects of the job, but not the
| "type C++ on your keyboard". AI can help with the latter, it
| will type what you tell it and you can focuse on the
| architecture and creative part of the whole thing.
|
| You don't have to trust AI in that sense, use it like
| autocompletion, you can program perfectly fine without it but
| it makes your fingers hurt more.
| causal wrote:
| This is the 5th OpenAI product called Codex if I'm counting
| correctly
| epolanski wrote:
| OT: I never liked about codex how it didn't ask for confirmations
| before editing. While Claude has auto accept off by default I
| never understood why codex didn't have it. I want to iterate on
| LLMs edit suggestions.
|
| Did they fix it?
|
| Otherwise I'm not interested.
| PeterStuer wrote:
| At least codex inside pycharm has auto edit off by default.
| wpm wrote:
| Maybe I'm just not getting it, but I just don't give a flying
| fuck about any of this crap.
|
| Like, seriously, this is the grand new vision of using a
| computer, this is the interface to these LLMs we're settling on?
| This is the best we could come up with? Having an army of
| chatbots chatting to each other running basic build commands in a
| terminal while we what? Supervise them? Yell at them? When am I
| getting manager pay bumps then?
|
| Sorry. I'll stick with occasionally chatting with one of these
| things in a sandboxed web browser on a single difficult problem
| I'm having. I just don't see literally any value in using them
| this way. More power to the rest of you.
| wendgeabos wrote:
| OK.
| karmasimida wrote:
| Not to rain on the parade, but this app feels to me ...
| unpolished. Some of the options in the demo feels less thought
| out and just put together.
|
| I will try it out, but is this just me, or product/UX side of
| recent OpenAI products are sort of ... skipped over? It is good
| that agents help ship software quickly, but please no half-baked
| stuff like Altas 2.0 again ...
| isodev wrote:
| I don't get why they announce it as a "Mac app" when the UI
| looks and feels nothing like a Mac app. Also electron... again.
|
| Why not flex some of those codex skills for a proper native
| app...
| tartoran wrote:
| What else do you expect from vibecoding? Even the announcement
| for this app is LLM generated.
| gordon_freeman wrote:
| How does Codex mac app compare with Cursor? If anyone who tried
| both can explain here?
|
| My experience with Cursor is generally good and I like that it
| gives me UX of using VS Code and also allows selection of
| multiple models to choose if one model is stuck on the prompt and
| does not work.
| throwaway314155 wrote:
| Coding agents with full automation like this require a
| different workflow that is almost purely conversational
| compared to Cursor/Windsurf/VS Code. It requires more trust in
| the model (but you can always keep Cursor open off to the side
| and verify its edits). But, once you get into the right rhythm
| with it, it can be _really_ powerful.
| teaearlgraycold wrote:
| Kind of embarrassing to demo "Please change this string to
| gpt-5.2". Presumably the diff UI doesn't let you edit the text
| manually? Or are they demonstrating being so AI-brained you
| refuse to type anything yourself?
| christkv wrote:
| What are the max context sizes ?
| beklein wrote:
| This will actually work well with my current workflow: dictation
| for prompts, parallel execution, and working on multiple bigger
| and smaller projects so waiting times while Codex is coding are
| fully utilized, plus easy commits with auto commit messages. Wow,
| thank you for this. Since skills are now first class tools, I
| will give it a try and see what I can accomplish with them.
|
| I know/hope some OpenAI people are lurking in the comments and
| perhaps they will implement this, or at least consider it, but I
| would love to be able to use @ to add files via voice input as if
| I had typed it. So when I say "change the thingy at route slash
| to slash somewhere slash page dot tsx", I will get the same
| prompt as if I had typed it on my keyboard, including the file
| pill UI element shown in the input box. Same for slash commands.
| Voice is a great input modality, please make it a first class
| input. You are 90% there, this way I don't need my dictation app
| (Handy, highly recommended) anymore.
|
| Also, I see myself using the built in console often to ls, cat,
| and rg to still follow old patterns, and I would love to pin the
| console to a specific side of the screen instead of having it at
| the bottom and pls support terminal tabs or I need to learn tmux.
| avazhi wrote:
| ChatGPT can't even write me a simple working AutoHotKey script so
| I'm not sure why I'd trust it with any actual coding. As I've
| done for about the past year with OpenAI showcases like this,
| this elicited an 'Oh, that's kinda neat, I'll just wait for
| Gemini to do something similar so it will actually work' from me.
| OlympicMarmoto wrote:
| It is baffling how these AI companies, with billions of dollars,
| cannot build native applications, even with the help of AI. From
| a UI perspective, these are mostly just chat apps, which are not
| particularly difficult to code from scratch. Before the usual
| excuses come about how it is impossible to build a custom UI,
| consider software that is orders of magnitude more complex, such
| as raddbg, 10x, Superluminal, Blender, Godot, Unity, and UE5, or
| any video game with a UI. On top of that, programs like Claude
| Cowork or Codex should, by design, integrate as deeply with the
| OS as possible. This requires calling native APIs (e.g., Win32),
| which is not feasible from Electron.
| bopbopbop7 wrote:
| > even with the help of AI.
|
| This is what you get when you build with AI, an electron app
| with an input field.
| airstrike wrote:
| I've done way, way more than that, as I'm sure others have
| too.
|
| This is just bad product management.
| bopbopbop7 wrote:
| So where is all this amazing software that you and others
| built with AI?
|
| All I see is hype blog posts and pre-IPO marketing by AI
| companies, not much being shipped though.
| measurablefunc wrote:
| There is a guy on twitter documenting his progress with
| moltbot/openclaw:
| https://x.com/Austen/status/2018371289468072219.
| Apparently he has already registered his bot for an LLC
| so he can make money w/ it.
| bopbopbop7 wrote:
| Some guy on Twitter selling an AI coding boot camp is an
| interesting example. Also it's literally just a post of
| him looking for a real developer to review his vibe coded
| bot???
| measurablefunc wrote:
| What does the bootcamp have to do w/ anything? He is
| using AI slop to make money, that's all that matters in a
| socio-economic system wherein everyone & everything must
| make profits to persist. Edit: found another example from
| coinbase:
| https://x.com/0xEricBrown/status/2018082458143699035.
|
| Edit: I'm not going to keep addressing your comment if
| you keep editing it. You asked for an example & I found
| two very easily. I am certain there are many others so at
| this point the burden of proof is on you to figure out
| what exactly it is you are actually arguing.
| saint_fiasco wrote:
| You won't see it because it's mostly personal software
| for personal computers.
|
| I've got a medical doctor handwriting decipherer, a board
| game simulator that takes a PDF of the rulebooks as input
| and an accounting/budgeting software that can interface
| with my bank via email because my bank doesn't have an
| API.
|
| None of that is of any use to you. If you happen to need
| a similar software, it will be easier for you to ask your
| own AI to make a custom one for you rather than adapt the
| ones I had my AI make for me.
|
| Under the circumstances, I would feel bad shipping
| anything. My users would be legitimately better off just
| vibe coding their own versions.
| measurablefunc wrote:
| Their goal is to ship as fast as possible b/c they don't
| care about what you care about. Their objective is to
| gather as much data as possible & electron is good enough
| for that.
| hdjrudni wrote:
| Doesn't have to be. I just revived one of my C++ GLFW app
| from 2009. Codex was able to help me get it running again and
| added some nice new features.
|
| I guess you get an Electron app if you don't prompt it
| otherwise. Probably because it's learned from what all the
| humans are putting out there these days.
|
| That said.. unless _you_ know better, it 's going to keep
| happening. Even moreso when folks aren't learning the
| fundamentals anymore.
| babypuncher wrote:
| At the end of the day LLMs just reproduce the consensus of
| the internet, so it makes sense that a coding agent would
| spit out software that looks like most of what's on the
| internet.
|
| LLM output is called slop for a reason.
| OlympicMarmoto wrote:
| Claude code is perfectly capable of writing low level
| rendering and input code and it can be equally as mindless as
| vibe coding web apps.
|
| E.g. just say "write a c++ gui widget library using dx11 and
| win32 and copy flutters layout philosophy, use harfbuzz for
| shaping, etc etc"
| rafram wrote:
| - Video games often use HTML/JS-based UI these days.
|
| - UE5 has its own custom UI framework, which definitely does
| not feel "native" on any platform. Not really any better than
| Electron.
|
| - You can easily call native APIs from Electron.
|
| I agree that Electron apps that feel "web-y" or hog resources
| unnecessarily are distasteful, but most people don't know or
| care whether the apps they're running use native UI frameworks,
| and being able to reassign web developers to work on desktop
| apps is a significant selling point that will keep companies
| coming back to Electron instead of native.
| anonymous908213 wrote:
| Given that OpenAI managed to single-handedly triple the price
| of RAM globally, people will very much care about their chat
| application consuming what little scraps are left over for
| them, even if they don't know enough about anything to know
| _why_ their system is running poorly.
| harikb wrote:
| I have been building Desktop apps with Go + Wails[1]. I
| happen to know Go, but if you are ai-coding even that is not
| necessary.
|
| A full fledged app, that does everything I want, is ~ 10MB. I
| know Tauri+Rust can get it to probably 1 MB. But it is a far
| cry from these Electron based apps shipping 140MB+ . My app
| at 10MB does a lot more, has tons of screens.
|
| Yes, it can be vibe coded and it is especially not an excuse
| these days.
|
| [1] https://wails.io/
|
| Microsoft Teams, Outlook, Slack, Spotify? Cursor? VsCode? I
| have like 10 copies of Chrome in my machine!
| alabhyajindal wrote:
| Wow Wails looks interesting! Hadn't heard of it before.
| hodanli wrote:
| I am in love with wails. having python and JS background
| with no go experience. I pm'ed Ai agents to create a fairly
| complex desktop app for my own use. it is day and night in
| terms of performance compared to lightest electron app.
| rafram wrote:
| I've looked into Tauri and Wails, but they don't seem
| realistic for a cross-platform app with wide distribution
| across multiple platforms and platform versions.
|
| One of Electron's main selling points is that you control
| the browser version. Anything that relies on the system web
| view (like Tauri and Wails) will either force you to
| aggressively drop support for out-of-date OS versions, or
| constantly check caniuse.com and ship polyfills like you're
| writing a normal web app. It also forces you to test CSS
| that touches form controls or window chrome on every
| supported major version of every browser, which is just a
| huge pain. And you'll inevitably run into bugs with the
| native -> web glue that you wouldn't hit with Electron.
|
| It is absolutely wasteful to ship a copy of Chrome with
| every desktop app, but Tauri/Wails don't seem like viable
| alternatives at the moment. As far as I can tell, there
| aren't really any popular commercial apps using them, so I
| imagine others have come to the same conclusion.
| harikb wrote:
| If the web-interface of a website can serve same HTML to
| all browsers, these UI can as well. I don't think we have
| IE6 level incompatibility these days. I have no idea what
| specific incompatibility you are talking about. I am
| writing my 4th desktop app since early 2025.
|
| But sure, you could have some specific need, but I find
| it hard to believe for these simple apps.
| pama wrote:
| My main take is exactly the opposite. Why not build everything
| with a simple text interface (shell command) so the models
| learn to use these tools natively in pretraining. Even TUI like
| codex-cli or claude code are needless abstractions for such use
| cases and make full automation hard. You could add as many
| observability or input layers for humans as you want but the
| core should be simple calls that are saved in historical and
| documentation logs. [the headless/noninteractive modes come
| close, as do the session logs]
| ryandrake wrote:
| It would be cool if I didn't have to worry about whether I
| was "in" or "out" of the AI TUI. Right now, I need at least
| two terminals open: One running my shell, that I use to issue
| shell commands, and one running Claude, where I can't. It
| would be nice if it could just be my shell, and when I wanted
| to invoke claude, I'd just type: c Do this
| programming task for me.
|
| Right in the shell.
| scottmf wrote:
| -p
| namelosw wrote:
| The situation for Desktop development is nasty. Microsoft had
| so many halfassed frameworks and nobody knows which one to use.
| It's probably the de facto platform on Windows IS Electron, and
| Microsoft use them often, too.
|
| On MacOS is much better. But most of the team either ended up
| with locked in Mac-only or go cross platform with Electron.
| harikb wrote:
| As I outlined in a sibling comment. You can still use React
| and your JS developers. Just don't ship a whole browser with
| your app.
|
| May be an app that is as complex as Outlook needs the pixel-
| perfect tweaking of every little button that they need to
| ship their own browser for exact version match. But
| everything else can use *system native browser*. Use Tauri or
| Wails or many other solutions like these
|
| That said, I do agree on the other comments about TUIs etc.
| Yes, nobody cares about the right abstractions, not even the
| companies that literally depend on automating these
| applications
| OlympicMarmoto wrote:
| This is another common excuse.
|
| You don't need to use microsoft's or apple's or google's shit
| UI frameworks. E.g. see https://filepilot.tech/
|
| You can just write all the rendering yourself using
| metal/gl/dx. if you didn't want to write the rendering
| yourself there are plenty of libraries like skia, flutter's
| renderer, nanovg, etc
| incr_me wrote:
| How is File Pilot for accessibility and for all of the
| little niceties like native scrolling, clipboard
| interaction, drag and drop, and so on? My impression is
| that the creator is has expertly focused on most/all of
| these details, but I don't have Windows to test.
|
| I insist on good UI as well, and, as a web developer, have
| spent many hours hand rolling web components that use
| <canvas>. The most complicated one is a spreadsheet/data
| grid component that can handle millions of rows, basically
| a reproduction of Google Sheets tailored to my app's needs.
| I insist on not bloating the front-end package with a whole
| graph of dependencies. I enjoy my NIH syndrome. So I know
| quality when I see it (File Pilot). But I also know how
| tedious reinventing the wheel is, and there are certain
| corners that I regularly cut. For example there's no way a
| blind user could use my spreadsheet-based web app
| (https://github.com/glideapps/glide-data-grid is better
| than me in this aspect, but there's no way I'm bringing in
| a million dependencies just to use _someone else 's_
| attempt to reinvent the wheel and get stuck with all of
| _their_ compromises).
|
| The answer to your original question about why these
| billion dollar companies don't create artisanal software is
| pretty straightforward and bleak, I imagine. But there
| _are_ a few actually good reasons not to take the artisanal
| path.
| jarek-foksa wrote:
| Customers simply don't care. I don't recall a single
| complain about RAM or disk usage of my Electron-based app
| to be reported in the past 10 years.
|
| You will be outcompeted if you waste your time reinventing
| the wheel and optimizing for stuff that doesn't matter.
| There is some market for highly optimized apps like e.g.
| Sublime Text, but you can clearly see that the companies
| behind them are struggling.
| cpuguy83 wrote:
| Not seeing complaints doesn't mean they don't exist. Not
| to mention ui latency that is common in electron apps
| that is just a low-level constant annoyance.
| weaksauce wrote:
| microsoft also uses react native for the start menu and also
| bricked that during a recent upgrade apparently... along with
| breaking other stuff.
| dheera wrote:
| This. Even Linux is nasty. Qt and GTK are both horrible
| messes to use.
|
| It would be nice if someone made a way to write desktop apps
| in JavaScript with a consistent, cross-platform modern UI
| (i.e. swipe to refresh, tabs, beautiful toggle switches, not
| microscopic check boxes) but without resorting to rendering
| everything inside a bloated WebKit browser.
| wilg wrote:
| Unpopular opinion: why would you want a "native app"? On macOS,
| basically every app Apple makes themselves is worse in terms of
| design, usability, and performance than a popular Electron-
| based alternative.
|
| For example, I tried opening a 200MB log file in Apple's
| Console.app and it hung. Opened right up in VS Code.
| hmokiguess wrote:
| I'm still waiting for the big pivotal moment in this space, I
| think there is a lot of potential with rethinking an IDE to be
| Agent first, and lots of what is out there is still lacking.
| (It's like we all don't know what we don't know, so we are just
| recycling UX around trying to solve it)
|
| I keep coming back to my basic terminal with tmux running
| multiple sessions. I recently though forked this
| https://github.com/tiann/hapi and been loving using tailscale to
| expose my setup on my mobile device for convenience (plus the
| voice input there)
| airstrike wrote:
| yeah, TUIs for AI is just lazy work imho. I'm glad at least
| this time it's a macOS app, but it's still just a shitty chat
| interface
|
| also this feels like a unique opportunity to take some of that
| astronomical funding and point it towards building the right
| tooling for building a performant cross-platform UI toolkit in
| a memory-safe language--not to mention a great way for these
| companies to earn some goodwill from the FOSS community
| quantumHazer wrote:
| Or maybe, hear me out, we don't need any of this ""agent""
| first shiny thingy
| hollowturtle wrote:
| There is little to no integration between deterministic IDE
| features(like refactorings) and LLMs. For example I don't want
| a statistical tool to rename a method by predicting tokens, I
| want it to use IDE features and not via another higher
| abstraction protocol like mpc, I want deeper integration.
| Sometimes I look at comments in code and think "why can't I
| have an agent checking if the content of a comment actually
| reflect the code below?" I feel like we're light years away
| from a killer integration
| hdjrudni wrote:
| This might actually be another area language servers shine.
| As I understand it, the TS Language Server can do renames.
| Ergo, we ought to be able to have the LLM ask the lang server
| to do the rename instead of trying to do it itself. That'd be
| easier than trying to integrate with each IDE individually.
| (Whereby "IDE" seems to be synonymous with "VSCode"
| lately...)
| hollowturtle wrote:
| Agree, another improvement i'd like along the lines or
| renames is lsp suggestions for method names, enums,
| functions, etc The llm should be able to autocomplete given
| lsp available symbols, this way it would avoid far less
| hallucinated methods
| hmokiguess wrote:
| Claude, at least, already supports LSP servers though.
| https://code.claude.com/docs/en/plugins-reference#lsp-
| server...
| hamasho wrote:
| More simple and similar app: vibe-kanban
|
| https://www.vibekanban.com/
| archiepeach wrote:
| Interesting timing for me personally as I just switched from
| running Codex in multiple tabs in Cursor to Ghostty. It had nicer
| fonts by default, better tab switching that was consistent with
| the keyboard shortcut to switch to any tab on Mac, and it had
| native notifications that would ping when Codex had finished.
| Worktrees requiring manual configuration was probably the one
| sticking point, so definitely looking forward to this.
| archiepeach wrote:
| We are certainly approaching the point where a high end MacBook
| Pro for development isn't required. Feels very close to just
| being able to use an iPad? My current workplace deploy on Vercel,
| we already test actively on feature branches and the models have
| gotten so good that you can reliably just commit what they've
| done (with linting and type check hooks etc) and in the rare
| event something is broken, follow up with a new commit.
| archiepeach wrote:
| * Replace MacBook with any high-end machine that requires a
| bunch of configuration for local dev. And replace iPad with any
| thin client that's much more portable and convenient, eg
| glasses that display a screen and Bluetooth keyboard. Why
| shouldn't I be able to describe the changes I want to an LLM
| from a coffee shop?
| laacz wrote:
| Judging from the performance issues with Claude Code, you won't
| be able to run a decent agentic cli or desktop workflow
| orchestrator on anything other than mbp.
| hollowturtle wrote:
| I don't know you, but apart from ai tools race fatigue(feel
| pretty much like frameworks fatigue), all I see is mouse
| traveling a lot between far distant small elements, buttons and
| textareas. AI should have brought innovation even in UIs we
| basically stopped innovating there
| waldopat wrote:
| It seems the big feature is working agents in parallel? I've been
| working agents in parallel in Claude Code for almost 9 months
| now. Just create a command in .claude/commands that references an
| agent in .claude/agents. You can also just call parallel default
| Task agents to work concurrently.
|
| Using slash commands and agents has been a game changer for me
| for anything from creating and executing on plans to following
| proper CI/CD policies when I commit changes.
|
| To Codex more generally, I love it for surgical changes or
| whenever Claude chases its tail. It's also very, very good at
| finding Claude's blindspots on plans. Using AI tools
| adversarially is another big win in terms of getting things 90%
| right the first time. Once you get the right execution plan with
| the right code snippets, Claude is essentially a very fast typer.
| That's how I prefer to do AI-assisted development personally.
|
| That said, I agree with the comments on tokens. I can use Codex
| until the sun goes down on $20/month. I use the $200/month pro
| plan with Claude and have only maxxed out a couple times, but I
| do find the volume to quality to be better with Claude. So far
| it's worth the money.
| Dowwie wrote:
| Hey, that's great OpenAI. Now add about 6 zeroes to the end of
| the weekly token limit for your customers and maybe we could use
| the app
| daxfohl wrote:
| It would be nice if it didn't have to be all local. I'd love a
| managed cluster feature where you could just blast some workloads
| off to some designated server or cluster and manage them
| remotely, share progress with teammates, etc. (Not "cloud"
| though; I'd still want them on the internal network). I imagine
| something like that is in the works.
| andrewchambers wrote:
| I do it with ssh and tmux. I suppose tools could make it
| better.
| keeeba wrote:
| Is everything OpenAI do/release now a response to something
| Anthropic have recently released?
|
| I remember the days when it was worth reading about their latest
| research/release. Halcyon days indeed.
| punnerud wrote:
| When can I get remote access in the iPhone app? Start on my
| laptop, check results using Tailscale/VPN and add follow up's on
| the mobile to run on the computer. Know many that would love this
| feature.
| gigatexal wrote:
| For pure code generation is ChatGPT 5.2 so much better than
| Claude opus 4.5 thinking to have me switch? I'm basically all in
| on Claude.
|
| Sure I could move to open code and use them as commodities but
| I've gotten use to Claude code and like using the vendors first
| party app.
| jtrn wrote:
| People's mileage may vary, but in my instance, this was so bad
| that I actually got angry while trying to use it.
|
| It's slow and stupid. It does not do proper research. It does not
| follow instructions. It randomly decides to stop being agentic,
| and instead just dumps the code for me to paste. It has the
| extremely annoying habit of just doing stuff without
| understanding what I meant, making a mess, then claiming
| everything is fine. The outdated training data is extremely
| annoying when working with Nuxt 4+. It is not creative at solving
| problems. It dosent show the thinking. The Undo code does not
| give proper feedback on the diff and if it actually did "undo."
| And I hate the personality. It HAS to be better than it comes off
| for me because I am actually in a bad mood after having worked
| with it. I would rather YOLO code with Gemini 3 flash, since it's
| actually smarter in my assessment, and at least I can iterate
| faster, and it feels like it has better common sense.
|
| Just as an example, I found an old, terrible app I made years ago
| for our firm that handles room reservations. I told it to update
| from Bootstrap to Flowbite UI. Codex just took forever to make a
| mess, installed version 2.7 when 4.0.1 is the latest, even when I
| explicitly stated that it should use the absolute latest version.
| Then it tried to install it and failed, so it reverted to the
| outdated CDN.
|
| I gave the same task to Claude Code. Same prompt. It one-shotted
| it quickly. Then I asked it to swap out ALL the fetch logic to
| have SPA-like functionality with the new beta 4 version of HTMX,
| and it one-shot that too in the time Codex spent just trying to
| read a few files in the project.
|
| This reminds me of the feeling I had when I got the Nokia N800.
| It was so promising on paper, but the product was so bad and
| terrible to use that I knew Nokia was done for. If this was their
| take on what an acceptable smartphone could be, it proves that
| the whole foundation is doomed. If this is OpenAI's take on what
| an agentic coding assistant should be--something that can run by
| itself and iterate until it completes its task in an intelligent
| and creative way.... OpenAI is doomed.
| vcryan wrote:
| Another boring update from OpenAI. Why would I want an
| orchestration tool tied to one model? Part of the value of
| orchestration tools is using the most appropriate and/or cost
| effective model for the task, sub-task, etc
| ChrisMarshallNY wrote:
| Eh. Kicked the tires for a few minutes. Back to the old clunker
| app.
|
| No worries. I'm not their target demographic, anyway.
___________________________________________________________________
(page generated 2026-02-02 23:00 UTC)