It really bothers me that it doesn't have support for devcontainers.
Only a closed set of languages are supported and the hook for startup installation of additional software seems to be not fully functioning at the moment.
Yeah that's why we basically built our own Claude Code Web but around Hetzner VPSs instead & terminal access. So you can use docker, open ports if you'd like. Some teams even needed us for a complicated R dev setup they wanted Claude to work with.
I was always disappointed by the Cursor version because the agents would make entirely new mistakes that Cursor IDE wouldn't make locally. Like so much that it was totally unusable. Completely messing up code edits to the point where a whole file would be deleted.
Interested to give this a go. But I would also need it to be able to run docker compose and playwright, to keep things on the rails.
I wish it didn't make public PRs to public repos. I sometimes fire off really speculative and sometimes silly requests and I really don't want a permanent record of these on an open source Github project. I could work on a fork but it's still fairly public.
Codex handles this much better. You choose when to make a PR and you can also just copy a .patch or git apply to your clipboard.
EDIT. They might have fixed this. Just testing. Does the mobile android app have Claude Code support yet or is it still annoyingly an iOS only thing?
EDIT2. It creates a public branch but not a PR. I'd still prefer that was a manual step.
Meanwhile, claude CLI has so many huge bugs that break the experience. Memory leaks, major cpu usage, tool call errors that require you to abandon a conversation, infinite loops, context leaks, flashing screens.. so many to list.
I love the feature set of Claude Code and my entire workflow has been fine tuned around it, but i had to to codex this month. Hopefully the Claude Code team spends some time to slow down and focus on bugs.
I like the workflow with Codex more. Though I like working with Claude more. So I wish Anthropic would copy the Codex workflow.
I like that Codex commits using your identity as if it was your changes. And I like that you can interact with it directly from the PR as if it was a team member.
I used Claude Code a lot until this weekend, when I gave Codex CLI a try, and I have to say, wow. The gpt-5-codex model is amazing. Sonnet 4.5 routinely gets stuff wrong, even Opus 4.1 isn't too amazing, but GPT 5 Codex just one-shots everything.
I've been using Sonnet whenever I run into the Codex limit, and the difference is stark. Twice yesterday I had to get Codex to fix something Sonnet just got entirely wrong.
I registered a domain a year ago (pine.town) and it came up for renewal, so I figured that, instead of deleting it, I'd build something on it, and came up with the idea of an infinite collaborative pixel canvas with a "cozy town" vibe. I have ZERO experience with frontend, yet Codex just built me the entire damn thing over two days of coding:
It's the first model I can work with and be reasonably assured that the code won't go off the rails. I keep adding and adding code, and it hasn't become a mess of spaghetti yet. That having been said, I did catch Codex writing some backend code that could have been a few lines simpler, so I'm sure it's not as good as me at the stuff I know.
Then again, I wouldn't even have started this without Codex, so here we are.
Weird, I tried the CoPilot and Codex CLIs and my experience was not good. I set it up with the same MCP tools I use elsewhere and the results were subpar compared to using agents in IDEs. I don't think it's a context issue either.
Claude's vscode extension and general ergonomics are vastly superior to Codex's. Codex has a comically inept UI, it literally can start lagging and has even crashed for me.
I built a version of this which wraps multiple CLI sessions locally. I do think the Web aspect and being able to access your CC session from anywhere is cool.
I've been hoping that Claude Code on the Web also works with MCPs; so I can start getting it to do things beyond just coding. It's pretty awesome to use Git as a source of memory/tracking what's going on and pull requests as a way to build in a human-in-the-loop review flow.
Love these discussions to find out what's new. For me replit.com is still the GOAT.
- Time to start your container (or past project) is ~1 sec to 1 min.
- Fully supported NixOS container with isolated, cloned agent layer. Most tools available locally to cut download times and ai web access risk.
- Github connections are persistent. Agents do a reasonable job with clean local commits.
- Very fast dev loops (plan/build/test/architect/fix/test/document/git commit / push to user layer) with adjustable user involvement.
- Phone app is fully featured... I've never built apps on roadtrips before replit.
- Uses claude code currently (has used chatgpt in the past).
Tips:
- Consider tig to help manage git from cli before you push to github.
- Gitlab can be connected but is clumsy with occasional server state refreshes.
- Startups that haven't committed to an IDE yet and expect compatibility with NixOS would have strong reason to consider this. It should save them the need to build their own OS-local AI code through early builds.
Honestly, I'm just flabbergasted at how incredible these tools are. I was able to build https://www.standup.net in a few days. Also was able update an old project https://www.microphonetest.com in a matter of hours with a plethora of features. Its truly addicting.
I have a question prompted by seeing what everyone is doing with Codex and Claude Code. I'm currently in a Data Analytics, B.S. program. I've thought of dropping out and focusing on coding with these AI tools, but some programmers have told me that by knowing SQL, Python, JavaScript and how to code in general, that it'll give me an advantage.
Is the 1.5 years that I have left worth it? (I already have an Associate's Degree).
I made an account just for you :) My opinion is: don't drop out.
1. The degree is useful. Having a Bachelor's opens up a lot of career paths because it shows that you committed to the Data Analytics program for four years. It also helps HR check off the "has a bachelor's" item on their list.
2. What you learn is useful. At the end of the day, you will be responsible for the code that the AI produces. How will you understand, explain, and justify your code to your colleagues and managers? "SQL, Python, JavaScript" and "theoretical Data Analytics knowledge" are both tools that will help you.
3. So far, senior engineers tend to have the most productivity boosts with AI. These engineers became "senior" before AI coding agents became mainstream, which means they know how to program. So based on this pattern, if you know how to program, then you will benefit more from AI.
Maybe you have other factors you are considering (e.g. money). My response is primarily based on the "existence of AI coding agents in the industry" factor.
It means they better fill a niche. We ourselves built our own twist on cc web and we found differentiation that they couldn't. For instance running claude in real VPSs in which you can run docker & docker compose, connect to via SSH or even host stuff. We also made our own file sync so you start on web, continue on desktop in your IDE, run code locally, go back to web & mobile...
I think IDEs we're gonna see Vims, Emacs, Jetbrains, Vscode. For now CC web seems to be the sublime text of that world, and Terragon/Sculptor are yet to differentiate enough like a jetbrains
We try to be the jetbrains of this, which is not a smart move for a bigger co like Anthropic to take
Gemini is really good at convincing they know what you're talking about. Sadly it hallucinates, and it does this confidently. You end up just thinking "well they confirmed x is greppable in y" but in reality they never used grep
The "Codex" model requires different promoting for the best results. You may also find, depending on your task, that the standard non-codex model works better.
I use Zed + Qwen CLI + free Grok. I stopped paying for LLMs about two months ago and can get everything I need for free. It would be great to have cheap Cerebras hardware with open-source models like Qwen Coder 480B and (soon?) Grok 3; that would unlock anything I need to do... locally...
I don't get this version of Claude Code. What changed my mind about AI coding was the fact that Claude Code was so good at using tools. If it changed some code, it ran tests, debug failures, etc. Having Claude Code on the web, without having access to a custom environment with the right tools available, just doesn't make sense to me. Claude Code on GitHub Actions is a much more usable variant for me. It allows for custom setup, but then it's not interactive like this one is. I really wish there was some middle ground.
We've got a product in beta right now that lets's you spin up a review app by just commenting "deploy" on a PR in GitHub. When you combine that with Claude Code on the web, it is pretty fun. You can be anywhere (on a boat, train, lying on the couch, in a stadium watching 18 innings of baseball) and using Claude Code on the web on any mobile phone (in a browser.) As it builds stuff, it's instantly deploying a review app for each update and so you can see the changes and then give it another request. Also makes it easy to just drop that review app into a groupchat to get feedback from other people who are also not at their computers. I don't have a link to a video yet but I posted a few screenshots here. If you want to try the review app functionality, just send me a message. https://www.linkedin.com/posts/jonessteven_anthropic-claude-...
Claude Code is awesome, no doubt, but I’ve recently fallen in love with Codex. It takes longer to respond, sure, but the changes it makes are way more thorough — the attention to detail is just next level.
38 comments
[ 0.23 ms ] story [ 51.6 ms ] threadOnly a closed set of languages are supported and the hook for startup installation of additional software seems to be not fully functioning at the moment.
Interested to give this a go. But I would also need it to be able to run docker compose and playwright, to keep things on the rails.
Codex handles this much better. You choose when to make a PR and you can also just copy a .patch or git apply to your clipboard.
EDIT. They might have fixed this. Just testing. Does the mobile android app have Claude Code support yet or is it still annoyingly an iOS only thing?
EDIT2. It creates a public branch but not a PR. I'd still prefer that was a manual step.
creating container -> cloning repo -> making change -> test -> send PR
is too slow of a loop for me to do anything much useful. It's only good for trivial "one-shot" stuff.
I love the feature set of Claude Code and my entire workflow has been fine tuned around it, but i had to to codex this month. Hopefully the Claude Code team spends some time to slow down and focus on bugs.
I like that Codex commits using your identity as if it was your changes. And I like that you can interact with it directly from the PR as if it was a team member.
I've been using Sonnet whenever I run into the Codex limit, and the difference is stark. Twice yesterday I had to get Codex to fix something Sonnet just got entirely wrong.
I registered a domain a year ago (pine.town) and it came up for renewal, so I figured that, instead of deleting it, I'd build something on it, and came up with the idea of an infinite collaborative pixel canvas with a "cozy town" vibe. I have ZERO experience with frontend, yet Codex just built me the entire damn thing over two days of coding:
https://pine.town
It's the first model I can work with and be reasonably assured that the code won't go off the rails. I keep adding and adding code, and it hasn't become a mess of spaghetti yet. That having been said, I did catch Codex writing some backend code that could have been a few lines simpler, so I'm sure it's not as good as me at the stuff I know.
Then again, I wouldn't even have started this without Codex, so here we are.
So lately I'll start with Sonnet for everything but the most complex tasks and then switch to Codex when needed.
https://github.com/built-by-as/FleetCode
I'd like to build an integration with Whisper Memos (https://whispermemos.com/)
Then I'd be able to dictate a note on my Apple Watch such as:
> Go into repository X and look at the screen Y, and fix bug Z.
That'd be so cool.
- Time to start your container (or past project) is ~1 sec to 1 min. - Fully supported NixOS container with isolated, cloned agent layer. Most tools available locally to cut download times and ai web access risk. - Github connections are persistent. Agents do a reasonable job with clean local commits. - Very fast dev loops (plan/build/test/architect/fix/test/document/git commit / push to user layer) with adjustable user involvement. - Phone app is fully featured... I've never built apps on roadtrips before replit. - Uses claude code currently (has used chatgpt in the past).
Tips: - Consider tig to help manage git from cli before you push to github. - Gitlab can be connected but is clumsy with occasional server state refreshes. - Startups that haven't committed to an IDE yet and expect compatibility with NixOS would have strong reason to consider this. It should save them the need to build their own OS-local AI code through early builds.
Is the 1.5 years that I have left worth it? (I already have an Associate's Degree).
1. The degree is useful. Having a Bachelor's opens up a lot of career paths because it shows that you committed to the Data Analytics program for four years. It also helps HR check off the "has a bachelor's" item on their list.
2. What you learn is useful. At the end of the day, you will be responsible for the code that the AI produces. How will you understand, explain, and justify your code to your colleagues and managers? "SQL, Python, JavaScript" and "theoretical Data Analytics knowledge" are both tools that will help you.
3. So far, senior engineers tend to have the most productivity boosts with AI. These engineers became "senior" before AI coding agents became mainstream, which means they know how to program. So based on this pattern, if you know how to program, then you will benefit more from AI.
Maybe you have other factors you are considering (e.g. money). My response is primarily based on the "existence of AI coding agents in the industry" factor.
I think IDEs we're gonna see Vims, Emacs, Jetbrains, Vscode. For now CC web seems to be the sublime text of that world, and Terragon/Sculptor are yet to differentiate enough like a jetbrains
We try to be the jetbrains of this, which is not a smart move for a bigger co like Anthropic to take
https://ariana.dev
1. claude code CLI, generally works, great tool use
2. codex on the web, feels REALLY smart, but can’t use tools
3. codex CLI, still smarter than claude but less situational awareness
4. codex via iphone app, buggier than the web app
5. claude code on the web, worst of all worlds
Gemini is really good at convincing they know what you're talking about. Sadly it hallucinates, and it does this confidently. You end up just thinking "well they confirmed x is greppable in y" but in reality they never used grep
https://cookbook.openai.com/examples/gpt-5-codex_prompting_g...
The "Codex" model requires different promoting for the best results. You may also find, depending on your task, that the standard non-codex model works better.