articles about Anthropic’s Claude Code, and the way I take advantage of it for programming, and totally different methods that I apply to make it simpler. Nevertheless, the final two weeks I’ve been experimenting increasingly more with OpenAI’s Codex and seeing vastly improved outcomes in comparison with Codex just a few months in the past.
For my part, Codex is equally good on numerous duties and has the benefit that it’s, in lots of instances, quicker than Claude Code and that it’s higher at doing precisely what it’s requested to do and never performing different duties (which is the issue I’ve skilled with Claude Code).
On this article, I’ll be discussing my expertise utilizing OpenAI’s Codex for superior coding duties and different software areas, in addition to some methods that I take advantage of to reinforce Codex’s efficiency.
Why use OpenAI Codex?
Initially, I wish to cowl why you ought to be utilizing OpenAI Codex. It’s price mentioning that the pricing of Codex for the 20x Max subscription is identical as Claude Code. The one differentiator is the standard of the outputs produced by the mannequin and the way effectively it will possibly full duties.
Contemplating I program each single day, it’s vital for me to remain up-to-date with the newest coding fashions and constantly check out new and upcoming fashions, corresponding to GPT-5.5, to see if it really works higher than my present setup.
I simply began utilizing Codex with GPT-5.5 round two weeks in the past and easily utilized it to some real-world duties I used to be engaged on. That is vital, as I consider working coding fashions on take a look at duties doesn’t really take a look at the mannequin’s capabilities, and it’s not a sound and full take a look at.
After I used it on a number of the extra complicated duties I used to be engaged on, I used to be fairly impressed by the outcomes. For my part, Codex was extraordinarily environment friendly at finishing some duties and accomplished them in a short time. Moreover, I bought the impression that Codex was higher than Claude Code at performing precisely the duties I used to be asking it to do and never altering different stuff within the code. Truly, an issue I’ve skilled with Claude Code just a few occasions is that I ask it to finish a selected activity, and it principally completes that activity, however it additionally modifications another issues I didn’t need it to vary.
It’s price mentioning that that is very a lot a steadiness. On one hand, you’ve got Claude Code’s method, which is to offer the mannequin extra freedom to make choices on what needs to be modified, which may result in the mannequin altering components of the code that you just don’t intend to vary. However, you’ve got Codex’s method, which is altering solely precisely what the consumer is asking you to replace. This may, alternatively, have the draw back that it results in bugs everywhere in the code as a result of it’s not up to date, just because Codex simply performs precisely what it’s requested to do and nothing else.
Particular methods I take advantage of to optimize Codex
On this part, I’ll cowl some particular methods I take advantage of to make Codex carry out higher than simply out of the field. I’ll cowl my setup and a few methods.
My setup
Initially, let’s cowl my setup. I do use quick mode on Codex at the moment as a result of I’m not hitting my limits that usually. Nevertheless, in case you are hitting your limits, you need to take into account turning off FastMode or getting one other Codex account.
Moreover, I take advantage of further excessive considering after I’m utilizing plan mode and excessive considering or reasoning after I’m utilizing regular mode, and I’m utilizing GPT-5.5, after all.
I’ve additionally given Codex entry to Playwright MCP, which is a method that it will possibly entry my browser and carry out actions there. That is extraordinarily environment friendly, for instance, for OpenClaw bots, which I’ll cowl within the subsequent part, and for really going into the browser and testing options that Codex has carried out. As I’ve talked about in a number of earlier articles, permitting your coding brokers to check their very own work vastly improves the efficiency of those coding fashions.
You’ll be able to learn extra on this in my article under:
How to Make Claude Code Validate its own Work
Lastly, I’m additionally utilizing YOLO mode with Codex, the place I give it, or enable it to carry out, any motion throughout the folder it’s working in. In my expertise, the frontier coding fashions, corresponding to Claude Code and Codex, should not inclined to creating extreme errors corresponding to deleting manufacturing databases or related, they usually’ll usually warn you earlier than taking irreversible actions.
Moreover, I additionally consider that should you arrange your codebase and infrastructure appropriately, this is not going to actually be a problem. An agent otherwise you, for that matter, shouldn’t have entry to completely delete databases and carry out irreversible harm on any infrastructure. That’s usually extra an indication of poor infrastructure design decisions quite than a problem with a programmer or a coding agent.
OpenClaw bots
One other use case I’ve for Codex is that I’m utilizing it for my OpenClaw bots. One of many nice benefits of utilizing Codex over Claude Code at the moment is that you may energy your OpenClaw bots together with your Codex subscription, which you aren’t allowed to do together with your Claude Code subscription anymore. That is vital as a result of, for my part, Codex is a frontier-level clever mannequin you need to use on your OpenClaw bots, which additionally has acceptable pricing.
With this, I imply that Claude Code API pricing merely isn’t relevant for nearly all programmers on the market, and thus isn’t an possibility for OpenClaw. As an alternative, you should purchase a $100 or $200 subscription with Codex and have a really clever mannequin energy your OpenClaw bots, which I consider is an efficient funding you can also make.
I additionally use quick mode on my OpenClaw bots since I’ve sufficient finances accessible for utilization. Nevertheless, you’ll be able to once more flip it off should you suppose it’s essential, and it, after all, is determined by the use case. In some situations, you’re extra depending on quick replies out of your coding agent, and in different cases, you simply carry out a fire-and-forget activity. The time it takes to carry out the duty shouldn’t be actually vital.
Worktrees
Sadly, OpenAI Codex hasn’t carried out a easy work tree setup but, as Claude Code has. That is positively a minus in my e-book, as work bushes are a vital characteristic to have when I’m engaged on a number of issues in the identical repo on the similar time.
Nevertheless, to fight this downside, I arrange a easy alias the place I create my very own work tree when spinning up Codex. I did this just by asking Codex to arrange an alias for me in order that if I write the command you see under, it is going to spin up a piece tree with the title offered.
codex-wt This was tremendous easy to arrange and solely took a couple of minutes with Codex.
Codex vs Claude Code
On this final part, I wish to cowl Codex versus Claude Code and my opinion on evaluating the 2 coding brokers and frameworks. For my part, there’s no clear winner between the 2 fashions. They’re each extraordinarily highly effective, and for my part, I can full even my most complicated duties with each fashions. Nevertheless, I do have some preferences in sure situations.
When I’ve a really particular activity I wish to full or am on the lookout for particular bugs, for my part, Codex works higher and is extra environment friendly at finishing the duty. In lots of instances, Claude Code may also be capable to full the identical activity, however merely take longer, from my expertise.
Moreover, as I discussed within the OpenClaw part, Codex lets you use the subscription on OpenClaw bots, which Claude Code doesn’t help you do. In case you are depending on working numerous OpenClaw bots, I extremely suggest you do it with Codex.
Quite the opposite, I believe Claude Code is extraordinarily highly effective and may full all my most complicated duties whereas nonetheless having numerous options that I actually take pleasure in. The work tree characteristic, for instance, is a superb inclusion from Claude Code, in addition to the brokers’ view, which they lately launched. For my part, the characteristic stack of Claude Code is extra highly effective than Codex and will thus be a purpose to decide on Claude Code over Codex.
Nevertheless, all in all, I consider the 2 fashions are neck and neck and each extraordinarily highly effective. We’ll simply need to observe each fashions sooner or later, proceed testing them, and see which one comes out on high in just a few months’ time. In the interim, I consider they’re each nice decisions, and what works greatest for you depends in your state of affairs and preferences.
Conclusion
On this article, I mentioned tips on how to get essentially the most out of OpenAI’s Codex. I mentioned why I began utilizing OpenAI Codex, highlighting how I want to remain on high of the newest coding fashions and wish to evaluate it towards Claude Code. I bought a really constructive first impression, noticing that the mannequin was capable of carry out even essentially the most complicated duties I’m engaged on. I then lined some particular methods I take advantage of to make Codex higher, corresponding to:
- letting it validate its personal work
- establishing an alias for work bushes
- utilizing it for my OpenClaw bots
Lastly, I additionally had a bit evaluating Codex vs. Claude Code, the place I highlighted that it’s extraordinarily shut, and which one is the higher mannequin. Which mannequin is healthier for you is determined by your preferences. I like to recommend that you just look into each fashions to see what works greatest for you, and in addition intently observe the fashions within the close to future, as a result of I consider numerous new options and extra highly effective LLMs will change into accessible.
👉 My free eBook and Webinar:
🚀 10x Your Engineering with LLMs (Free 3-Day Email Course)
📚 Get my free Vision Language Models ebook
💻 My webinar on Vision Language Models
👉 Discover me on socials:
💌 Substack
