GPT-5.2-Codex

I’m in Claude Code so often (x20 Max) and I’m so comfortable with my environment setup with hooks (for guardrails and context) that I haven’t given Codex a serious shot yet.

I consistently run into limits with CC (Opus 4.5) -- but even though Codex seems to be spending significantly more tokens, it just seems like the quota limit is much higher?

I don't understand why not. People pay for quality all the time, and often they're begging to pay for quality, it's just not an option. Of course, it depends on how much more quality is being offered, but it sounds like a significant amount here.

In my mind, they're hardly making any money compared to how much they're spending, and are relying on future modeling and efficiency gains to be able to reduce their costs but are pursuing user growth and engagement almost fully -- the more queries they get, the more data they get, the bigger a data moat they can build.

I only ever use it on the high reasoning mode, for what it's worth. I'm sure it's even less of a problem if you turn it down.

The OpenAI token limits seem more generous than the Anthropic ones too.

Experiencing that repeatedly motivated me to use it as a reviewer (which another commenter noted), a role which it is (from my experience) very good at.

I basically use it to drive Claude Code, which will nuke the codebase with abandon.

I asked codex to take a look. It took a couple minutes, but it managed to track the issue down using a bunch of tricks I've never seen before. I was blown away. In particular, it reran qemu with different flags to get more information about a CPU fault I couldn't see. Then got a hex code of the instruction pointer at the time of the fault, and used some tools I didn't know about to map that pointer to the lines of code which were causing the problem. Then took a read of that part of the code and guessed (correctly) what the issue was. I guess I haven't worked with operating systems much, so I haven't seen any of those tricks before. But, holy cow!

Its tempting to just accept the help and move on, but today I want to go through what it did in detail, including all the tools it used, so I can learn to do the same thing myself next time.

edit: username joke, don't get me banned

(here I am remembering a time I had no computer and would program data structures in OCaml with pen and paper, then would go to university the next day to try it. Often times it worked the first try)

A full week of that should give you a pretty good idea

Maybe some models just suit particular styles of prompting that do or don't match what you're doing

This is very similar to how humans behave. Most people are great a small number of things, and there's always a larger set of things that we may individually be pretty terrible at.

The bots the same way, except: Instead of billions of people who each have their own skillsets and personalities, we've got a small handful of distinct bots from different companies.

And of course: Lies.

When we ask Bob or Lisa help with a thing that they don't understand very well, they usually will try to set reasonable expectations . ("Sorry, ssl-3, I don't really understand ZFS very well. I can try to get the SLOG -- whatever that is -- to work better with this workload, but I can't promise anything.")

Bob or Lisa may figure it out. They'll gather up some background and work on it, bring in outside help if that's useful, and probably tread lightly. This will take time. But they probably won't deliberately lie [much] about what they expect from themselves.

But when the bot is asked to do a thing that it doesn't understand very well, it's chipper as fuck about it. ("Oh yeah! Why sure I can do that! I'm well-versed in -everything-! [Just hold my beer and watch this!]")

The bot will then set forth to do the thing. It might fuck it all up with wild abandon, but it doesn't care: It doesn't feel. It doesn't understand expectations. Or cost. Or art. Or unintended consequences.

Or, it might get it right. Sometimes, amazingly-right.

But it's impossible to tell going in whether it's going to be good, or bad: Unlike Bob or Lisa, the bot always heads into a problem as an overly-ambitious pack of lies.

(But the bot is very inexpensive to employ compared to Bob or Lisa, so we use the bot sometimes.)

This is what I do. I have a little TUI that fires off Claude Code, Codex, Gemini, Qwen Coder and AMP in separate containers for most task I do (although I've started to use AMP less and less), and either returns the last message of what they replied and/or a git diff of what exactly they did. Then I compare them side by side. If all of them got something wrong, I update the prompt, fire them off again. Always starting from zero, and always include the full context of what you're doing with the first message, they're all non-interactive sessions.

Sometimes I do 3x Codex instead of different agents, just to double-check that all of them would do the same thing. If they go off and do different things from each other, I know the initial prompt isn't specific/strict enough, and again iterate.

GPT-5.2 Thinking (with extended thinking selected) is significantly better in my testing on software problems with 40k context.

I attribute this to thinking time, with GPT-5.2 Thinking I can coax 5 minutes+ of thinking time but with Gemini 3.0 Pro it only gives me about 30 seconds.

The main problem with the Plus sub in ChatGPT is you can't send more than 46k tokens in a single prompt, and attaching files doesn't help either because the VM blocks the model from accessing the attachments if there's ~46k tokens already in the context.

Gemini 3 and Gemini 3 Flash identified the root cause and nailed the fix. GPT 5.1 Codex misdiagnosed the issue and attempted a weird fix despite my prompt saying “don’t write code, simply investigate.”

I run these tests regularly, and Codex has not impressed me. Not even once. At best it’s on par, but most of the time it just fails miserably.

Languages: JavaScript, Elixir, Python

The key is to adapt to this by learning how to parallelize your work, instead of the old way of doings things where devs are expected to focus on and finish one task at a time (per lean manufacturing principles).

I find now that painfully slow builds are no longer a serious issue for me. Because I'm rotating through 15-20 agents across 4-6 projects so I always have something valuable to progress on. One of these projects and a few of these agents are clear priorities I return to sooner than the others.

Those scripts are for running the docker command with all the ENV vars and settings. Whatever does that does NOT have to be Powershell if you don't want it to be.

Scary good.

But the good ones are not open. It's not even a matter of money. I know at OpenAI they are invite only for instance. Pretty sure there's vetting and tracking going on behind those invites.

So far it's rarely been the leading frontier model, but at least it's not full of dumb guardrails that block many legitimate use cases in order to prevent largely imagined harm.

You can also use Grok without sign in, in a private window, for sensitive queries where privacy matters.

A lot of liberals badmouth the model for obviously political reasons, but it's doing an important job.

Recently I tried working with both ChatGPT and Gemini (AI Studio) to take a really badly written PHP website and refactor it into MVC components. I've worked strictly through the web UI as this only involved a few files.

While both provided great guidance around how to approach disentangling this monolithic code, GPT failed miserably, generating code that was syntactically incorrect, and then doubling-down on it by insisting that it was correct and that errors were faults lying elsewhere. It literally generated code that lacked closing parenthesis and brackets.

In contrast, Gemini generated a perfectly working MVC version from the start. In both instances I did intentionally keep it on track to only separate the code into MVC and NOT to optimize anything, but it worked the first try. I've then taken it through subsequent refactorings and it's done superbly in that role.

So I can't speak to how well this works for large code bases, much less agentically. (my initial, very focused MVC refactor was about 1300 lines.) But when giving it a very specific task with strict guidance and rules, my results with Gemini were fantastic.

I'm not sure what your "empirical evidence and repeatable tests" is supposed to be. The AI not successfully converting a 3000 line C program to Python, in a test you probably designed to fail, doesn't strike me as particularly relevant.

Also, I suspect that AI could most likely guess that 80 lines of Python aren't correctly replicating 3000 lines of C, if you prompted it correctly.

Humans are very suggestible.

Yeah, it feels really strange sometimes. Bumping up against something that Codex seemingly can't work out, and you give it to Claude and suddenly it's easy. And you continue with Claude and eventually it gets stuck on something, and you try Codex which gets it immediately. My guess would be that the training data differs just enough for it to have an impact.

They did the same thing for gpt-5.1-codex-max (code name “arcticfox”), delaying its availability in the API and only allowing it to be used by monthly plan users, and as an API user I found it very annoying.

But Opus 4.5 exists.