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

▲

strongpigeon 3 hours ago | parent | next [-]

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 3 hours ago | parent [-]

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.

▲

bonesss 3 hours ago | parent | next [-]

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…

▲

strongpigeon 3 hours ago | parent | prev [-]

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 3 hours ago | parent [-]

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 42 minutes ago | parent [-]

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.

	▲	raw_anon_1111 18 minutes ago \| parent [-]
		If you look at the current hiring trends and how much longer it is taking developers to get jobs these days, a mid level ticket taker is definitely screwed between a flooded market, layoffs and AI. By definition, this is the worse AI coding will ever be and it’s pretty good now.

▲

motbus3 3 hours ago | parent | prev | next [-]

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 2 hours ago \| parent [-]
		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

▲

650REDHAIR 3 hours ago | parent | prev | next [-]

I hit the Claude limit within an hour.

Most of my tokens are used arguing with the hallucinations.

I’ve given up on it.

	▲	hnsr 2 hours ago \| parent \| next [-]
		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
	▲	TuxSH 2 hours ago \| parent \| prev \| next [-]
		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.
	▲	theshrike79 2 hours ago \| parent \| prev [-]
		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.

▲

petesergeant 3 hours ago | parent | prev | next [-]

I have a found Codex to be an exceptional code-reviewer of Claude's work.

▲

Areibman an hour ago | parent | prev [-]

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...