I really would like to see OpenAI’s focus on efficiency but everytime I use Codex, it wastes tokens like there’s no tomorrow, hitting week limit in a day, where I’m able to use Claude just fine. Maybe it’s based on the codebase, I don’t know, but I have better results with Claude than Codex.

▲

vorticalbox an hour ago | parent | next [-]

It might be your prompting.

My boss uses opus and gets good results when I use it always burns tokens. The other way is also true too I get great results with sol/terra but my boss does not.

▲

llama052 an hour ago | parent | prev | next [-]

At least with OpenAI you can use a third party harness like Pi.

▲

bicepjai an hour ago | parent | prev | next [-]

I had the opposite experience. Claude models and its harness feel like they are set to eat tokens for everything, especially if it’s ultracode effort. I have seen it spawn 6 agents and eat my 4-hour quota right in front of me. Codex is on point and follows instructions well even with max effort. I like my analogy of Claude being garrulous and Codex being laconic. If I see more limit hits in same sitting session, I have to rearrange my workflows. my experiments with qwen and deepseek have been good, cant wait to try glm and other models.

▲

throwup238 an hour ago | parent | next [-]

Just before I canceled my 20x Max sub I had a day where I had ~15% of my weekly I was trying to burn. I set it on ultracode and because I had set the max agents 32 for another project and forgot, the five research agents ended up spinning up a total of 26 subagents and burned through the remainder of my weekly in the span of 20 minutes before I noticed and shut it down.

“No, not like THAT!”

▲

wccrawford 6 minutes ago | parent | next [-]

Claude did the same thing to me the other day. I ran out of my 5 hr limit, and it went into my $100 credit they had given me. Multiple parallel agents. It ate it in no time flat.

When I checked, all that credit was gone, I still wasn't into the next 5 hours, and all the agents had failed, returning nothing.

I didn't even get anything for burning all that credit. If I had paid for it, I'd be very, very pissed.

▲

vanviegen an hour ago | parent | prev [-]

How can you burn through your weekly budget in 20 minutes? You'd hit your 5 hour budget way before that, right?

	▲	throwup238 16 minutes ago \| parent [-]
		The five hour budget is about 15% of the weekly on Max 20x. I had about 15% left.

▲

NyxWulf 41 minutes ago | parent | prev | next [-]

Here is an excerpt from the system prompt for UltraCode (Same for Fable,Opus,Sonnet):

"Ultracode. When a system-reminder confirms ultracode is on, that opt-in is standing: author and run a workflow for every substantive task by default. The goal is the most exhaustive, correct answer you can produce — token cost is not a constraint."

▲

StilesCrisis an hour ago | parent | prev [-]

Requesting ultracode is basically asking for maximum token usage. If you want to limit consumption, use medium or high.

▲

jimmydoe an hour ago | parent | prev [-]

same boat.

gpt 5.5/5.6 goes further on its own much more often than opus 4.8/5 does. codex capped ~300k context when claude does 1m.

I don't feel codex is saving tokens, and result is usually not as good imo.

	▲	gatio an hour ago \| parent [-]
		> codex capped ~300k context when claude does 1m. That's configurable in codex.. but there is a higher cost/usage to using it.