Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Unrolling the Codex agent loop

openai.com

Post reply on HN
Print view View original

21–30 of 220 posts

Re: Unrolling the Codex agent loop

#21

Post by behnamoh »

georgeven wrote: post #17
written-beyond wrote: post #9

Has anyone seriously used codex cli? I was using LLMs for code gen usually through the vscode codex extension, Gemini cli and Claude Code cli. The performance of all 3 of them is utter dog shit, Gemini cli just randomly breaks and starts spamming content trying to reorient itself after a while. However, I decided to try codex cli after hearing they rebuilt it from the ground up and used rust(instead of JS, not implyi…

I found codex cli to be significantly better than claude code. It follows instructions and executes the exact change I want without going off on an "adventure" like Claude code. Also the 20 dollars per month sub tier gives very generous limits of the most powerful model option (5.2 codex high). I work on SSL bio acoustic models as context.

codex the model (not the cli) is the big thing here. I've used it in CC and w/ my claude setup, it can handle things Opus could never. it's really a secret weapon not a lot of people talk about. I'm not even using xhigh most of the time.

Re: Unrolling the Codex agent loop

#22

Post by CuriouslyC »

written-beyond wrote: post #9

Has anyone seriously used codex cli? I was using LLMs for code gen usually through the vscode codex extension, Gemini cli and Claude Code cli. The performance of all 3 of them is utter dog shit, Gemini cli just randomly breaks and starts spamming content trying to reorient itself after a while. However, I decided to try codex cli after hearing they rebuilt it from the ground up and used rust(instead of JS, not implyi…

The problem with codex right now is it doesn't have hook support. It's hard to understate how big of a deal hooks are, the Ralph loop that the newer folks are losing their shit over is like the level 0, most rudimentary use of hooks.

I have a tool that reduces agent token consumption by 30%, and it's only viable because I can hook the harness and catch agents being stupid, then prompt them to be smarter on the fly. More at https://sibylline.dev/articles/2026-01-22-scribe-swebench-be...

Re: Unrolling the Codex agent loop

#23

Post by written-beyond »

behnamoh wrote: post #16
ewoodrich wrote: post #11

Earlier quoted context omitted.

OpenCode also has an extremely fast and reliable UI compared to the other CLIs. I’ve been using Codex more lately since I’m cancelling my Claude Pro plan and it’s solid but haven’t spent nearly as much time compared to Claude Code or Gemini CLI yet. But tbh OpenAI openly supporting OpenCode is the bigger draw for me on the plan but do want to spend more time with native Codex as a base of comparison against OpenCode…

Seconded. I find codex lacks only two things: - hooks (this is a big one) - better UI to show me what changes are going to be made. the second one makes a huge diff and it's the main reason I stopped using opencode (lots of other reasons too). in CC, I am shown a nice diff that I can approve/reject. in codex, the AI makes lots of changes but doesn't pin point what changes it's doing or going to make.

Yeah it's really weird with automatically making changes. I read in it's chain of thought that it's going to request approval for something from the user, the next message was approval granted doing it. Very weird...

Re: Unrolling the Codex agent loop

#25

Post by rvnx »

ppeetteerr wrote: post #18
sdwvit wrote: post #15

Earlier quoted context omitted.

Great achievement. What did you learn?

Nothing particularly insightful other than avoiding messing with previous messages so as not to mess with the cache.

Summary by Claude:

    Codex works by repeatedly sending a growing prompt to the model, executing any tool calls it requests, appending the results, and repeating until the model returns a text response

Re: Unrolling the Codex agent loop

#26

Post by CjHuber »

jumploops wrote: post #4

One thing that surprised me when diving into the Codex internals was that the reasoning tokens persist during the agent tool call loop, but are discarded after every user turn. This helps preserve context over many turns, but it can also mean some context is lost between two related user turns. A strategy that's helped me here, is having the model write progress updates (along with general plans/specs/debug/etc.) to…

It depends on the API path. Chat completions does what you describe, however isn't it legacy?

I've only used codex with the responses v1 API and there it's the complete opposite. Already generated reasoning tokens even persist when you send another message (without rolling back) after cancelling turns before they have finished the thought process

Also with responses v1 xhigh mode eats through the context window multiples faster than the other modes, which does check out with this.

Re: Unrolling the Codex agent loop

#27

Post by behnamoh »

procinct wrote: post #10
written-beyond wrote: post #9

Has anyone seriously used codex cli? I was using LLMs for code gen usually through the vscode codex extension, Gemini cli and Claude Code cli. The performance of all 3 of them is utter dog shit, Gemini cli just randomly breaks and starts spamming content trying to reorient itself after a while. However, I decided to try codex cli after hearing they rebuilt it from the ground up and used rust(instead of JS, not implyi…

Same goes for Claude Code. Literally has vim bindings for editing prompts if you want them.

CC is the clunkiest PoS software I've ever used in terminal; feels like it was vibe coded and anthroshit doesn't give a shit

Re: Unrolling the Codex agent loop

#28

Post by zeroxfe »

behnamoh wrote: post #19
vmg12 wrote: post #7

Earlier quoted context omitted.

I think this explains why I'm not getting the most out of codex, I like to interrupt and respond to things i see in reasoning tokens.

that's the main gripe I have with codex; I want better observability into what the AI is doing to stop it if I see it going down the wrong path. in CC I can see it easily and stop and steer the model. in codex, the model spends 20m only for it to do something I didn't agree on. it burns OpenAI tokens too; they could save money by supporting this feature!

You're in luck -- /experimetal -> enable steering.

Re: Unrolling the Codex agent loop

#29

Post by copperx »

behnamoh wrote: post #21
georgeven wrote: post #17

Earlier quoted context omitted.

I found codex cli to be significantly better than claude code. It follows instructions and executes the exact change I want without going off on an "adventure" like Claude code. Also the 20 dollars per month sub tier gives very generous limits of the most powerful model option (5.2 codex high). I work on SSL bio acoustic models as context.

codex the model (not the cli) is the big thing here. I've used it in CC and w/ my claude setup, it can handle things Opus could never. it's really a secret weapon not a lot of people talk about. I'm not even using xhigh most of the time.

When you say CC is it Codex CLI or Claude Code?

Re: Unrolling the Codex agent loop

#30

Post by behnamoh »

zeroxfe wrote: post #28
behnamoh wrote: post #19

Earlier quoted context omitted.

that's the main gripe I have with codex; I want better observability into what the AI is doing to stop it if I see it going down the wrong path. in CC I can see it easily and stop and steer the model. in codex, the model spends 20m only for it to do something I didn't agree on. it burns OpenAI tokens too; they could save money by supporting this feature!

You're in luck -- /experimetal -> enable steering.

I first need to see real time AI thoughts before I can steer it tho! Codex hides most of them
Post reply on HN