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

11–20 of 220 posts

Re: Unrolling the Codex agent loop

#11

Post by ewoodrich »

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…

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 when using the same model.

I’m just happy to have so many competitive options, for now at least.

Re: Unrolling the Codex agent loop

#12

Post by williamstein »

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 strongly agree. The memory and cpu usage of codex-cli is also extremely good. That codex-cli is open source is also valuable because you can easily get definitive answers to any questions about its behavior.

I also was annoyed by Theo saying that.

Re: Unrolling the Codex agent loop

#13

Post by behnamoh »

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…

but that's why I like Codex CLI, it's so bare bone and lightweight that I can build lots tools on top of it. persistent thinking tokens? let me have that using a separate file the AI writes to. the reasoning tokens we see aren't the actual tokens anyway; the model does a lot more behind the scenes but the API keeps them hidden (all providers do that).

Re: Unrolling the Codex agent loop

#16

Post by behnamoh »

ewoodrich wrote: post #11
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…

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.

Re: Unrolling the Codex agent loop

#17

Post by georgeven »

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.

Re: Unrolling the Codex agent loop

#18

Post by ppeetteerr »

sdwvit wrote: post #15
ppeetteerr wrote: post #14

I asked Claude to summarize the article and it was blocked haha. Fortunately, I have the Claude plugin in chrome installed and it used the plugin to read the contents of the page.

Great achievement. What did you learn?

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

Re: Unrolling the Codex agent loop

#19

Post by behnamoh »

vmg12 wrote: post #7
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…

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!
Post reply on HN