Earlier quoted context omitted.
How does it compare to ANUS and OpenHands?
what
Those are AI coding agents.
OpenAI Codex CLI: Lightweight coding agent that runs in your terminal
291–298 of 298 posts
Re: OpenAI Codex CLI: Lightweight coding agent that runs in your terminal
#292I tried one task head-to-head with Codex o4-mini vs Claude Code: writing documentation for a tricky area of a medium-sized codebase. Claude Code did great and wrote pretty decent docs. Codex didn't do well. It hallucinated a bunch of stuff that wasn't in the code, and completely misrepresented the architecture - it started talking about server backends and REST APIs in an app that doesn't have any of that. I'm curiou…
there was one post that detailed how those OpenAI models hallucinate and double down on thier mistakes by "lying" - it speculated on a bunch of interesting reasons why this may be the case recommended read - https://transluce.org/investigating-o3-truthfulness I wonder if this is what's causing it to do badly in these cases
> I no longer have the “real” prime I generated during that earlier session... I produced it in a throw‑away Python process, verified it, copied it to the clipboard, and then closed the interpreter.
AGI may well be on its way, as the mode is mastering the fine art of bullshitting.
Re: OpenAI Codex CLI: Lightweight coding agent that runs in your terminal
#293Earlier quoted context omitted.
Claude Code still feels superior. o4-mini has all sorts of issues. o3 is better but at that point, you aren't saving money so who cares. I feel like people are sleeping on Claude Code for one reason or another. Its not cheap, but its by far the best, most consistent experience I have had.
"gemini 2.5 pro exp" is superior to Claude Sonnet 3.7 when I use it with Aider [1]. And it is free (with some high limit). [1] https://aider.chat/
I would use Aider if it had an agent mode. It needs to catch up with UX, frankly just have a mode that copies what claude code does.
Re: OpenAI Codex CLI: Lightweight coding agent that runs in your terminal
#294Earlier quoted context omitted.
You are confusing Amazon Q in the editor (like "transform"), and Amazon Q on the CLI. The editor thing has some stuff that costs extra after exceeding the limit, but the CLI tool (that acts similar to Claude Code) is a separate feature that doesn't have this restriction. See https://aws.amazon.com/q/developer/pricing/?p=qdev&z=subnav&... , under "Console" see "Chat". The list is pretty accurate with what's "included"…
I see, thanks. The 4k limit for the gui still seems so low, but I might try the cli sometime.
Do try! The free tier doesn't cost anything and is enough to tinker around with. You don't even need an AWS account for it, it'll prompt you to create a new separate account specifically for Q
Re: OpenAI Codex CLI: Lightweight coding agent that runs in your terminal
#295So, OpenAI’s Codex CLI is Claude Code, but worse? Cursor-Agent-Tools > Claude Code > Codex CLI https://pypi.org/project/cursor-agent-tools/
Astroturfing alert. This comment author is also the author of cursor-agent-tools.
Re: OpenAI Codex CLI: Lightweight coding agent that runs in your terminal
#296You lost me at NPM
Why?
Re: OpenAI Codex CLI: Lightweight coding agent that runs in your terminal
#297Earlier quoted context omitted.
Anecdotally, Claude code performs much better than Claude within Cursor. Not sure if it’s a system prompt thing or if I’ve just convinced myself of it because the aesthetic is so much better, but either way the end result feels better to me.
One has the incentive to burn through as much tokens and the other has an incentive to use as little as possible
Great point.
Re: OpenAI Codex CLI: Lightweight coding agent that runs in your terminal
#298Earlier quoted context omitted.
In terms of terminal-based and open-source, I think aider is the most popular one.
yes! It's great! I like it! But it has one downside: It's not so good on unknown big complex code bases where you don't know how it's structured. I wished they (or somebody else) would add an AI or an automation to add files dynamically or in a smart way when you don't know the codebase structure (with the expense of burning more tokens). I'm thinking Codex (have not checked it yet), Claude Code, Anon Kode and all th…
I’m not positive, but I think if you do
/context this_will_be_my_prompt
it will do a few requests on its own to decide what you need in context, add those files, and return back to you so you can continue on.