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

211–220 of 220 posts

Re: Unrolling the Codex agent loop

#211

Post by fragmede »

tomashubelbauer wrote: post #180
energy123 wrote: post #153

Earlier quoted context omitted.

How do you achieve coordination? Or do you require the tasks be sufficiently unrelated?

I do this sometimes - let Claude Code implement three or four features or fixes at the same time on the same repository directory, no worktrees. Each session knows which files it created, so when you ask CC to commit the changes it made in this session, it can differentiate them. Sometimes it will think the other changes are temporary artifacts or results of an experiment and try to clear them (especially when your C…

I'm insane and run sessions in parallel. Claude.md has Claude committing to git just the changes that session made, which lets me pull each sessions changes into their own separate branch for review without too much trouble.

Re: Unrolling the Codex agent loop

#212

Post by fragmede »

rmunn wrote: post #128
fragmede wrote: post #85

Earlier quoted context omitted.

If the software is, say, Audacity, who's target market isn't specifically software developers, sure, but seeing as how Claude code's target market has a lot of people who can read code and write software (some of them for a living!) it becomes material. Especially when CC has numerous bugs that have gone unaddressed for months that people in their target market could fix . I mean, I have my own beliefs as to why they…

> ... numerous bugs that have gone unaddressed for months that people in their target market could fix . THIS. I get so annoyed when there's a longstanding bug that I know how to fix, the fix would be easy for me, but I'm not given the access I need in order to fix it. For example, I use Docker Desktop on Linux rather than native Docker, because other team members (on Windows) use it, and there were some quirks in ho…

GitHubactions is a bit of a special case, because it's mostly run in their systems, but that's when you just fork and, I mean, the problems with their (original) branch is their problem.

Re: Unrolling the Codex agent loop

#213

Post by Sateeshm »

adam_patarino wrote: post #199
coffeeaddict1 wrote: post #196

Earlier quoted context omitted.

Usually, I tell the agent to try out an idea and if I don't like the implementation or approach I want to undo the code changes. Then I start again, feeding it more information so it can execute a different idea or the same one with a better plan. This also helps the context window small.

Can’t you use git for that? I do that often and just revert changes. It does require me to commit often but that’s probably good anyways.

It's about not polluting the context. AI doesn't need information about things that didn't work in the new requests' context.

Re: Unrolling the Codex agent loop

#214

Post by adam_patarino »

Sateeshm wrote: post #213
adam_patarino wrote: post #199

Earlier quoted context omitted.

Can’t you use git for that? I do that often and just revert changes. It does require me to commit often but that’s probably good anyways.

It's about not polluting the context. AI doesn't need information about things that didn't work in the new requests' context.

That's interesting. I use those moments to show it what not to do. Does it not just repeat the mistakes?

Re: Unrolling the Codex agent loop

#215

Post by gzalo »

mike_hearn wrote: post #187
gzalo wrote: post #141

Wow, this part where they describe skills sounds quite odd https://github.com/openai/codex/blob/99f47d6e9a3546c14c43af9... Why wouldnt they just expose the files directly? Having the model ask for them as regular files sounds a bit odd

That's the whole point of skills - they help reduce context window usage by letting the model open only the ones that are relevant.

I know, but part of the logic from below the line I linked could have been deterministic, it could benefit from a single "load skill" tool that just loads the files client side!

Re: Unrolling the Codex agent loop

#216

Post by georgeven »

samstevens wrote: post #202
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.

hey I’m just spinning up in ssl birdsong models (BirdMAE, SongMAE, etc) can you share any resources? My email is stevens.994@osu.edu, would love to read your work.

dude you are spinning up my models! Emailing you!

Re: Unrolling the Codex agent loop

#217

Post by sakesun »

Razengan wrote: post #100
frumplestlatz wrote: post #62

Earlier quoted context omitted.

At this point I just assume Claude Code isn't OSS out of embarrassment for how poor the code actually is. I've got a $200/mo claude subscription I'm about to cancel out of frustration with just how consistently broken, slow, and annoying to use the claude CLI is.

Anthropic/Claude's entire UX is the worst among the bunch

Clause web is very slow compare to others.

Re: Unrolling the Codex agent loop

#218

Post by phrotoma »

alabhyajindal wrote: post #190
vorticalbox wrote: post #189

Earlier quoted context omitted.

yes [0] > The Rust implementation is now the maintained Codex CLI and serves as the default experience [0] https://github.com/openai/codex/tree/main/codex-rs#whats-new...

They should switch to a native installer then. Quite confusing

Yeah I'm out here installing a billion node things to have codex hack on my python app. Def gonna look into a standalone rust binary.

Re: Unrolling the Codex agent loop

#220

Post by lighthouse1212 »

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…

[dead]
Post reply on HN