| ▲ | icantevenhold 5 hours ago |
| It also fills up my HD with old versions.
I investigated and it took up something like 12 gigabytes in total on my system; which seems insane to me, it’s just a harness? People moan about how badly made Claude code is but Codex seems much worse on every metric |
|
| ▲ | InsideOutSanta 5 hours ago | parent | next [-] |
| All of the harnesses I've used are terrible at cleaning up after themselves. They leave all kind of clutter behind, to the point where on my dev VM, I now have an LLM run once a day to just look through the disk and delete everything that looks like it's leftover garbage. It's like fighting fire by employing an arsonist. |
| |
| ▲ | judge2020 2 hours ago | parent | next [-] | | Installed "clor.com" and it got into a loop of downloading its docker image from ghcr them throwing it away immediately because it was supposedly out of date (iirc). 65mbps continuous transfers for a week until I looked at my network traffic and saw 500gb of rx per day. | |
| ▲ | sroussey 5 hours ago | parent | prev | next [-] | | I just erased 20GB of Cursor’s cruft. | |
| ▲ | TeMPOraL 5 hours ago | parent | prev | next [-] | | Is that cruft or past conversation history / subagent history and observability logs? | | |
| ▲ | InsideOutSanta 4 hours ago | parent [-] | | Just garbage. Temp files, worktrees that weren't removed after subagents finished, build files... all kinds of things. | | |
| ▲ | thdr 4 hours ago | parent [-] | | But that's agent behavior, and not harness responsibility...? |
|
| |
| ▲ | klodolph an hour ago | parent | prev | next [-] | | Over eager use of /tmp is the worst. That’s RAM, my boy! Precious gold. | | |
| ▲ | arcanemachiner 38 minutes ago | parent [-] | | I don't think that's always true. Although I just looked into it, and even Ubuntu 26.04 appear to default to tmpfs for /tmp storage, so I guess it's fairly universal now. Not sure if I agree with that idea in principle... What's wrong with just wiping it intermittently?? |
| |
| ▲ | agentdev001 5 hours ago | parent | prev | next [-] | | Harness problem, or model problem? | | | |
| ▲ | NooneAtAll3 5 hours ago | parent | prev [-] | | > I now have an LLM run once a day to just look through the disk and delete everything that looks like it's leftover garbage ...are you sure it wouldn't consider your personal files garbage? | | |
|
|
| ▲ | umvi 5 hours ago | parent | prev | next [-] |
| Can't wait until we get really well designed harnesses written in a compiled language that doesn't bloat my computer. Will probably have to be written by a company other than OpenAI because codex is like the exact opposite of everything I just listed |
| |
| ▲ | dummydummy1234 5 hours ago | parent | next [-] | | Codex is written in rust, fyi... Not that I disagree. | | |
| ▲ | umvi 5 hours ago | parent | next [-] | | Oh, I haven't been keeping up. I assumed it was still TS since it prompts me to run npm all the time. | | |
| ▲ | Twirrim 5 hours ago | parent [-] | | They just use npm as a binary delivery mechanism, for whatever reason (I guess they expect all their users to have npm?) |
| |
| ▲ | lynx97 5 hours ago | parent | prev [-] | | Which generates unnecessarily huge binaries. | | |
| ▲ | rfgplk 5 hours ago | parent [-] | | It's because they statically linked it, and probably rely on a trillion pointless crates (as is standard in Rust development). A good statically linked harness can easily be ~5MB MAX |
|
| |
| ▲ | smartmic 5 hours ago | parent | prev | next [-] | | Found this one: https://usehax.dev/ Anyone experiences with it? | | |
| ▲ | serf 5 hours ago | parent [-] | | it's okay. it's minimal and somewhat opinionated, not integrated well with memory subsystems (although that's kind of the point) my only real criticism is that last I played with it it deals with slow provider responses very poorly , so lots of locally hosted llms require a lot of tuning to get it to handle streaming/non-streaming/timers well. way less minimal (but still pretty minimal) I prefer Pi; but different markets I think. hax fit my openbsd laptop well, espescially since Pi and related derivatives are kind of un-spokenly incompatible with the BSDs. | | |
| ▲ | OleksandrC 4 hours ago | parent [-] | | (author passing by) Could you please report the issues you've experienced on the repo? I did quite a bit of testing myself on local models (Qwen, Ornith, Gemma, Muse Glimmer) with llama.cpp, and they all worked fine. Details would be helpful. Also one brief note for Codex users specifically. hax can work out-of-the-box as codex-cli drop-in replacement (since it can use the already authenticated codex token), so it's super easy to try it - basically it will be a zero-config experience. |
|
| |
| ▲ | rfgplk 5 hours ago | parent | prev | next [-] | | Just write your own harness. Ironically Codex/Claude are both abysmal. | | |
| ▲ | theowaway213456 5 hours ago | parent | next [-] | | How do you even write a harness that can use a Claude subscription? I thought it was not allowed by Anthropic's ToS and can get you banned? | | | |
| ▲ | sroussey 5 hours ago | parent | prev [-] | | I did, and the weird things you have to do to make work at least decent. I’ve been doing evals and I got some things better than opencode but not as good as pi. Though my goal is to optimize for a browser and browser based llm so it can create stuff in a web container or at least generate ui by requesting json schema (a2ui style). |
| |
| ▲ | joquarky 2 hours ago | parent | prev | next [-] | | They're not made of fairy dust; you can build your own. | |
| ▲ | koe123 5 hours ago | parent | prev [-] | | Omp |
|
|
| ▲ | nicce 5 hours ago | parent | prev | next [-] |
| > People moan about how badly made Claude code is but Codex seems much worse on every metric Also, it feels that chatgpt.com and aistudio.google.com are the buggiest websites I have seen for long time. Why it is always something related to LLMs? |
| |
| ▲ | sdcfgy 5 hours ago | parent | next [-] | | All the LLM turds we've curled out at work are the same. | |
| ▲ | demibabs 4 hours ago | parent | prev | next [-] | | It’s actually insane how buggy the Gemini web version is (or at least was a few months ago, since I stopped using it). | |
| ▲ | bakugo 5 hours ago | parent | prev | next [-] | | Because they're the most likely to be 100% vibe coded. And as much as some people still deny it, AI code = buggy code. | |
| ▲ | platevoltage 4 hours ago | parent | prev | next [-] | | ChatGPT.com is dreadful. The whole thing chokes when the conversation gets moderately long. It's amazing that it's been allowed to stay this way. | |
| ▲ | slopinthebag 3 hours ago | parent | prev [-] | | [dead] |
|
|
| ▲ | whimblepop 5 hours ago | parent | prev | next [-] |
| My preferred Nix package for this patches at least that behavior out, afaict:
https://github.com/numtide/llm-agents.nix/blob/dc285bfd94ec7... https://github.com/numtide/llm-agents.nix/ |
|
| ▲ | jonplackett 5 hours ago | parent | prev | next [-] |
| It’s extremely ironic that the software that’s meant to end software is itself pretty terrible software. |
|
| ▲ | AgharaShyam 5 hours ago | parent | prev | next [-] |
| for some reason I had 11 separate codex and codex-code-mode-host binaries in my ~/.bun/install/cache/@openai . each weighing about ~300 MB. might be worth a look to anyone running low on disk space. |
|
| ▲ | verdverm 36 minutes ago | parent | prev | next [-] |
| Don't get me started on my custom NES harness, it generates ~10MB per turn. At least the harness itself is pretty tiny |
|
| ▲ | charliermarsh 5 hours ago | parent | prev | next [-] |
| I haven't worked with the update subsystem before but that seems like an oversight to me. I'm gonna fix it. |
|
| ▲ | rfgplk 5 hours ago | parent | prev | next [-] |
| Yep, .codex/packages/standalone/releases keeps all the old versions. Also each codex bin is somehow ~300MB. |
| |
|
| ▲ | orliesaurus 4 hours ago | parent | prev | next [-] |
| what's the lazy way to check? can you share where/how you cleaned up? |
|
| ▲ | Onavo 5 hours ago | parent | prev | next [-] |
| Even if you installed codex with brew? |
|
| ▲ | bayindirh 5 hours ago | parent | prev [-] |
| Remember: VSCode runs a complete headless Eclipse instance as its Java LSP, so I don't expect quality code from any of the big companies anymore. |
| |
| ▲ | dwattttt 5 hours ago | parent | next [-] | | Are you referring to something built into VS Code, or an extension? It looks you're talking about https://github.com/redhat-developer/vscode-java, which is RedHat's doing. | |
| ▲ | accrual 5 hours ago | parent | prev [-] | | Yes, my DEV VM tended to fill up with VSCode backups as well. I finally expanded the disk so it's less of an issue today, but for a while ENOSPC was resolved by cleaning up ~/.vscode-server/cli/servers. |
|
