Hacker News Reader

Comment by InsideOutSanta | Hacker News Reader

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.

View on HN

Running an LLM to delete files seems like overkill to me. Couldn't a cron job do the same thing? Or is the clutter just put into random places, which, if true, seems like bad software, which then leads me to consider the output of LLMs in general, which then leads me to wonder why are we doing this?

But, I'm just wondering.

Oh it makes all sorts of temporary files and directories, sometimes in the right places as per UNIX filesystem conventions, but often not.

You could use snapshots or whatnot to reset the state whenever you like. Using an LLM to clean up files often seems like overkill to me.

Wouldn't a snapshot delete everything else you saved?

You keep your source tree on a separate file system with version control, one hopes.

So you only snapshot the rest. (And since your source tree is under version control, finding stray garbage there is straightforward unless you checked it in)

Just have an emphemal VM which you nume daily.

Its the only way I trust to install anything from these companies.

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got into a loop of downloading its docker image from ghcr them throwing it away immediately because it was supposedly out of date (iirc). 65mbps continuous transfers for a week until I looked at my network traffic and saw 500gb of rx per day.

Sisyphus' updater

Over eager use of /tmp is the worst. That’s RAM, my boy! Precious gold.

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??

It’s RAM unless you have swap enabled.

Did not know this. Was looking at htop yesterday scratching my head as to why there was over a GB in swap with ram <0.25 capacity. Had been teeing logs there pretty heavily

I just erased 20GB of Cursor’s cruft.

Is that cruft or past conversation history / subagent history and observability logs?

Just garbage. Temp files, worktrees that weren't removed after subagents finished, build files... all kinds of things.

But that's agent behavior, and not harness responsibility...?

Harnesses should be responsible IMO for managing lifecycle stuff, including worktrees and temp files.

It’s simple, deterministic stuff. At least most of the time.

Hence my question.

I assume auto-updates are handled by deterministic code that's far away from anything agents can touch (self-modifying harnesses like Autolith notwithstanding). With the same behavior showing up in multiple high-profile harnesses (Codex, Claude Code), it feels likely there must be some actual reason for doing it this way.

I didn’t see your reply.

It should be the harness responsibility to create / destroy things like worktrees and scratch spaces, and communicate to the agent (e.g. via system prompt) where the scratch space is and its purge schedule. Harness should also set appropriate env vars to make this work in tools.

> With the same behavior showing up in multiple high-profile harnesses (Codex, Claude Code), it feels likely there must be some actual reason for doing it this way.

I think fixing it is just not high on the priority list.

Went down the same hole, seeing all the massive logs, in plain text and as json, but ever eventually found the real culprit: snap caches of insane sizes.

Why wouldn’t you just rebuild the VM every day? Then you don’t have to run around trying to catch and delete things, it’s set up with exactly what you want.

It's funny how differently people use LLMs. I have agents that run for weeks, building something from a detailed plan with clear goals that gate progress. I don't like to constantly baby LLMs and tell them what to do. It would be inconvenient to rebuild the VM every day, then restore it and start everything again.

When did you create that workflow? I ask because I used to have something with a lot of carefully designed stuff like that back in Spring, but as the Summer progressed I found that getting out of the agent's way more and more has worked really well. I've been coding for 17 years, so this year has been a real journey as I've let go of some of the control of "this is how each step must be done". Those years of experience do mean that problems jump out pretty readily after the fact and and once you point out the problems to the agent it's pretty good at correcting them.

Today, I generally spend a few hours on a spec, let the agent run for 4 to 6 hours and I'm 90% there, with maybe a couple of days of tweaks, then a couple of days of iterations coming from user feedback after that. I've stopped using skills almost entirely now, mainly using them just to keep discovery of MCP or API docs out of context until needed. I have a few bullet points on testing and style in AGENTS.md, but I'm pretty sure it would probably run pretty close to what I'm looking for even without those these days.

Harness problem, or model problem?

Let's be real, what do you think wrote the harness?

> 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?

"In my dev VM". Everything of value in there is in a git repo.

Reply on news.ycombinator.com