Yeah, thinking that after the last supply chain attack, people would be smarter than ship things with LiteLLM.

Does anybody know how Wayland performs on these?

Running Cosmic (which is a Wayland-only DE) on a DGX Spark. It just works.

I'm working on a side project that requires a lot of fine tuning of 3D worlds. Codex ended up creating thousands of artifacts, basically loads of screenshots, in its worktrees, and doesn't clean up after itself.

On a work project, we're moving financial processes from Excel to code, and Codex ended up creating and storing thousands of validation tests unnecessarily. That ended up eating 90GB after we let it loose on a Windows VM that we connected with a custom agent between codex and the VM.

This is definitely a Codex thing and I've never seen this happen in Claude Code or Antigravity.

It's silly I have to tell it to make part of the build process to clean old artifacts or it'll just default to keeping endless folders of test builds and old builds without cleaning them up. The same seems to usually be true with documentation and reference material.

There was a REALLY annoying period where I'd give it full control of a VM and a dedicated project folder and it'd continually refuse to delete anything I asked it to or just silently archive it, even though everything was already in a git repo. It seems to have gotten somewhat better about that now, but I still include "create cleanup scripts to delete unnecessary project content" in the default steps before doing the final merge on a change.

Prior to the above I never had an agents.md or memory enabled.

Heh, Claude recently (last couple of weeks) left behind several jj workspaces with many GBs of builds in my env.

Had to tell it to update it's agents.md to not do that...

Codex is obsession with validation tests. It drives me insane.

That's the only reason these models are good though. They don't one shot things. They get it wrong and then keep checking until they get it right. You gotta let them test

Agents prefer some sort of tests to check their output.

I would argue that the better you can “close the loop” the better. One of my favourite agent activities is giving it a firmware bug and JTAG access + a serial port. That setup means that flashing, debugging (inspecting variables and whatnot, setting breakpoints, etc), and logging can all happen completely autonomously.

Works especially well for transient/hard to repro bugs. It’ll either set breakpoints or write a monitoring script, go to sleep, get woken up by the harness when the bug trips, inspect state, put together a new build based on a hypothesis built from the debugging, flash it, and loop. I’ve had sessions run completely autonomously for over a day and come with a beautiful one-line solution to a gnarly race condition.

In that regard it’s like a human: you can read code all day if you want and you might get somewhere, but being able to inspect what happened, build a new theory, test it, and iterate is way more powerful 99% of the time.

This kind of approach works so well.

I was trying to upload HDR photos to Instagram and couldn't figure out how to make it preserve the HDR-ness of my photos, and was going back and forth with an agent - step by step we'd slowly iterate on a photo, I'd upload, then I'd download the jpg and give it to the agent and it'd think, change something in the format, and we'd try again.

I got impatient and just said fuck it and gave it chrome-devtools and a blank instagram account and a test photo, and it figured the whole thing out in about a half hour. I built a little browser-based tool from what it discovered, and I use it to run my HDR photos through to format them correctly for instagram and it works a treat.

Rust is notorious for this, one thing some people do is force Rust to have a salvage yard for builds so all those dependencies are shared by everything regardless of what you are building or where, but holy moly, can someone make Rust output smaller files? Hard drives are always having some reason to never go down to sane prices.

When I was younger I thought we would be having exabyte hard drives by now.

The issue is that people's idea of illegal immigrants are hardened criminals living a lift of crime, whereas in reality the majority of people that are being deported are normal people that overstayed their visa, ie. the low hanging fruit. So people can be both supportive of the policy but dismayed at the implementation, which is what we are broadly seeing here.

The Harvard-Harris survey linked above asks separately about “deporting immigrants who are here illegally and have committed crimes.” Support for that was at 78% in July.

There was opposition to Noem’s theatrics. But it seems like Mullen’s quieter approach has taken the heat off and most of the focus now is on the shit inflation and Iran war.

I found 3.8 Flash in Agy to be generally better than GPT 6, and only behind from Opus 5.5.

Thanks. To be honest, I don't know because I have a personal Max plan I use for this stuff and never set any telemetry up on it to get accurate metrics.

Notes was suggested in another comment as the next app in the series, so yeah I think it's a very good idea to do something like a workspace.

Thanks. Kinda jealous that you don't have to do slides to be honest.

That's how Claude works with pptx files, but the format is terrible to work with harnesses. Maybe that's going to improve but the it's currently the user experince is not good.

That's a really good suggestion, thanks. I've been thinking about what to do next, and notes is probably the natural progression, especially if you want to share between different devices with no cloud.