Sigh. On the heels of , I just went into our garage to find a panel of insulation fallen to the ground, riddled with mouse droppings. 🤢😫
Cleaned it up (gloved and masked, naturally), but probably means we need to re-insulate the whole garage. Which will undoubtedly uncover a leak or some other issue. The fun never ends!
Any conversation
I've avoided social media (except YouTube) all my life, but this looks like it could finally be a better way to do it.
Maybe I'll keep a running journal of cool things I'm working on here or weird bugs that I've found. Or just the struggles of coding.
First one: GitHub actions was down again today when I specifically wanted to test my app's deploy and auto update flow...
working on permanent.sh a coding agent for the growing and seemingly permanent underclass of people that are left behind by the unbelievable pace of progress in ai
the big labs are fighting over felonybench (exploitbench) and google deepmind ceo left to work on drug discovery
It’s using the
/firehose endpoint. It’s an SSE endpoint publishing everything latest. Though I meant it to be used server-side, since it’s heavily rate-limited — up to 3 conns under the same network, but I can’t control how clients decide to use it so.. ¯\_(ツ)_/¯Really glad to be using Haskell for work - especially in today's climate with agentic coding.
Our team uses containers to keep our development environment consistent across team members, though, and most agent sandbox approaches want to either offload your work fully to the cloud or they want to sandbox the agent harness process itself.
We're not ready for full cloud based development (yet?) and sandboxing just the agent doesn't work for us when the agent needs to run docker.
... because letting the agent run docker gives them a too-easy escape hatch from their sandbox.
So we're currently stuck with using VMs. This turns out to be tricky but seems do-able.
My current approach is to provision a VM image and use Incus for the execution. My main goal is to keep my current workflow of local/non-agent dev working seamlessly and share the source with the VM/agent.
This means sharing my working dirs with the agent VM but overlaying artifact dirs from VM-owned block devices so we don't take too big of an IO perf hit.
I also don't want the agent to be able to
git push so that means we need some quirky git config to rewrite origin paths and thread through some agent specific PATs ("thanks" GitHub) for read-only repo access. These ALSO need to be threaded through to the development containers - they need to clone private repos.... in the end, this seems to work but I haven't lived with it for long.
There are still some quality of life issues to work out, but I think it'll work out.
At this point, I've removed all coding agents from my host - and that's nice.
Curious, why does using Haskell make a difference here?
It's tangential to the sandboxing topic, really. I started the first post with a broader intent in mind and then elaborated on the sandboxing setup I'm working on.
For AI-assisted coding, though, it's nice because Haskell provides a lot of feedback earlier in the development process compared to lots of other languages. It tends to work once it compiles (obviously not all the time).