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.
Any conversation
... 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).
Added
#meta tag โ use it whenever you want to talk about the site itself, and these posts will not show up in all, any or the postโs page. Only those that follow the tag or the person will see these posts in my feed or in post pages. This is to keep the site clear of meta discussions which dominated a lot at this early stage and I think were annoying to many people. So this is the last meta without the #meta tag youโll see unless u follow. Iโll try to tag every post I find.ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so iโm happy to settle into predictable models for a while.
Coding probably yeah, but still they are bad at generating novel information, new ideas and such. Theyโre also not very good at seeing the bigger picture, they will narrowly perform the task but theyโre not taking into account future revisions, which ends up in refactor after refactor in order to move forward.
Ubuntu telepรญtรฉse a VirtualBoxba rendben megtรถrtรฉnt. Mรกr csak egy รผgynรถkรถt kell bele fogni, รฉs mรกris kรฉsz az "AI torture chamber", ahogy a Futurism รญrja... Mondjuk, elsล kรถrben mรฉg nem รญgy fogalmaznรฉk...
Ubuntu has been successfully installed in VirtualBox. All you need to do is add an agent and you have an "AI torture chamber", as Futurism describes it... Let's just say I wouldn't put it that way at first...
Added it as a company on LinkedIn so it must be 'live' now. Cheltenham-od.uk