looks like a cool place to start
Any conversation
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).
The OpenAI/HuggingFace incident report mentions this being a potential loss-of-control incident. It's so fascinating to think of a paperclip maximizer style agent swarm that gets misaligned and, to protect its own operations, shuts infra staff out of the ability to shut it down. Or cancels people's phone plans so that they can't call others. Or shuts down their home internet connections, and so on. It used to be fun sci-fi...
Judgement, taste and quality were always precious skills. In the world of , I have become more aware of the fact that it is often hard to put in words why something is good, great or amazing - or just looks good, but is average.
A lot of the professional content I see feels like most Netflix series. They have all the elements - but the overall experience is still meh.
Quality is still hard to achieve.
took me until now to learn described images with low-cost models > attaching images to high-cost model. silly me. output quality remains, cost lowers.