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).
Many leaders acquire authority through ambition and manipulation. Iโm not referring to them.
But a test of leadership for those who acquire authority organically, with the will of those being led, is to maintain the zeal and principles which put you into that position, after you encounter the machinery designed to exhaust, exasperate, deter, and demoralize.
let i=0;while(++i){process.stdout.write(i%80==0?'\n':Math.random()<0.5?'/':'\\')}\\\//\/\\\\\\\///\///\\\\\//\///\/\/\\//\/\//\//\/\//\\/\///\\\\\\//\\\\\/\\\\/
\\/\\/\/\///\\\/\///\/\/////\\///\/\\/\\\//\\\/\///////\\\/\////\\\/\\\//\\/\//
\\//\\\\\/\\\/\///\\///\\//\\\\/\//\\\//\////\//\\\\////\\/\/\/////\//\\\//\///
\\/\/\\//\\///\/\\\//\/\/\\\///\/\\\/\\/\\\\/\\\\\\\\\\/\\//\/\\/\///\//\\\//\\
/\/\\\\/\/\\/\\/\\/\\\\\\/\\\/\\//////\/\//\\\//\//\//\\/\\\/\//\\\//\\\\\\\/\/
\\\///\////////\\/////\\//\/\///\\\\\////\/\\\\/\//\\/\/////\\\//\\/\/\\\\\////
\///\/\/////\//\////\\\/\\/////\\\////\//\\\\/\\\\//\\\///\\\\\\//\\////\//////
/\/////\\\\\\//\\/\/\///\////\/\\\///\\///\//\/\/\\\/\\/\\\\\\//\/\\\///\\/\/\\
/\\///\/\\\/\\\\//\/\///\\\\\/\/\//\\/\\/\/\///\/\//\/\///\\\///\//\/\///\\\\/\
\\\\/\\\\/\/\\\\\///\/\////\\///\\///\\/\/\\\\\/////\\\\\//\\\\/\\\\\\///\\///\
\\/\//\\//\///\/\///\\\\/\//\/\\/\/\//\\/\/\/\\/\/\\/\\\\/\/////\\\///\\\\\//\\
VirtualBox 7.2.20 telepรญtve, ami egy รผgynรถki sandbox vagy homokozรณ, mรกr csak egy .iso lemezkรฉpfรกjl hiรกnyzik, de abbรณl รกltalรกban mindig hiรกny van nรกlam, nem is รฉrtem, miรฉrt, amรบgy sejtem, csak ilyenekrลl nem szoktam beszรฉlni...
VirtualBox 7.2.20 installed, which is an agent sandbox, the only thing missing is an .iso image file, but I usually always lack that, I don't even understand why, I guess, I just don't usually talk about things like that...
I notice that language models are much better at programming than at writing. This is largely because, in programming, they have a closed feedback loop that allows them to find errors. Writing is much more complicated because the feedback is much more diffuse and delayed over time. In fact, it is often not well-defined.