time
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).
I read
Still trying to figure out the boundaries of these tools' strengths without outsourcing important thinking, problem-solving, and the collective building-up of a mental model of the systems we're developing.
The shape of LLM tools as toolsโfit for a purpose, ergonomicโis becoming clearer, and human patterns of behavior with them that do more harm than good are also becoming easier to recognize.
Devs! Drop your so we can follow each other! Love to see the projects youโre working on. Mine: โ
โฆ
Gave up on github after the acquisition. Very glad I did, given the unsurprising decline since then.
github.com/Aeres-u99
I have created a small tool, codeatlas, that basically generates an index to codebase that your llm can lookup syper quick, github.com/Aeres-u99
there is also a cbz->pdf converter that I wrote for eink devices which is nice
a kis laptopnak pedig nincs elรฉg memรณriรกja, szรณval ezt a fลterminรกlt eredetileg programozรกsra vettem, azt nem tudom mรกr, mit akartam programozni vele, de pont รบgy zรบg, mint egy adatkรถzpont, รฉs hogyha egy kicsit korszerลฑsรญtem, a Gemma 4 LLM รฉppen visรญtva el fog tudni futni rajta
and the little laptop doesn't have enough memory, so I originally bought this main terminal for programming, I don't know what I wanted to program with it anymore, but it hums like a data center, and if I upgrade it a little, the Gemma 4 LLM will be able to run on it screaming