What’s the difference between a script-kiddy and a real ? Abstraction. You can program your whole life without learning how to meaningfully abstract problems into simpler pieces that TRULY make the problem easier to understand.
I’m not talking about design patterns or vs . These tools can help. But to really simplify something for others, you need an intellectual empathy that many simply never figure out.
Any conversation
A lot of people write so much software to sandbox their AI agents.
I say don't bother. Just give your agent its own non-admin local user account. It's easier and much more effective.
I give my AI Full-Access. :p
My whole machine is set up to make way too much easily accessible with shell tools (email, stock trading, payments, mms group chats.) I can't trust it.
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...
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).
A thing I've been doing lately is trying to come to the same conclusions others have without looking their the direct techniques and code. Last night I tried to figure out why people do vector based retrieval for RAG and ended up running these experiments: n0tls.com/…/2026-09-03-i-think-…rag-with-grep.html
I'm still going to do an explore agent.