What if i don't have thoughts worth logging?
Any conversation
Big holiday today in Greece, bells ringing, bands singing, people gathered in the village, eating, enjoying life and I'm spending it inside coding. I don't feel bad and I'm not , it's just that I'm a bit odd. I don't like these forced gatherings. Feel stressful.
โฆ
Itโs called Dekapentavgoustos, meaning 15th of August in Greek, itโs a celebration of Virgin Mary. Itโs a big national holiday.
I think I may be use this for now to spill out my guts a bit. Set out boundaries guys. I was basically ignoring how important that is, whatever is at work, family, relations. Be loved being you, you don't have to meet any expectations beyond yours.
Just read a really interesting article on Japanese geography and history and it made me realise despite how great the Japanese are at adapting to a changing world they actually donโt have much of a history of being the centre of that innovation unchartedterritories.tomaspueyo.com/โฆ/how-japans-geography-determined-its
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).
Itโs using the
/firehose endpoint. Itโs an SSE endpoint publishing everything latest. Though I meant it to be used server-side, since itโs heavily rate-limited โ up to 3 conns under the same network, but I canโt control how clients decide to use it so.. ยฏ\_(ใ)_/ยฏ