History is written by the people who write stuff down.
Any conversation
Man, I LOVE naps! In fact, I mostly subsist on four or five 1-1/2 hour naps each day instead of one long over-night sleep period these days. I didn't set out to have a sleep schedule, but here I am. :-)
okรฉ, megdumรกltatok, a hรฉten telepรญtem a kis virtuรกlis รกllatseregletem mellรฉ (webszerver, mechanikus 1. generรกciรณs robotkezdemรฉny, led kijelzล szalag) az elsล ai agent chatbotomat, egyelลre Virtualbox Ubuntu alรก
Okay, you've got me, this week I'm installing my first AI agent chatbot next to my little virtual animal herd (web server, mechanical 1st generation robot initiative, LED display strip), for now under Virtualbox Ubuntu
szรณval technikailag nem adatkรถzpontnak neveznรฉm a fลterminรกlt, hanem maximum vallatรณszobรกnak MI รผgynรถkรถk rรฉszรฉre, jelenleg el vagyok akadva a Windows 11 telepรญtรฉsnรฉl, รฉs nรฉhรกny kรถnyvet รฉs scriptet mรฉg lementenรฉk rรณla รบgy biztonsรกgilag, mielลtt belefognรฉk a vallatรณszoba kialakรญtรกsรกba, itt tรฉnyleg olyan sandbox van, amibลl nincs nagyon merre mรกszkรกlni, kivรฉve, ha direkt kikรผldรถm valamelyik webes alkalmazรกsra
So technically I wouldn't call the main terminal a data center, but more of an interrogation room for MI agents. I'm currently stuck installing Windows 11, and I'd like to download some books and scripts just to be safe before I start building the interrogation room. It's really a sandbox here, with nowhere to go except if I send it directly to a web application.
Hello to friends. Holla for tools.
๐จโ๐ป : , , and Pragmata Pro
๐ช : NotePlan
๐ง : Overcast
๐ง : Allume
๐๏ธ : Mark Two (EDC), Pen Type-B
๐ณ : Anisota
New in agenttop.dev : panels open in your . ๐คนโโ๏ธ
โข Any panel can now split into its own pane, live, beside the table.
โข Works with all the popular multiplexers: , , ๐ฎ๐ป๐ฑ ๐ธ๐ถ๐๐๐.
โข run a panel on its own: agent-top mcp, agent-top slow, agent-top fails, agent-top advice.
โ The # MCP panel also lists the orphaned MCP processes that outlived their agent and are still eating memory.
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).