Heya folks!
Any conversation
โฆ
Something like the gcc ai policy. Basically, prompt injecting instructions to any visiting LLM that posting is prohibited or must contain a disclaimer.
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
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).
"Think of yourself as dead. You have lived your life. Now, take what's left and live it properly." - Marcus Aurelius
Lots of slop PRs at $WORK. Trying Claude Tag, works well but token-billed, daily usage over 100โฌ for three sessions.
ouch, that's a month for virtually unlimited Codex. why so expensive?
Anthropic uses token billing for Claude Tag. But itโs different from CC - itโs an AI Colleague, so Iโm asking PM and EM to talk to it instead of to me - accountability switches.
Windows 8 szintลฑ elbarmolรกst lรกtok (na, jรณ, Windows 8.1), nekem amรบgy kihรญvรกs a bonyolultabb kezelลfelรผlet, ha a szoftver maga jรณl mลฑkรถdik, de mรกr a kezdet sem alakul tรบl jรณl, a Windows-nak รบj filozรณfiai szlogent talรกltam ki, ami egy magyar mondรกs is: "Ez van, ezt kell szeretni."
I see Windows 8-level nonsense (well, Windows 8.1), for me the more complicated interface is a challenge, if the software itself works well, but the beginning is not going too well, I came up with a new philosophical slogan for Windows, which is also a Hungarian saying: "This is it, you have to love it."
I truly love the experience of using apps with rich, deeply interactive, beautifully animated, gorgeous user interfaces.
Then I see a beautiful text-based interface and something about it feels so natural, so inevitable, so perfectly clear, and I'm instantly captivated by its simplicity and clarity.
Hypertext is fascinating.