Married for 13 years. Still in love, but struggling. So many paths we could go.
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).
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.
what are ya'lls favorite wikipedia page?
I myself is partial to the 'variations' entry for high fives
Catastrophic interference is also a favorite Wikipedia page and concept. The thing is, it doesnโt only happen to artificial neural networks, Iโve had it happen to me a few times. Especially with pin numbers, newer pins overwriting old ones and Iโm always scared when Iโm having hard time remembering something that this catastrophic interference applied and now the information is gone from my brain.
WezTerm for local and remote multiplexing really is the ideal experience - it's so much better than using zellij, tmux, zmx, and friends.. I don't think they pitch this feature hard enough on their site.
I think the in-terminal multiplexers have their place - e.g. if you need to access from mobile (no WezTerm there) or on machines where you simply don't want to install WezTerm for some reason. WezTermrm could probably eliminate that last one by packaging just the mux server.
โฆ
Something with people, bartender maybe, or something with no critical thinking, delivery person, taxi driver and such. Or I go back to being a DJ as I was doing when I was young.
@fastidiousprofilefollow
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyerswrote:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyerswrote:I had hit a throttle now. Thatโs a โsubtle" way to tell me to slow down.