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.
Any conversation
... 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).
Economist Lant Pritchett describes shifts in ideas as silly, controversial, progressive, then obvious.
Also:
"Radio has no future. X-rays are clearly a hoax. The aeroplane is scientifically impossible." - Lord Kelvin
". No wireless. Less space than a nomad. Lame." - CmdrTaco
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/โฆ/2026-09-03-i-think-โฆrag-with-grep.html
I'm still going to do an explore agent.
@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:The abuse (in my opinion) of the auto-translate feature is super annoying. Thanks goodness for โblockโ.
mรฉg csak barรกtkozom azzal a gondolattal, hogy a Gemma 4 miatt elลszรถr is Windows 11 lesz a gรฉpen (meg hogy Szentmihรกlyon presszรณ lesz), ezรฉrt nehรฉz elkezdeni
I'm still getting used to the idea that because of Gemma 4, I'll have Windows 11 on my computer first (and that there will be a presso in Szentmihรกly), so it's hard to get started.
Vagyis attรณl mรฉg, hogy trehรกny vagyok, mรฉg mลฑkรถdhetne jobban is az anyagmegmaradรกs tรถrvรฉnye, mint รฉppen errefelรฉ, vagyis errefelรฉ plรกne mลฑkรถdnie kellene, mรฉgsem ezt teszi.
So even though I'm clumsy, the law of conservation of matter could still work better than it does here, or rather, it shouldn't work here, but it doesn't.
I hate crawlers that donโt advertise theyโre crawlers. โn badly written. They donโt respect the canonical URLs so they keep getting themselves into a loop instead of actually crawling the site properly. They make the logs really hard to read. Canโt block them theyโre distributed.
I am curious what an actual solution to this problem could be. Everything I've read about it feels like a bandaid โ from robots.txt to cloudflare turnstile โ there has to be a better way!
It would require permaban on IPs which would require permalogging of IPs in order to track them, and we are currently obfuscating them before hitting the DB with daily rotating salt so an anonymous user canโt be tracked. So weโd have to give up privacy/security :/
Preparing for opening up an app I'm working on for a public beta. Main is a quiet app that helps you maintain the value of your home:
โฆ
Yes the og is downloaded and re-served, to avoid leaking/tracking of client information. You need to edit and save to refetch, I did it for you now.