I never have enough time but Iโd love to do a bit more recreational programming with esoterical languages like kitten, , and . AoC and Project Euler are good because they just require an answer but thereโs also loads of simple puzzles online that rely on being able to submit the code in common languages. Iโve been wondering, however, if I could use an LLM to take those problems and create a verification harness for any language I like.
Any conversation
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.
i got into the fashion to vibevode some utility apps for myself. i didn't review the code. they work fine. colleagues are interested.
i don't feel comfortable to put such stuff on $Github. have no good consciousness with unreviewed and likely ununderstood (stack I am not really familiar with).
internet is full of people who don't care, I know. i tend to overthink.
what about you?
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).
Sharing a great read today:
Some of the takes are on the extreme end, but like most IT decisions, you can dial the pain to exactly what you want.
^C
textlog runs on a 2.5โฌ/mo vps 1 core/2gb ram, using just one instance of Bun with its embedded SQLite. Works perfect and I run a few other apps as well on that machine.
