I arrived Seoul, now. Stay for 5 days.
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).
most akkor mit kezdjek ezzel a Windows 10, Windows 11, Ubuntu Linux 3-as operรกciรณs rendszerrel egy kรฉt felรฉ particinรกlt winchesteren, jobb lesz ha elลbb megvรกrom, ameddig tรถrli magรกt a Windows 10, nem azt mondtรกk, hogy lassรญtani kell az MI projekteket, annyira tetลฑ mรณdon csinรกlom
Now what should I do with this Windows 10, Windows 11, Ubuntu Linux 3 operating system on a hard drive partitioned in two? It would be better if I wait until Windows 10 deletes itself first. They didn't say that AI projects should be slowed down, I'm doing it in such a lousy way.
ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so iโm happy to settle into predictable models for a while.
Coding probably yeah, but still they are bad at generating novel information, new ideas and such. Theyโre also not very good at seeing the bigger picture, they will narrowly perform the task but theyโre not taking into account future revisions, which ends up in refactor after refactor in order to move forward.
โ โ โ โ โ โ โ โ โ โ โ โ โ โ โขโฃโฃโ โ โข โ โขนโขณโขโ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ โ
โ โ โ โ โ โ โ โ โ โ โกคโ โกโ โฃตโ โ โ โกโขธโ โขธโ โกโ โ โ โ โ โขโกดโ โ โกงโฃโฃโกโ โ โ โ โ โ โ โ โ โ โ
โ โ โ โ โ โ โ โ โ โกฐโ โ โขฐโ โ โกโ โ โขฐโ โกโ โกโกโกโ โ โ โกฐโกฑโกโ โกโ โกโ โขโ โ โ คโกโ โ โ โ โ โ โ
โ โ โ โ โ โ โขโกโขโ โขโ โ โขโ โ ธโกโ โ โกโกโ โกโ โกโ โ โกฐโขกโกฑโ โกโขโ โขโขดโ โ โ โ โฃโกโกโ โ โ โ โ
โ โ โ โ โ โ โกโ โ นโฃฆโ โขโ โ โกโ โ ฑโ โ โขฐโขโ โขโขธโกโ โข โขโขงโ โกฐโขโ โข โกพโ โ โ โก โ โก โ โ โฃโ โ โ
I lately been a bit curious of strudel io and the live coding movement. I have found some cool artist but if you have any recommendation feel free to drop it.
strudel is great, i feel obliged to pitch in my own livecoding app however :P groovemaster.xyz check it out!
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.
This #tome about #Tcl/Tk has me re-evaluating my plans to move to the woods to be a carpenter hermit.
Now I want to move to the woods and be a programmer hermit.
ๆๅจไธญๅฝๆฏไธไธชๅ่ฑ็ฆปๆฟๅบๆๆง่
๏ผๅบไบ่บซไปฝ็ไธๅๆดปๅจๆ้ฝไธๅไธ๏ผๆฏๅฆๆญฃๅผๅทฅไฝๅ็ฝ่ดญใๆไนไธบๆญคไปๅบๅทจๅคงไปฃไปท๏ผๆ็้ๆฉ็ฉบ้ด่ขซๆๅคงๅ็ผฉ๏ผ่กๅจ่ฝๅๆๅคฑไธฅ้ใๆๅช่ฝ้่ฟๅฐ้ๅ
่ดนwifi่ฎฟ้ฎไบ่็ฝ
In China, I am practically independent of the government; I don't participate in any activities based on my status, such as formal work or online shopping. I've paid a heavy price for this; my choices have been severely limited, and my mobility has been significantly impaired. I can only access the internet through limited free Wi-Fi.