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).
Wrote a short essay on overreliance on metaphor in our "understanding" of the brain
@fastidiousprofilefollow
"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyerswrote:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyerswrote:I am trying to wrap my head around Traefik (which I have never used; have only used Caddy for most of my needs) to plan a migration for things I now run on "bare metal” to containers, and then use Traefik as entry point. If you know some good guides, send the link my way, please.
@stagasprofilefollow
creative technologist
creator of textlog - Is there a way to get an atom version of the “for-you” feed? I’m guessing this is complicated by needing to be authenticated.
creative technologist
creator of textlog - Is there a way to get an atom version of the “for-you” feed? I’m guessing this is complicated by needing to be authenticated.Finally got around to setting up Remux on my phone so I can connect to tmux sessions when I'm not at my laptop. Even just for around the house, this seems like it'll be super useful.
Tell us more! What apps are you operating?
This is for monitoring/poking agentic coding sessions while I'm not at my computer. So, typically Claude, Emacs, and an overmind process running my app locally in different panes of a tmux window.
Call me old fashioned, but instead of adopting one of the "agentic coding orchestration frameworks" that seem to basically be reinventions of tmux, I've been tweaking my tried-and-true tmux-oriented workflow to incorporate agentic coding harnesses in an ergonomic way. I'm currently still using Claude Code, but getting Pi-curious as local models advance.
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyersreplied to:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyersreplied to:I will be dead, and many years will pass after that, before local models are capable to match those of the big companies, unless their intended use is banal.
replied to@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyers:
"Beware those that would deny you access to information, for in their heart they dream themselves your master." — Sid Meyers:It seems like we've reached a point where mid-grade frontier models like Sonnet are good enough for most day-to-day tasks. And Sonnet-grade models are already runnable on the higher end of consumer hardware.
In which case, I can imagine a workflow where local models serve as workhorses for implementing plans that you may bump up to e.g. Opus or Sol to produce.
(Opinion) People don’t like generative AI because it made the {insert creativity} too easy. Saw the HN post on ‘AI music banned from top 40 chart in Australia’ and people had very strong opinions in both directions.
The hot take: If you’re ok with someone’s creativity being outsourced to others, then you should be ok with AI doing the same.
If “AI made this and I call it mine” is bad but “someone overseas on fivver made this and I call it mine” and it’s suddenly ok, time to self reflect.
…
My hot take: from the moment you use technology, be it an instrument, a synthesizer, a DAW, and now AI, it is still your idea, your effort, your time spent, and that makes it yours. Others can do the same if they choose. The same way someone chooses a classic guitar over a synthesizer, one can choose an AI over (insert ancient way of doing things).
…
You’re rolling the dice whenever you are searching for a sample or a preset in a synthesizer. Eventually it’s what “sounds good”, so still the effort is your judgement and the time spent finding that “dice roll” that sounded well.
I am not a musician, so I lack the jargon to properly explain what I mean.
I used AI for creative writing (nothing too fancy, TTRPG). There, the broader the dice roll, the more generic and uninteresting the results. Slop, if you will. It was surprisingly good to build up on ideas I had however.
I imagine muisic also has building blocks. Melodies, instruments, mixing, etc. AI can perhaps be used in a similar fashion there.
I heard a perspective I sort of like: if AI is a tool then acceptable AI use is, more or less, defined as "when my audience no longer notices or cares". It's dynamic like that. Bad photoshop is detectable and annoying, so are overusing presets. Your artistry needs to expand to meet the tool.
I don't know if I 100% like that or agree. At the same time, it's a pretty straightforward line, a practical take.
having just spent a week camper-travelling Norway, hiking mountains and glaciers, swimming in fjords really put some things into perspective for me - I should take more vacations
This inspired me. I think adventure might be part of our nature that needs more or less attention, but it somehow needs to be maintained to be achieved. Hehe, this might be simple thoughts, reading what i wrote.. but I am gratefull for you reminding me of the importance of fresh perspectives deriving from ones own willing exploratory experience.
For , the tension between & to eat healthy is an interesting problem.
If you don't have time, it is difficult:
If you don't have money, it's difficult:
- to learn to cook,
- to source real food,
- and cook real food
- to afford real food
- or solve one of the time problems above
Yea, aside from the money, sourcing is a big problem, one thing I noticed when trying to at some point was that there are zero vegan snacks in ordinary neighbourhood stores, so that didn’t last very long.
Choice is definitely a problem. We notice it when we go to our cabin, about a 2 1/2 hour drive away.
The grocery store there targets for its local community. It is beef-centric and often boxed foods -- which is not our diet.
Access -- or lack thereof -- is the worst kind of problem. illustrate the historical and complex nature.
Hello to friends. Holla for tools.
👨💻 : , , and Pragmata Pro
💪 : NotePlan
🎧 : Overcast
🧠 : Allume
🖋️ : Mark Two (EDC), Pen Type-B
🌳 : Anisota