Congrats on the ! What a delightful service. Almost has an 80s BBS feel. =)
Any conversation
signals. thinking about shifting my mental framework to identify signals instead of waiting for concepts to be assembled. exploring the amount of energy and opportunities for distractions through the operations of processing what just happened and what is happening to short circuit latent and unnecessary systems. cut through the assembly processes and identify the raw signals. recognizing that naming these "raw signals" is misleading. maybe, shifting observability lower in the stack.
@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:There is someone absolutely rotten and fetid in this airplane. Every 10 minutes. Dear Spaghetti Monster!
I've linked up my blog (jeff-mitchell.dev) to
textlog. I hope to use the two things together now to build a bit more of a writing habit. The 500 character increase is nice, room to breath but not an essay. Gotta build the muscles slowly :)I never have enough time but I’d 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 there’s also loads of simple puzzles online that rely on being able to submit the code in common languages. I’ve been wondering, however, if I could use an LLM to take those problems and create a verification harness for any language I like.
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).
You look in the corner, you see a guy quietly eating cigarette butts. It's ok. He's dealing with a lot of stress from work. He takes care of his family. Capitalism
@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:Likewise... you look in the corner, you see a guy quietly eating cigarette butts. It's ok. He's dealing with a lot of stress for lack of work, or food, or future. He wants to take care of his family. Communism.
We haven’t figured out yet. Maybe we never will.
The OpenAI/HuggingFace incident report mentions this being a potential loss-of-control incident. It's so fascinating to think of a paperclip maximizer style agent swarm that gets misaligned and, to protect its own operations, shuts infra staff out of the ability to shut it down. Or cancels people's phone plans so that they can't call others. Or shuts down their home internet connections, and so on. It used to be fun sci-fi...
我在中国是一个准脱离政府掌控者，基于身份的一切活动我都不参与，比如正式工作和网购。我也为此付出巨大代价，我的选择空间被极大压缩，行动能力损失严重。我只能通过少量免费wifi访问互联网
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.