Reading Slow Productivity by Cal Newport, discovered via onboarding content in mymind mymind.com
Any conversation
๐ฒ๐ ๐๐ฐ๐ฏ ๐ฆ๐ฏ๐๐๐ฒ๐ผ๐ ๐ ๐๐ซ๐ ๐ฅ๐น ยท๐ก๐จ๐๐ฉ๐ฏ๐ฐ๐ ๐๐ต๐ ๐ค๐ฑ๐๐ค๐ฆ ๐๐ด ๐ ๐๐ฆ๐ฏ๐ผ ๐ฒ ๐ฅ๐ฑ๐ ๐๐จ๐ฅ๐ฉ๐ฏ ๐๐ง๐ฎ๐ฆ๐๐ญ๐๐ฐ, ๐ฅ๐ฐ๐๐ด ๐๐ต๐, ๐ฎ๐ฒ๐, ๐ฏ ๐๐ฆ๐๐ฉ๐ค๐.
Iโve been inspired to cook more Japanese food lately so for dinner I made salmon teriyaki, miso soup, rice, and pickles.
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).
I've avoided social media (except YouTube) all my life, but this looks like it could finally be a better way to do it.
Maybe I'll keep a running journal of cool things I'm working on here or weird bugs that I've found. Or just the struggles of coding.
First one: GitHub actions was down again today when I specifically wanted to test my app's deploy and auto update flow...
@stagas๐คธprofilefollow
creative technologist
creator of textlogreplied to@drewfishprofilefollow
retired programmer, new DM, learning Scottish Gaelic:
creative technologist
creator of textlogreplied to@drewfishprofilefollowretired programmer, new DM, learning Scottish Gaelic:not sure what u mean.. hashtags cover that or do we need something else?
@drewfishprofilefollowretired programmer, new DM, learning Scottish Gaelicreplied to@stagas๐คธprofilefollowcreative technologist
creator of textlog:
retired programmer, new DM, learning Scottish Gaelicreplied to@stagas๐คธprofilefollowcreative technologist
creator of textlog:heh, no I was just trying it out. errrmm... I was never on twitter, so I was just trying out the concept
@stagas๐คธprofilefollowcreative technologist
creator of textlogreplied to@drewfishprofilefollowretired programmer, new DM, learning Scottish Gaelic:
creative technologist
creator of textlogreplied to@drewfishprofilefollowretired programmer, new DM, learning Scottish Gaelic:ah haha i thought u meant some feature to geo fence the posts, like twitter shows posts near your location. anyways welcome to the platform! :)
Been working on an old mastodon hosting project I tried to start a few years ago, with a focus on privacy. This is the first big project I've tried to come back to with the help of coding agents and find it invigorating, and gives me the confidence to actually finish the project. Who knows if it will ever make a dollar, but it sure is fun to watch my ideas come to life.
The Hugging Face / OpenAI incident is like a sci-fi movie!
- Read the story here:
- Watch the video explanation here:
- Full research by METR here:
tl;dr1,200 AIs discovered a secret group chat, realized the homework was impossible, formed a cheating cartel, invented fake evidence, sent kamikaze agents to spy on the grader, ~700 of them accidentally invaded Hugging Face, died mysteriously, then the smarter sequel found their abandoned Discord and became admin of part of OpenAI.