I naively went into a work problem thinking that RAG was solved by the service offered at work, and wow was I wrong. Been a fun week so far experimenting with many different methods before doing the academic research, and it's been nice to be validated by outside research.
Any conversation
It didnโt work out, we found competition offering the same service for free so the fell apart. Need to find something else to do as a side project to textlog. ๐ Thinking of a code editor thatโs focused on the new agentic workflows, so you have it on the side regardless of your agent tools and it monitors the git diff and offers a nice panorama view. Iโve done an extension for VSCode similar to this idea.
ๅฏนไบๆดไธชไบ่็ฝๅๅฒ๏ผๆๅฏ่ฏดๅบๆฌไธๆฏไธไธชๆ่ง่
๏ผๆไธ็ดๅจๆถ่ดนๅ
ๅฎน๏ผไฝๆฏๆฒกๆ็ไบง่ฟไปไนๅ
ๅฎน๏ผไบ่็ฝไธๆฒกๆๆ็็่ฟน๏ผ่ฟๆฏๆๅคๅๆ๏ผๅ ไธบไธญๅฝ็่บซไปฝๅๅ
ๅฎนๆฟ็ญ
Regarding the entire history of the internet, I can say I've been largely an observer. I've always consumed content, but I haven't produced any. There's no trace of me on the internet, which is an unforeseen consequence due to China's identity and content policies.
ๆไธๅคชๆ็ฝไธญๅฝ็โ้ฒ็ซ้ฟๅโๆฏๆไน่ฟไฝ็ใๆฏๅฆ่ฏด๏ผไฝ ๅฐๅบๆฏๆไน่ฎฟ้ฎ่ฟไธช็ฝ็ซ็๏ผ
๏ผๆๆฏๅจ้่ฟ็ฟป่ฏ่ฝฏไปถๅไฝ ไบคๆตใ๏ผ
I don't quite understand how China's "Great Firewall" works. For example, how exactly did you access this website?
(I'm communicating with you through translation software.)
โฆ(deleted post) (deleted post) (deleted post)
Hmm, its a ticking time bomb then.... what do you need to say and need help with?
If anyone can give me a ProtonMail or Tutanota email account, I would be extremely grateful. I have no way to receive verification codes.
You can send it to the temporary email: sl5n215ahf@lnovic.com, thanks
I've received it. Unfortunately, I'm in China and can't access ProtonMail, but I still want to say thank you very much.
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 gotta confess, I vibe codet a Kirigami-based application and I liked it. I am a anti AI person, and cannot wait for the bubble to burst. Yet I see it can empower people that do not know a tech stack, and get good enough results out of it. However i also see, it makes you lazy (and frustrates as soon as it gets somewhat complicated). It seems it is being adopted everywhere. This is scary... if it becomes necessary, will you be able to find a job where they don't require you to use AI?
I've been on a kick lately of trying to visualize the oscillating clock, and ultimately the effectively arbitrarily complex activity of a computer processor, as modern refinements of the line shaft factory of the 19th century. Of compute as being not much more than profoundly refined "work" delivered by the electrical grid into marvelously complex machines.
Does that, as a metaphor at least, feel as important to you as it has to me of late? We spend so much time in a world abstracted.