Donโt be beholden to one LLM basket.
Get yourself an Openrouter account, get yourself an open source harness like pi and get yourself educated.
I will die on this hill.
I agree with this. I already use different models for different tasks in part for this reason.
Never bothered with an OpenRouter account though, I just have accounts set with each provider.
And Pi is excellent. I actually find it much better than Claude Code.
Coming from HN to post that I've been using Argon all week and it's the first Gemini model I've stuck with for more than a few minutes. It's very good for what I do and it's so nice to read back another style of voice.
These days Ive been learning how to deal with guilt and feeling gulti about things I didn't cause. NGL is hard man, how do you start cntl-z your brains on that
I've spent way too much time recently writing TUIs for productivity (eg. merging github PRs, Google Chat DMs, firewall approval requests into one dashboard, another for watching actions on my PRs) and lost a lot of productivity as a result.
I'm not an optimist, just a pessimist who's still proactive: I don't think things are going to get better, but I just can't talk myself into giving up yet.
Big list of events you've attended! Definitely dump more photos when you find the time. I'm more of a casual Nu-Metal enjoyer myself, but I can also appreciate some of the classics.
It's taken me 5 years to get a photo storage engine off the ground. I've got it now, so I now have to go back through time and get the photos up.
AC/DC next Thursday!
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.
#haskellnotesfollow#ainotesfollow
... 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.
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).
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyerswrote:
The interface needs some work. For example, I would like the textarea that I am using right now to be as wide as the header above. Also, where is the character counter?
Made barbecue this evening. Lamb and chicken for meat, pepper and zucchini for veggies. Yummy! Kids loved it, the boy's sleeping now, the girl is reading a book, the wife's out with her girls, I'm with wine. Life's good.