Are tokens an equivalent of work? Like a currency and therefor a tool to steer and prioritize work in large orgs. Hypothesis: In the end all workpackages will consist of 1 accountable human and 99% tokens burnt by an ai.
Any conversation
@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:Twitter was 140 chars. That makes it double the dream, right?
ennek a laptopnak mindegy már szegénynek, annyi minden történt már vele, most települ rá a Gemma 4 26B A4B QAT, az eredeti tervek szerint, amik lehet, hogy nem is a mi terveink, de arról mi már nem nagyon tehetünk, mert a körülmények áldozatai lettünk
This laptop doesn't matter anymore, poor thing, so much has happened to it, now Gemma 4 26B A4B QAT is being installed on it, according to the original plans, which may not have been our plans, but there's not much we can do about it, because we've become victims of circumstances
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 still don't get how now after AI coding there's people saying that contrary to common belief code wasn't a bottleneck and I realized that when I was starting to code at 10yrs ago when I was 15 and read it in a stackoverflow comment. I thought that was the common belief and still can't believe a lot of supposed senior programmers apparently believed so.
Yes, code was never the bottleneck and of course now it never will be either. Figuring out semantic modeling of data that makes sense across business domains and figuring out the right way to use digitalization to modernize processes, and the change cultures as become possible through such work - that’s much more bottlenecks! Code is easy; people and process is hard!
Spending mornings scouring job boards and listings and applying.
Afternoons working on Cheltenham Open Data and iOS app development.
What about you?
A thing I've been doing lately is trying to come to the same conclusions others have without looking their the direct techniques and code. Last night I tried to figure out why people do vector based retrieval for RAG and ended up running these experiments: n0tls.com/…/2026-09-03-i-think-…rag-with-grep.html
I'm still going to do an explore agent.
hey! welcome :)
hey bro, nice platfrom!
whats the stack?
Thanks! It's server-side React with Bun and SQLite. There is zero frontend JS!
a Gemma 4 a Google tulajdona, nem tárol más adatot, csak amiről a gépen fogom a Rezső nevű OpenClaw ügynököt kérdezgetni, helyileg azt sem itt tartja, hanem a felhőnek csúfolt infrastruktúrában, ami legvalószínűbben valamelyik brazíliai esőerdőben foglal helyet vagy Finnországban
Gemma 4 is owned by Google, it doesn't store any other data, except what I'll ask the OpenClaw agent named Rezső about on the machine, it doesn't keep it locally either, but in the infrastructure mocked as the cloud, which is most likely located in a Brazilian rainforest or in Finland
one-point-five-shotted a local node app for creating social posts. drawing from static pages (hey this exists) or new blog posts (timely). with copy/paste to x, and one click post to bluesky and mastodon, tag manager and stale/archive/reject/refresh options. An idea and a solution in about 10 minutes. Madness.