I do remember early SourceForge. It remember it as very clean, simple and reliable, and popular.

Not popular. Core. It was the trusted place for open source software. Then it was ads. Then the day they bundled there was a MASS exodus. And the 14 people who ran their own source code interfaces scoffed and said "see. I told you." And we all said "yup" - we knew something would happen one day, but that was a worst-case-scenario that few thought was even a remote possibility.

> And the 14 people who ran their own source code interfaces scoffed and said "see. I told you." And we all said "yup" - we knew something would happen one day, but that was a worst-case-scenario that few thought was even a remote possibility.

And nobody learned their lesson and they all piled over to the next centralized system that offered "FREE!".

And so it goes.

I mean, we got ~15 years of great service out of them for free. I used to pay for my own servers in colo for all the stuff Github has been providing for free all that time. It'll suck to move, but I've done it before. It's hard to turn down the loss leader they want to give me, when it's a really good product. Now that it's stopped being a really good product, maybe it becomes easier to turn down, I dunno.

Promotional pricing? Are they saying that after the promotion, it will cost more than 7.5x??

Hmm, maybe they're discouraging copilot+Claude through pricing, nudging people to anthropic suite of tools. That sucks. I've been super happy with copilot+opus/sonnet.

Yup

Well fuck that then

Also coding agents will happily compile android applications (of maximum complexity) via Github Actions where you can just pick them up with Obtainium. No PC needed

What is obtainium.

An android app that tracks releases to install the latest versions of apps directly from github.

Also it works with private repos too if you provide a personal access token (fine-grained) in the Obtainium app settings. Just make sure to "release" (on the Releases tab) the .apk file on the GitHub repo and tag it latest.

I use 'just' (command runner) and the 'gh' CLI to automate this:

    # Build and publish a GitHub release
    release: apk
        VERSION="v$(date +'%Y.%m.%d')-$(git rev-parse --short HEAD)"; \
        APK="build/app/outputs/flutter-apk/app-release.apk"; \
        REPO="$(git config --get remote.origin.url | sed -E 's#.*github.com[:/](.*)\.git#\1#')"; \
        echo "Releasing $VERSION to $REPO"; \
        git tag "$VERSION" 2>/dev/null || true; \
        git push origin "$VERSION"; \
        gh release create "$VERSION" "$APK" \
            --repo "$REPO" \
            --title "$VERSION" \
            --notes "Automated release for $VERSION" \
        || gh release upload "$VERSION" "$APK" --repo "$REPO" --clobber

you already could! just install Termux, npm install your favourite agent harness (pi for one has explicit Termux support, but its AGENTS.md works just fine with Claude Code for example - https://github.com/badlogic/pi-mono/blob/main/packages/codin...), and say you want an android app. It problem solves for a bit, then spits out an apk out to your Downloads folder.

Let me try this. Last year this was a dream. Can't belive we are so close to automate all of this.

My major issue last time was providing the feedback to the agent by running the apk on phone i.e, pass the debug log from the apk back to agent so it can iterate on it without me providing any input.

ask the agent to run adb log so it can read it for itself

I just run claude code on my phone, in termux

Hypothesis: it's a sprawling, labyrinthine mess because it was grown at high speed using Claude Code.

There’s a lot of redundancy, because there has to be to make the system useful. It’s a hacked together mess.

Partway through, I recognized the function calling syntax as similar to Nix which I just started learning.

Turns out the implementation of the article is in Haskell, another declarative language.

At work. we use Power Query with it's M language - a declarative language with lazy evaluation.

Is there something about declarative languages that makes them especially suitable for data work?

I mean — the ideal of an SQL query is you say what you want, and it’s up to the engine to determine how to give it to you — that is, being declarative.

Part of it is there’s so many different ways to represent data, and even more ways to compute a given quantity — but the quantity itself often has a clear definition (sum this column from all rows where this holds, say)

This maps nicely to Cybermen in Dr Who

I learned about this from The Wire. They called it "the headshot"

Why GPT 5.1?

Far better results compared to GPT 5.4 and Opus 4.6. Not great for execution due to speed but has consistently had better comprehension of the codebase. Maybe it's a case of "holding it wrong" regarding the other models but that's been my experience.