I have tried that and it works well for me. I can also recommend using a Visual Studio plugin called Markco that lets you comment a markdown file. It’s resembles words commenting feature. I use it to comment LLM generated markdown.

I have a ML project. I usually set up a team of agents, where I have a leader, archivist, research assistant, researcher, developer and tester. The team generates hypothesis based on papers, test it, and iterate over that. Everything is documented using a lab notebook. It burns tokens but I have found some promising strategies that I am testing.

Nice, I am going to this for Swedish law! Any suggestions on how one can model parliament voting when a law passes using GitHub? Or all the work that preceded a law, that’s like a feature request or a bug report.

I’ve done this for Swedish laws: https://github.com/se-lex/sfs (Markdown with git history)

https://github.com/se-lex/sfs-processor (processor with Git, md, md with temporal tags, or html as output formats)

Thank you! Didn’t know that existed.

I started doing it for Finland!

Parliament voting, maybe upvotes and downvotes on a pull request?

Do you have any good resources for what you are describing?

Why would you when an open source version already exists?

You’re going to brute force every possible state of a sandbox building game. See you on the other side of the heat death of the universe; hope you stocked up on Claude Code credits.

So https://malus.sh/

Good luck with all that

Is this service a joke? I'm not even sure after reading the reviews at the bottom there.

Haha yeah its a joke, but it sure is prophetic

I dunno. I just let Claude build a python script that calls Claude code though subprocess.run().

I recently made a sort of Autoresearch with that approach. The script calls Claude Code to create a hyphotesis, then code based on that, evaluate- rinse and repeat. I am still trying to figure out if I am actually on to something or just burning tokens. Jury is still out.

That's totally a valid approach! Especially for a very specific workflow you are looking for. For the cases I cover in cook, I had done those patterns enough times that I figured it was time to build a tool/skill for Claude so that I didn't have to explain it as much and also not have to wait for claude to code it up, and possibly interpret me wrong. Now ask claude to "/cook race 3 of foo plan with review, pick the best" and it knows what to do.

I think you're onto something, but I would add that it's sort of like a live REPL that has an integrated agent but with extra steps.

I haven't used python much but I wouldn't be surprised if you can set up a sufficiently powerful REPL with it. I know Julia can do it very well and it's a very similar language. Obviously there are powerful Lisps that do this very well as well.

I went quite far down this approach last year; you're welcome to take what you want from my repo -

https://github.com/riazarbi/way

Hey scrappyejoe, way looks pretty cool. The goal of cook is to be unopinionated, exposing primitives for the shape of workflows as opposed to defining what happens in those workflows. Cook is something that way could use under the hood.

Cool, I'm already digging into your stuff, thanks for posting it.

that's rlm

Has anyone tried to set up a container and let prompt Claude to escape and se what happens? And maybe set some sort of autoresearch thing to help it not get stuck in a loop.

I want this the other way around as a plugin in Chrome. So I can easily spot the bullshit. And I would prefer that it translated LinkedIn to something salty, maybe pirate speak?

I really want a DeathClaw product.

There is a Dungeon Clawer.

I bought magnetic self adhesive tape and mounted in on my fridge. Now it’s the family calendar. So nice.

That seems incredibly overpowered for a calendar lol. I imagine doing this with a kindle / e-ink display might also be more energy friendly.

It might be much more energy efficient, but it doesn’t really matter when the annual energy cost is $2 for the iPad