site banner
ArjinFerman  Tinfoil Gigachad  1mo ago (text post)   554 thread views

Tinker Tuesday for January 13, 2026

This thread is for anyone working on personal projects to share their progress, and hold themselves somewhat accountable to a group of peers.

Post your project, your progress from last week, and what you hope to accomplish this week.

If you want to be pinged with a reminder asking about your project, let me know, and I'll harass you each week until you cancel the service

1
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

Oof, ok, have to take the L on this week. Had better luck @Southkraut?

Not a lot, for lack of time.

I got a little time in on the issues I mentioned last week. My procedural mesh collisions are set up correctly, but radial gravity and custom movement controllers are still WIP.

Maybe I'll do some more this evening, but who knows whether I'll get around to it.

So I started back on my project to allow building in minecraft with llms. I was working on it over the summer but my idea of reusable components that the ai could assemble got a little too complex for me.

I've been backed away on that and been focussed on giving it a specific functions to build common things that need blockStates set. I've got everything dockerized and have a live server for testing with players online.

The MCP (Model Context Protocol, used to provide functions that large language models can interact with) client landscape is a bit rougher than I expected. Claude Desktop works well, but only works with Claude. A lot of the programs that claim MCP support are focussed on MCP marketplaces.

Sure, MCP marketplaces are probably better for the average user. But few make life easy for a crazy developer working on a silly project on his own.

I got Cherry Studio working with my MCP server and it supports multiple LLMs. The downside is that it's MCP support isn't great. I noticed that it's not passing tool parameter descriptions to the LLM, which makes them struggle a bit more when working with something unusual.

Visual Studio Code does work as a client, but you need to put it in agent mode. Then whenever it gets an error it starts trying to rewrite your code to fix it instead of just running the minecraft functions.

What I found interesting is that each of the LLMs I've tried have a distinct character.

If you tell Claude to build something cool, it will start building something neat. But it is basically absent minded and forgets a lot of steps. So your throne room will not have any walls. Torches will just float in the air.

Gemini builds things fairly competently but kind of meets your minimum requirements. The results are a bit bland. eg your castle won't have an interior.

OpenAI / ChatGPT just goes hog wild building giant structures. They aren't well thought out and look strange. But you have to admire its ambition.

I've added in build task queues in the hopes that it will be possible for llms to review executed queues later and add to existing builds. I'd like to test having multiple llms modify a build queue and see what I get.

There's not a huge amount of interest in this project outside of myself, but I'm having a lot of fun with it.

My young kids have just gotten into minecraft, and this seems like something they'd love. We actually play luanti (an open source clone) so there's no chance of connecting to your server, but maybe I'll have to tinker around with something like this. There's been a lot of cool work in reinforcement learning with minecraft, but I never did anything with that since it sounds too compute intensive for me, but stuff with llms would be much easier/cheaper.

Primarily as an exercise to familiarise myself with my new guitar, I'm recording a guitar arrangement of a well-known piece of contemporary classical music which has been used in several films. I'm enjoying it, but my God, I'm so used to playing along with a click track, I'd forgotten that that isn't the norm in classical music. Ugh.

Well, that wasn't nearly as bad as I feared it would be.

Got my first job offer. Even negotiated it up fairly easily. Almost too easily. It's going to involve a lot of Java, and I hate Java, but such is life.

Another company seems to like me, and they are bringing me nearly all day for a whole series of interviews with the whole team I'd be working with. I'm kind of hoping they give me an offer because I think I'd rather work with them. But beggars can't be choosers, and providing for my family comes first.

While I've been feverishly updating my skillset, I think an appreciation for containers finally set in for me. They were a tedious black box that defied my profound need to see all the moving parts transparently. A silent, frustrating wall when the slightest thing went wrong in a tangle of configuration options, CI:CD or honest to god bugs in the container itself. But since I've been speeding through off the shelf dbs, web servers, reverse proxies, caches, etc in an effort to freshen up my knowledge of what's even out there and say with a straight face "Yeah, I've used that before", being able to just download a container with a few configuration parameters has been infinitely easier than cluttering up my OS with a dozen different technologies.

Congratulations! and some sympathies re: Java/gradle/maven

Containerization's one of those things that I've got badly mixed feelings on. Too many businesses (and open source communities!) use it as an alternative to actually understanding and managing their dependency graph or actually setting up sane requirements. But the whole 'full isolation and discrete permissions' is good! But it's trivially easy to set up a container that doesn't actually live up to that. Most of big formats have surprisingly good behavior. But the performance overhead for using networking for every form of interprocess communication can get pricey, and even if you don't care about performance the implementation and documentation is near-universally pants.

But if you need to be able to take a server functionality out behind the shed and Ol' Yeller it, it's hard to beat, and much more practical for that purpose than having twenty VMs rolling around.

Yeah, I'm stilling holding out for a better offer from the other place. Their tech stack is .net which I've spent the majority of my career in, so it's a much better fit. Plus I've received every indication the pay will be better too.

Ouch. As someone who used to write mostly .net, I commiserate. Maven might be slightly better than the old MSBuild, but I write pom.xml the way I write k8s manifests: by copying a good one from another project. There's no way you can write one by hand without making a critical mistake.

I have no idea what angel blessed the authors of Docker, but Dockerfiles have the best syntax in the world. Well, CMD/ENTRYPOINT mess aside.

Well, had a whopper of an interview today. Got really good feedback, and will supposedly have an answer by tomorrow.

I may yet be saved from the Java Dungeon. .Net master race 4 lyfe!

Writing mvn files used to be pretty annoying, but LLMs are now pretty decent at doing this kind of boring work. Unless you're trying to do something very tricky, any LLM now would probably produce a workable mvn/gradle file for most common use cases. Same for stuff like manifests - Google, actually, pretty much tells you to use gemini now to generate all that (they actively promote trainings on how to generate all cloud configs with gemini). I am happy about it, never enjoyed this part of work and always tried to automate it away as much as possible.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats