You won't believe it but thats actually a very hard problem to solve algorithmically.
If you want to search further, it is called the “containment under free rotation” problem.
Edit:
There is a tool called trimesh that lets you load in meshes, compute convex hulls, and compute oriented minimum bounding boxes. https://trimesh.org/quick_start.html search for "bounding box" on that page.
Short parts: Each layer is finished quickly, so the plastic stays warm, and layers fuse strongly before cooling.
Long parts: Each layer takes much longer to complete, so by the time the nozzle returns, the previous line has already cooled too much, leading to poor interlayer adhesion.
Try those one by one:
Raise nozzle temperature.
Raise hotplate temperature.
Reduce part cooling fan speed, or disable it after the first few layers.
If you have an enclosure, raise the enclosure temperature.
If it is not temperature related but rather inconsistent extrusion, try:
Slow print speed. That makes more consistent extrusion, especially on long straight runs.
Increase flow/extrusion multiplier slightly (e.g. +2–4%) to compensate for under-extrusion on long lines.
This one is off topic, but you mentioned a "debugging" flowchart / q/a for plants or gardening and thats exactly what I am looking for. Do you have a link (or book recommendation) to such a resource?
and also only once you've invested the multiple weekends of migrating your whole setup and config to a completely new syntax/concept and invest the necessary time and brainpower to learn everything related.
The tool is not just one LLM though. It uses multiple LLMs and multiple other non-llm things.
Your argument is akin to saying:
you can't sit and ride on a wheel, so a wheel can never be used for personal transport. And thus the natural conclusion once you understand what a wheel can do is that you can't sit and ride in a car, so a car is also useless for personal transport.
In my experience you can use a LLM to point out typos or grammar errors, but not to actually edit or rephrase your work.
These will still fall prey to the reason that LLM summaries are bad.
So you didn't try out this specific LLM based tool, but you extrapolate your experience from generic LLMs to judge it? To me that sounds like a hasty generalization .
I just want to genuinely now whether this specific tool might be more useful at a specific applications than generic LLMs, yet here on the lemyverse a discussion like that is impossible because AI BAD. It's a sad and frustrating state of affairs.
I agree with mostly everything from this blog post. But I am also very curious about projects like these: https://github.com/mindverse/Second-Me that claim to be able to learn to immitate you. Which might end up being good enough for doing the final touches.
I tried, but it wouldn't run on my hardware. I get to the training process and then it errors out at some point. If anybody has any experience or is willing to try it out, please let us know whether it was actually any good or not.
I'm too lazy to spin up docker containers and config for stuff that would make my life a bit better, but not enough to warrant the hassle... Like for example a finance management software that can hook into my bank. Or document management with automatic email imports etc.
To be fair: Motherboard, cpu and ram I bought 6 years ago with an nvidia 1660. Then I bought the Radeon RX 6600 XT on release in 2021, so 4 years ago. But it's a generic gaming rig.
I would be surprised if 2000$ worth of modern hardware, picked for this specific task would be worse than that mini PC.
If anybody likes the concept of generating a backend from a yaml, but doesn't like the LLM focus - there is a well established project for a well established format.
You won't believe it but thats actually a very hard problem to solve algorithmically.
If you want to search further, it is called the “containment under free rotation” problem.
Edit:
There is a tool called
trimeshthat lets you load in meshes, compute convex hulls, and compute oriented minimum bounding boxes. https://trimesh.org/quick_start.html search for "bounding box" on that page.