My preferred controller platform is of the QuinLED line - comes with power distribution, voltage regulators, fat copper lines, configurable data-line resistors, and smart auxiliary hardware support all for an affordable $30-$50 per controller. (quinled.info)

<https://kno.wled.ge/> - WLED homepage and probably my favorite clever URL of all time.

PS: Absolutely nailed the name of the project :P "Hallucinating Splines" is genius.

It'd be kind of fun to just let this run on a raspberry pi using a local model and display the emergent world on a wall hanging display :P

Thanks for sharing.

Update: What would it take to run this locally / offline? I'm not quite sure how the cloud flare layer works. Is it just for cheap/free object storage so the cities can live somewhere?

Then I found his other article on an alternate wiring for a shimano mountain bike RD-310 7/8 speed drive train (which unlocks 9-speed ability), which thus let me use the rugged 7/8-speed derailleur for the cassette WITH shimano dura-ace indexed bar-end shifters (which use, get this, 9-speed spacing on an 8-speed index because it made their system "proprietary"). All of this works together flawlessly <3 <3 RIP sheldon brown.

If I could snap my fingers and break toxic habits and patterns, I would have done so decades ago :)

Also I need to track down that Star Trek TNG episode... it sounds poignant.

The LLMs can certainly use raw CSS and it works well, the challenge is when you need consistent framing across many pages with mounting special cases, and the LLMs may make extrapolate small inconsistencies further. If you stick within a rigid framework, the inconsistencies should be less across a larger project (in theory, at least).

Now when I ask questions about design decisions, the LLM refers to the original paper and cites the decisions without googling or hallucinating.

With just these two things in my local repo, the LLM created test scripts to compare our results versus the paper and fixed bugs automatically, helped me make decisions based on the paper's findings, helped me tune parameters based on the empirical outcomes, and even discovered a critical bug in our code that was caused by our training data being random generated versus the paper's training data being a permutation over the whole solution space.

All of this work was done in one evening and I'm still blown away by it. We even ported our code to golang, parallelized it, and saw a 10x speedup in the processing. Right before heading to bed, I had the LLM spin up a novel simulator using a quirky set of tests that I invented using hypothetical sensors and data that have not yet been implemented, and it nailed it first try - using smart abstractions and not touching the original engine implementation at all. This tech is getting freaky.

As an analogy, there might be some interesting discussions happening at my local Community Center, or my neighbor's house, but I would have no way of knowing. But to discover these discussions, I would need to meet someone with a shared interest who would, in turn, share with me a place that they go to for continued discussions and to hang out with interesting people who share an interest.

So maybe, if done correctly, this is a feature? The good content is one extra network connection away, but easy enough to find if an advocate chooses to highlight content, share a connection, or otherwise create an inbound reference to the community.