Wanted to reply to you directly also to increase the chance you see this because I think I had exactly the same intrusive thought as you, and actually built such a cluster recently. Would love to hear what you think: https://x.com/andreer/status/2007509694374691230/photo/1
I think that's amazing, surprisingly physically nice looking, and now you've gone and reminded me that Plan 9 is an option, which is kinda another tangent I didn't need:), but IIRC Plan 9 is really low resource so it might be a good fit (aside it lending itself to distributed computing). Have you written up the build anywhere?
No, not beyond what I already put in the twitter thread. I wanted to wait until I had some cool distributed software running on it too, but then I ran into trouble with the plan 9 wifi drivers for the rpi being unstable and so I'm still working on fixing that. It does serve as a great test bed for that purpose too, as with 8 nodes I can get much more reliable data about how often the driver gets stuck
Instead of having to use lots of dongles and usb ethernet, I just wired them all up using brass rods, a small 5V power supply in the base, and boot them over WiFi (just the kernel and wifi config on the sd card).
Raspberry pi's are cheap, easily available, and there is an absolutely massive trove of information about them on the internet. And the scale means that the linux implementation is very stable and "just works" to a degree that is extremely hard for other SBCs to match.
Sure, VMs are the logical choice, but not everything has to be logical. Real hardware does feel more real :-)
What _does_ matter is the huge reduction in the much more dangerous brake dust, as electric vehicles convert the kinetic energy back to the battery charge via generation instead of wasting it via friction: https://news.ycombinator.com/item?id=44666157
Would hybrids also have the same advantage? I have 2 hybrids as I have use cases that need gas (rural driving). One of them is a traditional style and the other is a 50 mile electric option which can use gas when needed.
The comment is that they’re 10-15% heavier, not that they generate 10-15% more tire dust.
In general tire dust generated seems related to tire compound (softer tires = more dust) and weight of vehicle. Although EVs are heavier, they also tend to use harder tires for more efficiency, so it would not surprise me if it’s a wash by equivalent tires to whatever is used in normal combustion cars.
Seems to me the focus for tire dust should be focused on the truly heavy vehicles: how much do 18 wheelers generate, given they’re typically weighing 10-40x what a regular car weighs.
Same experience in Norway. 95%+ of new cars sold are electric.
I've been riding my bike to work along the same road for 15 years. I used to have to hold my breath along some sections of my ride. Now the air in the city is almost as fresh as in the countryside.
For use in retrieval/RAG, an emerging paradigm is to not parse the PDF at all.
By using a multi-modal foundation model, you convert visual representations ("screenshots") of the pdf directly into searchable vector representations.
Claude.ai handles tables very well, at least in my tests. It could easily convert a table from a financial document into a markdown table, among other things.
You can put a subset of the dimensions in your vector database, thus saving a lot of cost by reducing memory/compute when retrieving nearest neighbors.
You can turn this into a pocket "lisp machine" by following the instructions on http://www.ulisp.com/show?4JAO - although I don't think this can make use of the LoRa interface (yet).
The hardware is cool, but its just a PCB and the edges of the display are vulnerable. I would recommend 3D printing a case to protect it, especially if you are planning to bring it around with you. There are .stp files for one in the official github repo.
I've been lucky to get to work through a few of these already, they do give a decent introduction in how to use Vespa tensor expressions.
I believe it's one of the most flexible ways in any vector (or other) database to express how to rank your query results, and it's compiled down to fast native code for execution, using openblas etc. where appropriate.
