Dare you to try explaining all this to your elderly relatives.

Nothing a little bodge-wiring and a Pi compute-module can’t fix.

This feels like it needs a ‘Hunger Games’ add-on.

“Blink twice if you’re in danger.”

The ‘Old Man’s’ side-gig.

It’s Texas.

The fire department hosed them with beer until they could be peacefully removed.

There’s a Mister Polybius on line 2. He sounds very annoyed. Says the Association of Veterans of the Punic Wars would like to have a word.

RUD: https://www.wordorigins.org/big-list-entries/rapid-unplanned-disassembly-rud

Ghost of Tito has spoken. Worked out really well for him.

Remembered I had an unopened Pi5-8GB on the shelf.

Was jokingly going to suggest a WASM version. But then: https://github.com/ffmpegwasm/ffmpeg.wasm

EFF supporter for years. Have so many of their t-shirts (amazing designs, btw). Cindy Cohn is the real deal. Anyone online should go pay attention to them.

Slept out there in the open on a camping trip a while back. Clearest sky I ever saw.

The cacti are amazing. Also, great bouldering. Highly recommended.

The problem with CAG is not just that it hogs memory, but to keep it fresh you have to keep re-indexing. If the corpus is large and dynamic, it can easily fall out of date and, at runtime, blow out the context window.

GraphRAG has some promise. NVidia has a playbook for converting text into a knowledge graph: https://build.nvidia.com/spark/txt2kg

It’ll probably have the same issues with reindexing, but that will be a common problem, until someone comes up with better incremental training/indexing.

Looks interesting. Will give it a whirl on my home server.

In this article, they talk about bringing up a local RAG system to let people run an LLM off a large document corpus: https://en.andros.dev/blog/aa31d744/from-zero-to-a-rag-system-successes-and-failures/

Wonder if this, connected to something like that, and wrapped in an easy end-user friendly script or UI could be a good combination for a local, domain-specific, grounded knowledge-base?