Econolicious

🚨Carney - The Eleven Year Plan🚨 I spent the last week lining Mark's every move in 30 documented steps since 2015. No more doubts! It was never about saving the planet, and I have proof. Watch the house of cards getting built step by step. Let me know if you see it too!

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

Naming well is a great hack because the thing that’s more fun to say gets said more often, and the idea it’s associated with gets free infiltration into people’s thoughts

The best part about Rubner going from GS to Citadel is he no longer has an arthritic, colorblind poodle doing his charts

Part of the reason NYC is expensive is everything free becomes immediately over crowded and terrible Equinox doesn't need to make their gyms proportionally nicer to charge $300 a month, simply charging $300 a month is the utility

The US education establishment has deliberately hobbled men with overwhelmingly female teachers who can’t handle boys and load them with drugs, and has since tried to eliminate any ability to identify all talent by ending advanced programs in public schools. Then we are told we need to import foreign talent because we’re dumb. Have made variations on this post before - we don’t even know how much talent we have, and have lost, because we have not tried to find it - and even tried to suppress it for political reasons. It’s just a sick and dirty thing. Imagine the Wright brothers being forced onto ADHD drugs and endless ‘time outs’ instead of tinkering with bicycles - which led to the invention of flight.

This article is the embodiment of a broken academy drained of meaning. One item in the queue is an article discussing what woke science is. This piece is a great exhibit. Academia is recast as just a job, the passion is pathologized, and the vocation is treated as a psychological hazard rather than the reason the enterprise ever worked at all. There is no point in enduring low pay and years of delayed life if the work is not a calling. Once that premise was abandoned - once working hard at something you love was framed as toxic, and excellence itself became suspect - the rot was inevitable. What replaced it was a culture of mediocrity: lowered expectations, therapeutic language standing in for standards, and institutions more concerned with emotional perceptions than truth.

Actually, it's different and worse. Tens of billions of nonprofit donations by billionaire widows and divorcees built out a gigantic patronage machine larger and stronger than the party itself that have captured every organ of institutional power and the part of the coalition that seeks to win election to office are the clients of the NGO's and the public sector unions rather than vice versa. This is why not one leading Democrat can break with the Borg on brainwashing confused youth to yearn to be chemically castrated and dismembered, forbidding any woman from drawing a boundary between herself and any man who says he is a woman, infinity immigration, immunizing endless welfare fraud from any scrutiny, and the looting of public schools by an endless succession of sinecures and consultancies that enact mindless equity-focused nostrums that destroy student literacy and numeracy while enriching a class of ill-educated rent-seekers who promote their successors through the educational system. These are all non-negotiable commitments for which the party is a vehicle making any and all rhetoric about "abundance" mere wind in the service of propagating the grift.