DB

Journalists will make a major comeback soon. You heard it here first

God please help me god please I promise if the S&P goes down on Monday I will sell and go back to the Bronx and teach kids electrical engineering please I’ll be good please forgive me.

I don’t like cash net nets b/c the cash doesn’t earn much w/o leverage. I prefer productive assets and smart capital allocation. In a way, $FFH.TO $ELF.TO and $FIH.U are all net nets selling below liquidation value, growing and returning capital.

@HESaBSG @iBladesi Bosh

smoking some pork belly in nyc. having friends and family over. the alcohol is flowing. there much pain in the world, but not in this backyard.

Japan has a 112-year-old gas monopoly that heats an entire prefecture. Zero competitors. No debt. ¥5B cash on the balance sheet. Trading at 42 cents on the dollar of book value. 1.9× EBITDA. The reason it's cheap: nobody on Wall Street has ever heard of it. $9537.T (bio for more info)

@atelicinvest 100% fake

This is frightening as fuck but for a completely different reason.

@PurpleDrink_LLC Goat

I was not emotionally prepared for this today

@churrascooooo Mine is so fire. All the premium selections and they don’t mark up that much. Blessed.

my corner store has the worst selection of items in the city from top to bottom, its truly appalling but i gotta roll with them because they're the home team, it is what it is

SahBabii has officially entered the music rotation

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.

@taobanker lol

HIGHLY-PAID, HIGHLY-REGULATED BANKERS MOMENTS AFTER YOU FILE YOUR "CONFIDENTIAL" IPO

These tweets make me so bullish

@volcrushed It’s a tourism attraction now. Really pisses me off. All luxury I see in NYC I immediately assume is fake

Especially in the past two years the stigma around buying/wearing fake designer goods has all but gone away. A decade ago canal st. was never this crowded and people would press you if you popped out with anything high-end about where you got it, price, etc...

@volcrushed Cook king. This is why I’m nice to everyone and do favors whenever I can

The same people that wouldnt push my resume when the market was hot are asking me for internal referrals. God is good and hell naw

@churrascooooo So blackpilling

i think trump has tried to do a lot domestically that no one has ever tried before but its just gone to show that you actually cant do anything to stop what is coming

Listening to Trumps speech right now. Lol we’re gonna open down 3%. This war isn’t ending anytime soon

@dalibali2 😂😂😂

@dbull888 Thanks Andy.

Amazon can’t even win this contest. Fucking losers.

God I love Buffett so much. Only guy I’ve ever idolized besides Druck. I’m going to cry when he dies.