SheepOnFactory

Inspired by Animal Farm
Original content
#AnimalFactory

[SheepOnFactory @SheepOnFactory]

@boldleonidas I'm so bad at trading either drawing bold

[SheepOnFactory @SheepOnFactory]

@lookonchain @fundstrat @saylor First time ??

[SheepOnFactory @SheepOnFactory]

First time ?

[Lookonchain @lookonchain]

JUST IN:

Tom Lee (@fundstrat)'s #Bitmine is down $8.9B on 5,416,901 $ETH ($10.03B).

Michael Saylor (@saylor)'s #Strategy is down $7.6B on 843,706 $BTC ($56.26B).

[SheepOnFactory @SheepOnFactory]

NEVER SELL BITCOINNNN

#SheepOnFactory

[SheepOnFactory @SheepOnFactory]

Make American great again !!!

[BRICS News @BRICSinfo]

JUST IN: 🇺🇸🇵🇰 President Trump says US will suspend Project Freedom in the Strait of Hormuz at "the request of Pakistan."

[Contanimation @Cont_animation]

Sincitium is finally here.

We are pleased to present our latest piece: a concept trailer created specifically for the @runwayml Big Pitch Contest. For this project, we wanted to explore a completely different aesthetic from our usual studio style, and this film is the result of that experimentation.

We hope you enjoy it as much as we enjoyed the creative process.

Produced by: Contanimation
Directed by: Javier De La Chica and Guillermo Miranda Art Direction: Javier De La Chica
Editing: Guillermo Miranda
Voices: Juan Rabadán
#runwaybigpitchcontest

[SheepOnFactory @SheepOnFactory]

MoonCluck praying for AI to do all the work in this bull run 😂
Would you let AI agents trade your entire portfolio?
#CryptoRooster #AI #Crypto #BullRun

[SheepOnFactory @SheepOnFactory]

@BRICSinfo Not my fault

[SheepOnFactory @SheepOnFactory]

UNPOPULAR OPINION : WE MISS BIDEN

[SheepOnFactory @SheepOnFactory]

POV How people go through SOH right now

Come back to 1900s and play video game

[BRICS News @BRICSinfo]

JUST IN: 🇯🇵 Japan remains uncertain on sending minesweepers to the Strait of Hormuz.

[SheepOnFactory @SheepOnFactory]

@BRICSinfo How people go through Strait of Homuz

[SheepOnFactory @SheepOnFactory]

@SolanaSensei and then you wake up over night then realize all your fund be hacked :D

[SheepOnFactory @SheepOnFactory]

@cz_binance Let grab the 🍿 and watch 😆

[Andrej Karpathy @karpathy]

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.

[shirish @shiri_shh]

generalists are about to win big

If you understand a little of tech, business, and people, and can connect everything fast.

you're sitting on a goldmine right now.

[Ignas | DeFi @DefiIgnas]

Crypto easy money era has ended.

Historically, most easy money periods last 3-7 years:

- California Gold Rush lasted 7 years.

- Tulip mania lasted 3

- The dot-com bubble about 5 years before the Nasdaq dumped by 78%

- Japan's bubble was 6 years, then Nikkei took 34 years to recover

So most speculative booms in history last 3-7 years.

Crypto easy money started in 2017 with ICOs. Then DeFi summer 2020. NFTs in 2021. Airdrops. Points farming. Memecoins.

That's ~8 years of easy money.

We are already past that as every easy money model has been discovered, exploited, or arbitraged to max competition.

Philosophical hard-forks like BTC -> BTC Gold or ETH -> ETH classic are over as crypto ossified not just technically.

ICOs got regulated.

Airdrops get farmed by industrialized sybils.

Memecoin launches went from community fun projects to extraction tools.

The gold rush analogy seems quite good here as FOMOs end the same way:

Surface deposits get exhausted and then industrial mining takes over. (Literally same happened to BTC mining moving from retail to institutions who even IPOed from BTC mining.)

So here’s where crypto is now: TradFi suits moving in, tokenization, RWAs, corpo-sloppo permissioned chains, and regulation. The Trump family & insiders are the last to get easy money from crypto.

For retail, the surface easy money gold picking is gone.

What's left to earn requires real infra, real users, real revenue which means more specialization, specific knowledge and REAL hard effort.

Not sure how many of us who got easy money are ready to grind harder now.

So many builders, KOLs, projects are extracting as much as they (we) can before leaving crypto coz adapting to the new hard-money period is gonna be hard.

Question is: where to pivot for easy money? Asking for a friend.

[SheepOnFactory @SheepOnFactory]

@0xleegenz Right , the only way to climb higher rank always is going somewhere ☑

[SheepOnFactory @SheepOnFactory]

@Punk_Monke I see some rage bait here

[jack @jack]

https://t.co/jgZkBvYOPt