Mr. Buzzoni (@polydao)

BUILD KARPATHY'S SECOND BRAIN WITH CLAUDE FABLE 5 + OBSIDIAN Andrej Karpathy (openai co-founder) shared an architecture that turns Claude into a persistent second brain instead of a basic chat window how it works: > you point Claude Code at an Obsidian vault folder > you drop articles, PDFs, or video transcripts into raw folders > Claude reads the files, updates topic summaries, and cross-references everything > the knowledge base compounds like interest instead of resetting on every new chat the setup is simple: > install and create a local vault directory > open the directory in Claude Code and paste Karpathy's wiki prompt: > > let the agent generate raw, wiki, and CLAUDE.md schema directories > drop any text file into raw and tell the model to ingest it > ask questions across the whole vault and query compiled summaries this eliminates rag database overhead and keeps your local vault organized how do you manage your local knowledge base?

THIS DOCUMENT FROM ANTHROPIC WILL LITERALLY GET YOU PROMOTED > the fastest way to reach a senior position is to automate your current job this technical paper shows how to encode your daily workflows into Claude build custom "Skills" to force the AI to do the heavy lifting: > package your routines into automated folders > the agent executes your tasks flawlessly in the background > it connects directly to your local tools via MCP servers hand off the junior work to the agent and easily claim your promotion grab the exact blueprint right here 👇

THE EXACT SETUP TO RUN KARPATHY'S OBSIDIAN AND CLAUDE ARCHITECTURE everyone wants to automate their Zettelkasten using Karpathy's LLM-WIKI method, but nobody explains how to actually install the local agent here is the exact technical configuration to make it work: > securely backup your current Obsidian database > install NodeJS and authenticate Claude Code via terminal > build a dedicated AI vault to separate local generation from personal notes > run the agent inside VS Code for a seamless development environment once it is running, the AI completely takes over the maintenance of your second brain watch the full video tutorial right here 👇

KARPATHY WROTE THIS DOCUMENT TO COMPLETELY AUTOMATE OBSIDIAN WITH CLAUDE I was ready to abandon my second brain manual cross-referencing was destroying my workflow, but finding this exact document opened my eyes to a completely different approach it is incredibly convenient -> Karpathy's method turns the AI into a full-time maintainer for your Zettelkasten: > the LLM reads every new source and integrates it into a structured wiki > Obsidian becomes your visual IDE while Claude operates as the backend > the agent runs automated checks to find contradictions across your notes > your entire vault compounds automatically without you typing a single link the friction is completely gone. I just feed it raw documents and the agent organizes my entire life here is the official document from Karpathy explaining the architecture 👇

CLAUDE + OBSIDIAN = THE ONLY AI FORMAT THAT WILL SURVIVE THE NEXT DECADE I struggled to build a functional second brain until I applied Karpathy's system -> I used to rely on walled gardens to store my thoughts, jumping from one app to the next then I moved everything to plain text in Obsidian and connected it to Claude seeing the AI read my entire folder locally completely upgraded my approach to work: > you point the AI directly at your local directory for instant context > you own your data forever because everything stays on your machine > the setup eliminates subscription fees and messy database exports > the open format is immune to startup failures because simple text lasts forever complex note apps will eventually shut down. a plain text folder works for a lifetime watch the breakdown 👇

pov: you buy $5,700 NVIDIA's DGX Spark and subscribe to Claude Opus 4.8 only to realize your AI behaves like a consultant on day one confident, articulate, and wrong about things everyone else considers obvious why the company brain is the missing primitive: > context bottleneck - intelligence is cheap but Anthropic calls context the scarcest resource for autonomous agents > graph memory - keyword search finds documents but a company brain maps how facts and relationships connect > wasted effort - teams duplicate projects because they have zero visibility into what other departments are building > exit risk - when employees quit, their knowledge walks out the door because memory was never built into the systems > give them a company that remembers and they compound its intelligence >> give them a company that forgets and you just automated your way to confusion save this before you pay your next subscription invoice 👇

A 23-year-old game modder from Prague uploaded one image of a battle axe into Claude Opus 4.8 and built a $6,200/month 3D asset factory without opening a single modeling tab he let the model write the entire geometry script for Blender from scratch the workflow that prints ready-to-sell assets: > reference upload: drop a high-res weapon concept into the chat window > reasoning layer: Claude Opus 4.8 analyzes the edges, weight distribution, and scale > code generation: the model spits out a flawless python script in 13 minutes using 5,000 tokens > render loop: the code executes inside Blender, auto-generating complex 3D meshes with surface imperfections he found a minor shading bug, fixed it manually in 40 seconds, and uploaded the finished axe to TurboSquid and Sketchfab Earnings breakout: Week 1 > $1,120 Week 2 > $1,450 Week 3 > $1,780 Week 4 > $1,850 1 month > $6,200 net profit > most 3D artists are still spending 14 hours extruding vertices manually and crying about industry layoffs he bypassed the entire pipeline for the price of an API key

THIS 2-HOUR STANFORD LECTURE WILL SHOW YOU HOW CLAUDE OPUS 4.8 ACTUALLY WORKS > pretraining. SFT. RLHF. tokenization. evaluation > the same pipeline that powers Claude Opus 4.8 - explained from first principles by the people who research it now read the article to see how to use those skills in practice👇

This Harvard lecture on Markov Chains will teach you more about how markets move than 10 years of discretionary trading > markets are memoryless - next price depends only on current state, not history the quants running 60%+ win rates on prediction markets use exactly this math