Claude + Obsidian has been game changer in not needing to explain context to Claude every session and a step towards creating systems. Next stop is to learn to use Obsidian better and unlock knowledge graphs.
Karpathy just wrote the manual for Claude + Obsidian as a real second brain.
Most vaults die the same way. A year of saved articles and highlights. None of it linked. The graph rots while it still looks impressive.
So he moved the upkeep to the model. You curate sources and ask questions. Claude files, links, and reconciles. You keep judgment. It keeps the books.
raw belongs to you and never gets edited. wiki belongs to Claude. It isn't RAG. Your sources compile once into linked pages and compound from there.
9 rules. Start with 10 sources, not 10,000.
Most people hoard notes. This turns them into a brain that maintains itself.
The next move in AI isn't building agents - it's making your craft legible and open source.
For me: 5+ years at McKinsey, now in industry. Open-sourced my craft as Claude skills.
https://t.co/kKNXnUYO1W
๐ Super Bowl hits different when it's less than a mile from your office.
We couldnโt help but generate this 4K poster with https://t.co/IDc8TFKJjr combining two star quarterbacks (Sam Darnorld and @DrakeMaye2) into a single face-off. Youโll likely see it while walking to the stadium.
Wishing both teams the best of luck tonight.
#SuperBowl #VLMRun #SeattleSeahawks #NewEnglandPatriots #SBLX @vlmrun
โจ ๐๐ป๐๐ฟ๐ผ๐ฑ๐๐ฐ๐ถ๐ป๐ด ๐ฉ๐๐ ๐ฅ๐๐ป ๐ข๐ฟ๐ถ๐ผ๐ป โ our new visual agent that ๐ด๐ฆ๐ฆ๐ด, ๐ณ๐ฆ๐ข๐ด๐ฐ๐ฏ๐ด, ๐ข๐ฏ๐ฅ ๐ข๐ค๐ต๐ด.
Todayโs frontier Vision-Language Models (VLMs) โ GPT-5, Claude 4.5, Gemini 2.5 Pro โ can describe what they see โฆ
But they canโt ๐ฎ๐ฐ๐ on it.
๐ย https://t.co/AXOeRDexpR
๐คฏ Building computer-vision applications is never going to be the same again. As @karpathy says, "English is going to be the new programming-language", and we just made that happen for programming visual AI.
๐จโ๐ป This past month, the @vlmrun team cooked up something magical that I'm especially proud of - a natural-language interface to build and run computer vision workflows (object-detection, OCR, parsing, and so much more) โ all via our new @vlmrun MCP server.
๐ It works with any MCP-compatible AI agent (Claude, OpenAI, Cursor, etc.) and abstracts complex visual workflows into simple English commands. No need to write Python or fiddle with bespoke computer-vision code โ just say what you want your agent to do, and it does it.
Hereโs a glimpse into what you can build today (https://t.co/Ur6YY31UQE):
โ๏ธ Image AI agents โ run detection, tagging, blurring, cropping, and more traditional CV tasks with English
โ๏ธ Document AI agents โ extract totals from invoices, search visual content, or act on whatโs found
โ๏ธ Video AI agents โ understand scene content, trim clips, add subtitles, and create ready-to-share edits
โ๏ธ And best-of-all, it's fully programmable with English.
๐งโ๐ณ MCP Showcase: https://t.co/Ur6YY31UQE
๐ MCP Cookbooks: https://t.co/xfnfRRU5EI
๐ MCP Docs: https://t.co/aFL2cd94gC
#computervision #ai #agents #llm #vlm #mcp #vibecoding #genai
In the world of generative models, a new way of seeing who is leading in the market. I am not surprised to see Claude's adoption and growth. Data & Graph Credit: @poe_platform , https://t.co/JvE6SIU0fB.
Have been testing different LLM models - ChatGPT, Claude, and Perplexity - each has strengths and quirks. Hereโs a quick breakdown of my experience with each model๐งต #AI#LLM
Perplexity โ Research-oriented
โ Lightning fast, combining web search & deep research modes
โ Prompts the user with follow-up questions - handy as you brainstorm
โ Can pull in relevant images/videos for holistic learning
โ TBD
Listened to @danielpriestley 's recent episode on Diary of a CEO podcast, few things stood out:
๐ค World is quickly evolving from an industrial age to digital age, with a new set of business rules, and whatever we learnt in school is becoming redundant
๐ฉ๐ผโ๐ป Power is shifting from institutions and large corporations to individuals with success defined by those building with a strong personal brand and scalable business model
๐ฝ๏ธ Most of us are primarily consumers - only 1% of LinkedIn users publish weekly
โฐ๏ธ Lastly, we need to better appreciate the mountain we are on and the value we bring to the world
โก๏ธ Excited to share that I am starting an AI+Education company called Eureka Labs.
The announcement:
---
We are Eureka Labs and we are building a new kind of school that is AI native.
How can we approach an ideal experience for learning something new? For example, in the case of physics one could imagine working through very high quality course materials together with Feynman, who is there to guide you every step of the way. Unfortunately, subject matter experts who are deeply passionate, great at teaching, infinitely patient and fluent in all of the world's languages are also very scarce and cannot personally tutor all 8 billion of us on demand.
However, with recent progress in generative AI, this learning experience feels tractable. The teacher still designs the course materials, but they are supported, leveraged and scaled with an AI Teaching Assistant who is optimized to help guide the students through them. This Teacher + AI symbiosis could run an entire curriculum of courses on a common platform. If we are successful, it will be easy for anyone to learn anything, expanding education in both reach (a large number of people learning something) and extent (any one person learning a large amount of subjects, beyond what may be possible today unassisted).
Our first product will be the world's obviously best AI course, LLM101n. This is an undergraduate-level class that guides the student through training their own AI, very similar to a smaller version of the AI Teaching Assistant itself. The course materials will be available online, but we also plan to run both digital and physical cohorts of people going through it together.
Today, we are heads down building LLM101n, but we look forward to a future where AI is a key technology for increasing human potential. What would you like to learn?
---
@EurekaLabsAI is the culmination of my passion in both AI and education over ~2 decades. My interest in education took me from YouTube tutorials on Rubik's cubes to starting CS231n at Stanford, to my more recent Zero-to-Hero AI series. While my work in AI took me from academic research at Stanford to real-world products at Tesla and AGI research at OpenAI. All of my work combining the two so far has only been part-time, as side quests to my "real job", so I am quite excited to dive in and build something great, professionally and full-time.
It's still early days but I wanted to announce the company so that I can build publicly instead of keeping a secret that isn't. Outbound links with a bit more info in the reply!
@spillai & I are building our personal AI agent using @airtable's no-code platform for everyday tasks. We started with an AI generated weekly meal planner for our family. What other tasks can we task the AI agent with?