Raj

hang it in the louvre

Shelly-Ann-Fraser-Pryce, 8x times Olympic medalist, obliterating other parents at a school event.

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.

⚽️ culture in 🇺🇸 is about what makes parents happy. We create new leagues, tournaments, & whatever is necessary to appease parents. It’s not about the kids & what they need, so we can’t expect a better national team when the system is not about developing players.

There’s a growing obsession with pouring hundreds of millions into state-of-the-art sports facilities, as if elite players are manufactured by architecture and price tags. Football investors, in particular, love to unveil these massive projects with the same promise: this investment will pay for itself by producing top-tier talent. It sounds compelling, but it fundamentally misunderstands how player development actually works. Elite players aren’t the product of pristine buildings or exclusive complexes. They emerge from repetition, freedom, and access, thousands of unstructured hours with the ball, often in small, tight spaces, long before they ever set foot in a high-performance center. By the time a player reaches one of these facilities, most of the real development has already happened. If investors truly understood this, their strategy would look very different. Instead of concentrating resources into a single, expensive hub, they would decentralize access. They’d build dozens, hundreds, of small, free, local pitches embedded in communities. Places where kids can show up anytime, play without barriers, and fall in love with the game on their own terms. Because the real lever isn’t luxury, it’s volume, accessibility, and environment. The next generation of elite players won’t come from marble-floored academies. They’ll come from the streets, the cages, and the small-sided pitches where the game is played constantly, creatively, and without permission.

We’ve raised $400M at a $9B valuation. Investors include Georgian, G Squared, Prysm, 1789, YC, Coatue, a16z, Craft, and QIA, with strategic investments from Accenture, Databricks, Okta, and Tether. We’re also lucky to have incredible individuals backing us, including Shaq and Jared Leto. This funding will help us scale our ambition and expand beyond coding into AI systems that center human creativity. Replit is now used at 85% of the Fortune 500. We have an opportunity to help shape the future of work. One where AI abstracts away the boring parts and humans shine as creative directors. We’re also investing more globally, particularly in Europe, Asia, and the Middle East. Innovation can come from anywhere in the world, and we want to help unlock it.