Allen 🔬👽

Just published a new article about the direction of $META. After the event yesterday, I have some questions… @justafiend/is-meta-headed-in-the-right-direction-e29027cfaa60" target="_blank" rel="nofollow noopener">medium.com/@justafiend/is…

anthropic running the exact same marketing playbook with every release. “our model is so capable and dangerous, ahh we are afraid to release it”. just put the model in the bag lil bro.

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.

ANTHROPIC ACCIDENTALLY LEAKED Claude Code source code and someone made a copy of it on GitHub, in just 1 hour it already got 1.5K stars.

What the fuck did I just watch?

Everyone needs to hear this…

This is legitimately hilarious lmao

But alas, according to o3, it already “closed the interpreter” and so the original prime is gone 😭(11/)

🚨 NEW: It’s only been 3 days since Google launched Firebase Studio ... but devs are already building like it’s 2030. It's like Cursor + Lovable + Replit + Bolt + Windsurf: ALL IN ONE 10 insane examples that prove it's gonna change application development forever: 👇

I don’t want to connect my coffee machine to the wifi network. I don’t want to share the file with OneDrive. I don’t want to download an app to check my car’s fluid levels. I don’t want to scan a QR code to view the restaurant menu. I don’t want to let Google know my location before showing me the search results. I don’t want to include a Teams link on the calendar invite. I don’t want to pay 50 different monthly subscription fees for all my software. I don’t want to upgrade to TurboTax platinum plus audit protection. I don’t want to install the Webex plugin to join the meeting. I don’t want to share my car’s braking data with the actuaries at State Farm. I don’t want to text with your AI chatbot. I don’t want to download the Instagram app to look at your picture. I don’t want to type in my email address to view the content on your company’s website. I don’t want text messages with promo codes. I don’t want to leave your company a five-star Google review in exchange for the chance to win a $20 Starbucks gift card. I don’t want to join your exclusive community in the metaverse. I don’t want AI to help me write my comments on LinkedIn. I don’t even want to be on LinkedIn in the first place. I just want to pay for a product one time (and only one time), know that it’s going to work flawlessly, press 0 to speak to an operator if I need help, and otherwise be left alone and treated with some small measure of human dignity, if that’s not too much to ask anymore.

You’re cancelling family members for holding different political views and these guys are belly tapping & Obama and Trump had like a 20 minute conversation and were laughing and joking. Do you see it, anon? No, you don’t, you poor sap.

you are getting lapped by people 50% dumber than you because they don’t overthink shit. aim. fire. correct later.

8. Portalgraph: A 3D projector that projects VR space into the real world

It's only been 1 day of CES 2025, and the announcements have already been incredible. The 10 most impressive reveals of CES 2025 so far: 1. A 360° AI-powered body scanning health mirror that can scan your heart, weight, and metabolic health

It's underrated how many mega successful people are just innately way higher energy (sleep 5-6 hours a night, always on, work through weekends for the fun of it, etc.) Becomes painfully evident the more of these you interact with: they just operate at a high frequency.

"Your startup is just a GPT wrapper" OpenAI is a Nvidia wrapper Nvidia is a TSMC wrapper TSMC is a ASML wrapper ASML is a sand wrapper Sand is a silica wrapper

This is one of those situations when you lost but still won. I’m grateful for last night. No regrets to get in ring one last time. I almost died in June. Had 8 blood transfusions. Lost half my blood and 25lbs in hospital and had to fight to get healthy to fight so I won. To have my children see me stand toe to toe and finish 8 rounds with a talented fighter half my age in front of a packed Dallas Cowboy stadium is an experience that no man has the right to ask for. Thank you 🙏 #PaulTyson

I truly hate that the loudest feedback for AfroTech always comes from the most unserious soapboxes..I promise if you’re here for real ROI, your focus wont even accommodate space for the bullshit.

Soooo who said taking my Rams salary in bitcoin was dumb again? 🤔🤫😌