Jeffrey Jensen

After a supernova, the universe gets new pieces to build with. AI gave us new thinking pieces too. Here they are...

Footage released from the THIRD Presidential assassination attempt has reignited the debate over women protecting the President. When shots were fired, the female agents IMMEDIATELY ran away. Should female officers be protecting the leader of the free world? 🇺🇸

Seems I have to build all the tooling for the future of software myself. With Claws and Tokens!

🚨 TRUMP: 5G & 6G ARE WEAPONS FOR TOTAL BODY PENETRATING SURVEILLANCE! President Trump casually dropped the red pill bomb in front of tech execs: “What does [6G] do? Give you a little bit deeper view into somebody’s skin? See how perfect it is?” He said it. Out loud. On record. Linking 5G signals and the incoming 6G rollout directly to 3D spatial penetrative surveillance that can peer through skin, clothes, walls — your entire private existence turned into an open book for the machine. This isn’t about TikTok videos loading quicker. This is millimeter-wave wizardry weaponized. Terahertz-level frequencies that don’t just connect your phone — they map your body in real time, track your vitals, see through concrete, and build a digital twin of every human on the grid. They sold you 5G as “progress.” Now 6G is the panopticon upgrade: total penetration, total visibility, total control. No more hiding. No more off-grid. Your organs, your movements, your bedroom — all broadcast to whoever holds the keys. Trump knows. The insiders know. The same crowd pushing AI, digital IDs, and CBDCs wants you naked under their all-seeing eye. “See how perfect it is,” he smirked… while the deep state cheers. They laughed at 5G conspiracy “theorists.” Now the President is basically confirming it. Your move, normies. Will you keep staring at your glowing rectangle while they turn the air itself into a surveillance net? Or are you finally ready to reject the smart-grid prison?

Paperclip AI is ass

I built a six step pipeline that creates videos that sound exactly like you and a YouTube API scraper that finds gaps in industries for video ideas!!

Electric liquids | plasma | super cool ionized gas in specific materials

@StefanBurnsGeo Is that earth facing and is that current?

This large Earth-facing coronal hole is pretty gnarly. Engage your imagination! What's everyone seeing?

The only constraint is did the AI read my note correctly and did it plan correctly so it needs to ask the human did I do this right?

An MD file is just a note

My AI agent architectures are just English

Might get hub repo’s are just English MD files

My automations templates and deliverables are in English

I code in English My deliverables are in English My strategies in architectures are in English English English English

A 5G tower at an elementary school in California has been shut down after multiple students and teachers were diagnosed with cancer. The data is starting to catch up with the marketing. A 2022 review found that 74% of studies showed negative health effects near these towers. DNA Damage: RF radiation creates micronuclei in the blood—a marker for cancer. We are essentially living in a microwave. The Blood-Brain Barrier: RFK Jr. has warned for years that 5G disrupts the very shield that protects our brains from toxins. The Profit over People: Why are these towers near schools? Because the industry prioritizes signal strength over biological safety. ✨🙌🏽💫 © Reality Check

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.

Knowledge Architecting highvibetribe.beehiiv.com/p/knowledge-ar…

🚨 BREAKING: Scientists just learned how to control magnetism at the atomic level. Not materials. Not circuits. Individual spin patterns. Read that again. Instead of using electric charge… they’re using the spin of electrons to store and process data. And it gets crazier: They can create tiny magnetic whirlpools called skyrmions… that move with almost no energy and can store massive amounts of data This means: Faster computers Lower power usage Ultra-dense memory But the real shift is this: We’re not just building electronics anymore… we’re engineering structure at the smallest possible scale. So the real question is: If information can be stored in spin itself… what limits computation? Follow me I’m tracking where physics becomes technology.

@RealAlexJones Ur an idiot

VIDEO FOOTAGE: Iranians Volunteer To Go Out On Major Bridges & Around Powerplants, Putting Their Lives On The Line In Response To Trump's Threat To Destroy Their Infrastructure & Eradicate Their Civilization! 🔴WATCH/SHARE THE LIVE ALEX JONES SHOW NOW: x.com/i/broadcasts/1…