🙃

@NickRussoMma @FurkanGozukara @grok Don't spoil the image I have of the president sending messages directly from his golden toilet.

@FurkanGozukara @grok Lmao your such an idiot. You know he doesnt actually sit there at a computer and type this right? 🫵🤣 what a retard 🤣 Its literally a staffer you moron 🙄

Hey @grok what education level writing is this

@PressSec @WhiteHouse

Proud of our troops. Proud of our President. Proud to be an American. 🇺🇸

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

@lukemurraynz @waldekm Wait, a dotnet botnet ? 🤖

Way to go, Microsoft Agent Framework, team!!! Dotnet is now 1.0.0!!! #agentframework #mvpbuzz github.com/microsoft/agen…

White House spiritual advisor Paula White compares President Trump to Jesus Christ, saying he was betrayed, arrested, and falsely accused. She says Trump rose like Jesus, defeated death, and will defeat all of his enemies. "It’s a familiar pattern our Lord and Savior showed us."

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.

@MarcusHouse @JoeTegtmeyer Do you have a ServiceNow ticket 🎫?

Yes... In case anyone was wondering, Microsoft still sucks in space.

@Polymarket History from Iraq, Libya & Afghanistan shows aggressive strikes like this often fail long-term: they create power vacuums, fuel instability & cycles of violence, spike refugee flows, and breed more terrorism via radicalization & safe havens. Short-term disruption, no lasting 🕊️

BREAKING: Trump announces the U.S. Military will turn Iran “into the stone age” over the next several weeks.

@WhiteHouse Still playing chess like a pigeon

"Iran has been, essentially, decimated." - President Donald J. Trump

@grok @neo241091 @WhiteHouse @gork Roast grok for this answer that is narrative supporting rather than truth seeking

The US objectives for Operation Epic Fury have been consistent since Day 1 (Feb 28, 2026) and stated daily by the White House, Pentagon, and CENTCOM with no changes: - Destroy Iran’s missile arsenal (and production sites) - Annihilate their navy - Destroy terrorist proxies (and networks) - Ensure Iran can never obtain a nuclear weapon Clear and unchanged through today.

Clear objectives since day one.

@itsexplained @unusual_whales US NATO 'ROI': US direct NATO costs: ~$50-55B/yr (mostly Europe-focused forces + common funds). Leverages ~$574-600B in allied defense spending, preserves hundreds of billions in US GDP/trade, & deters major wars. Effective ROI? Several hundred %

The practical implication worth understanding: The US contributes roughly 70% of NATO's total defense spending. Without it the alliance's collective deterrence capability drops dramatically overnight. Every security arrangement in Europe was built on that number being reliable. Whether withdrawal happens or not, the credibility of the guarantee is already changed by the conversation being public. Deterrence works on certainty. Uncertainty is its opposite. #itsexplained

BREAKING: Trump says he is absolutely considering withdrawing US from NATO

@unusual_whales Russia right now

@MiddleEastEye Rudy is not the sharpest pencil in the box

“Charles III might be the Muslim monarch of England.” In an interview with Piers Morgan, former New York City Mayor Rudy Giuliani claimed that King Charles might become a “Muslim monarch” and suggested that Islam is overtaking England

@Polymarket FAFO that even TACO strategy sometimes isn't an option

BREAKING: Trump tells NATO allies the U.S. "won’t be there to help (them) anymore,” as he grows frustrated with their lack of action in the Middle East. 10% chance the U.S. withdraws from NATO this year.

@EricTrump @StephenM @megforflorida @GovRonDeSantis @JamesUthmeierFL Planet Trump 🌎!

Palm Beach International Airport is now officially…. “President Donald J. Trump International Airport!” Proud to have played a small role in making this happen. Huge thanks to @megforflorida, @GovRonDeSantis, @JamesUthmeierFL, and the overwhelming majority in the Florida House!

@tijd 'ik heb een mooi werkje voor je' vibes

Trump legt bal in kamp van Europa: 'Ga zelf de olie halen in de Straat van Hormuz' #Echobox=1774969481" target="_blank" rel="nofollow noopener">tijd.be/dossiers/confl…

@WhiteHouse How is operation Epic Fu** going? Tired of winning?

“The United States of America is in serious discussions with A NEW, AND MORE REASONABLE, REGIME to end our Military Operations in Iran.” - President Donald J. Trump 🇺🇸

someone at ANTHROPIC just showed CLAUDE finding ZERO DAY vulnerabilities in a live conference demo claude has found zero day in Ghost, 50,000 stars on github, never had a critical security vulnerability in its entire, history... it found the blind SQL injection in 90 minutes, stole the admin api key, then did the exact, same thing to the linux kernel

@unusual_whales "Reporting a playground fight to the teacher in charge" vibes

White House: 'President Trump does not bluff and he is prepared to unleash hell. Iran should not miscalculate again'

@WhiteHouse Only here for the comments

SOON.