Your curated collection of saved posts and media
Elon Musk with NVIDIA CEO Jensen Huang, Apple CEO Tim Cook, President Trump, Chinese President Xi Jinping, and members of the U.S. delegation in Beijing. https://t.co/sooA1y9yl1
New paper in Nature. The more a government controls its domestic media, the more it dominates AI training data, the more pro-regime outputs we get from AI. By scraping the open web, LLMs are unwittingly laundering state-coordinated narratives into seemingly objective answers. https://t.co/msncoexOoO
Singapore here we go ๐ฅ https://t.co/0qx2W6hfe4
Singapore here we go ๐ฅ https://t.co/0qx2W6hfe4
my entire Hermes Agent setup is controlled from one folder on a VPS I can manage it from my laptop or phone in under 10 seconds, spin up isolated agents per project, and never lose context here's the full setup: > bash command "ssh hermes" auto-connects to the VPS > session pinned in CMUX terminal for instant access > Claude Code session inside the ssh connection with full remote access > everything runs from a control station folder folder structure: vps-agents/ โโโ README .md overview + how to use it โโโ CLAUDE .md auto-loaded project context for Claude Code โโโ agents/hermes-main/ โ โโโ inventory .md IP, hostname, where it runs, who owns it โ โโโ docker. md draft docker-compose + first-boot checklist โ โโโ runbook. md "it broke, what now" โ 7 common scenarios โ โโโ env-map. md table of which keys live where (no values) โ โโโ backup. md GitHub backup flow + restore steps โโโ shared/ โโโ security. md VPS-wide hardening checklist โโโ commands. md Docker / Hermes / UFW cheat sheet from this session I can spin up new docker-isolated agents per area and each one can have sub-profiles the whole stack is documented, backed up to GitHub, and accessible from anywhere
Hermes Agent changed how I work it's the highest leverage agent framework you can set up right now what makes it different: > it routes tasks to the right model based on complexity and cost > learns your voice and preferences over time > handles context switching without losin
Working on a โHooded Ouroborosโ collection of Herm skins. Work your Hermes with style! Kaio has already laid amazing foundational work, just trying to open up the spectrum. https://t.co/EYhVR3CSET

Jack Dorsey on how every company can now be a mini-AGI: https://t.co/eAhu9dNwCG
Jack Dorsey on how every company can now be a mini-AGI: https://t.co/eAhu9dNwCG
See you in Singapore. BTW, I'm starting to look more and more like our logo. https://t.co/oMSebDUNPk
Red light can literally reduce fat in the belly / waist area via spot reduction, some fascinating research shows. (๐งต1/8)
Will putting red light on your balls triple your testosterone? The science might surprise you. (๐งต1/8)
@MSaintjour @nikitabier See https://t.co/kiuZ7QXLzb and https://t.co/5zCgGYmZcO for what you are up against. My reach is down too. We are all competing to get on peopleโs feeds.

@TriCast_ Yes sir! Built https://t.co/kiuZ7QXLzb best AI news from X
@maticrobots Cleaningโฆ https://t.co/OSGBTLW7XX
They put me in makeup. https://t.co/1qaGfK9s54
Introducing Higgsfield Supercomputer The first ever cloud-native, self-learning AI agent for end-to-end task execution. 40+ built-in tools. Three layers of memory. Access via browser or Telegram. Powered by enhanced Hermes Agent. https://t.co/ZgWQBcjhk3
I finished the dataset for the most recent DoW UFO/UAP release - the entire corpus is up on hugging face/GH It also ships with an Hermes Agent skill so you can easily start querying the data immediately. Go chase some anomalies ๐ https://t.co/KpiMeFVPIb https://t.co/6gSfB0mjzi

posting on ๐ 30,000 ft in the air all thanks to @Starlink @United ๐ซถ https://t.co/EdlOzqVcal

Local agent media superpower. ComfyUI and Hermes Agent running together locally on AMD Ryzen AI Max+ processor based Agent Computer. https://t.co/M1yg4KHx86
Everyone at Red Bull Mirage brought a DJ. We brought a robot. The robot worked out of the box, no additional training onsite. 8 hours. 700+ Red Bulls served. 99%+ success rate. No humans, no breaks, no resets. Shifting desert light. Cans handed in at every angle. Thousands of people are moving around it. The robot just kept serving. ๐ค๐ฅซ
We asked the CEO of HuggingFace @ClementDelangue what the risks of releasing powerful open source models are. He says restricting AI creates more risk than openness. "Six, seven years ago, at the time it was GPT-2, and there was already a lot of people saying that it was too dangerous to release in open source." "Mythos, when it was announced was crazy dangerous... In a few weeks or a few months, everyone is gonna be using Mythos, and not destroy the world as a result." "For cybersecurity, the biggest risk is that a few players have capabilities that other people don't have... If you make it more open, it's usually easier for defenders to react and make the whole system safer." "The idea of restricting a technology like AI based on risks is like saying, 'Some people can punch other people, so let's tie down everybody's hands.'" "Otherwise you slow down progress, you create massive gaps in terms of controls, in terms of capabilities, and you create actually additional risks."
Weird how some people always target open-source in AI! First it was: โOpen-source AI will destroy the worldโ (spoiler: it didn't and it won't) Now: โOpen-source is a cybersecurity threat because of AIโ Both narratives are far too simplistic. The truth is that the exact same r
watching a team of agents tackling a hard theoretical physics problem is quite mesmerizing - self-correcting, deriving hard equations, computing intermediate results, re-estimating the best approach https://t.co/RhUmNXkGLB
Meet physics-intern๐งโ๐, our agentic framework for theoretical physics. It takes Gemini 3.1 Pro from 17.7% to 31.4% on CritPt, a new SOTA on one of the hardest benchmarks for LLMs. Theoretical physics is hard for humans and LLMs alike. But physics-intern decomposes problems and
Digitโs been clocked in since 2023, streaming continuous operations. https://t.co/DQpAJsCOy2
Digitโs been clocked in since 2023, streaming continuous operations. https://t.co/DQpAJsCOy2
@bhalligan Mine builds an AI news site from X: https://t.co/kiuZ7QXLzb
7,000 false positives per square millimeter. The culprit was the lab gloves. University of Michigan researchers just upended a core assumption in microplastics science. Latex and nitrile gloves, worn by the scientists doing the measuring, shed stearate particles that look chemically identical to polyethylene. Standard infrared and Raman instruments can't tell them apart. The gloves were counting as plastic. Seven glove types tested. All contaminated. The cheapest fix: switch to cleanroom gloves, which dropped false positives to around 100 per mmยฒ vs. 7,000. The "credit card per week" headline (5 grams, WWF/Newcastle 2019) has separate problems. A 2022 re-analysis found severe methodological errors in the original estimate. Actual measured intake is likely 100x lower. None of this means microplastics are harmless. Last month's data on brain accumulation still stands. But the numbers driving the panic may have been measuring the scientists, not the environment. Science catching its own errors is exactly how it's supposed to work.
hey surprise - you can just launch interactive in tmux and then tail the jsonl - shipped a small wrapper...ralph loop iterating to full parity rn https://t.co/3N4klSSEwd https://t.co/Q1ODMrVdpB
Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK

First place: Brut-V by @daumerval A full browser-based RISC-V assembler and Processing-style sketch framework, where Hermes Agent wrote the 6,200 lines of assembly and bootstrapped a JS assembler to byte-perfect parity with the reference simulator through a self-correcting diff/patch loop, demonstrating agents as tools for building tools. https://t.co/bFIWxb0cV8

Hermes Agent now has Computer Use๐คฏ You can now control your actual computer with ANY model through Hermes Agent ร @trycua not just frontier models locked behind special modes. Even crazier: โข Runs entirely in the background โข Doesnโt hijack your PC โข You keep full control of your keyboard, mouse, and screen while the agent works This is starting to feel less like an AI chatbot and more like a real agentic operating system.
Google ๅ ฌๅผ Skills ใๆฅใ 13ๅใฎในใญใซใๅ ฌ้ใClaude Code / Antigravity / Gemini CLI / Cursor / GitHub Copilot ใปใไธป่ฆใจใผใธใงใณใใๅฏพๅฟใใฆใ Agent Skills ๆจๆบๆบๆ https://t.co/9xvVKn004h
New to open source? Learn how to find a good first issue, open a pull request, and make your first contribution with GitHub for Beginners. ๐ https://t.co/PNRb746zCh
MrBeast just gave one of the strongest endorsements possible for Starlink: โI will only book flights exclusively on planes with Starlink. I donโt care if it means an extra layover - Iโll sit in the back of the plane if it gives me Starlink.โ He says Starlink has become the backbone of his global productions and travels because it works in places where traditional internet simply doesnโt exist: โข Filming in Antarctica - one of the only reliable ways to stay connected โข Building wells deep in rural Africa with full internet access hours away from cities โข Driving through remote villages and open fields with a Starlink dish mounted on the vehicle while maintaining signal the entire time He described it as: โStarlink is literally magic. It makes no sense.โ Now people are actively choosing flights based on whether the plane has Starlink onboard