Terminal automation + e2e testing solved Now as simple as snapshot, click, type: – wterm renders terminal-in-html, every cell in the a11y tree – agent-browser automates pages via the a11y tree Here's opencode in one browser driving Claude Code in another https://t.co/kuuy9E78c2

I started contributing to @NousResearch Hermes Agent by doing one thing: reading the code. Then a small fix. Then another. Gateway platforms, skills, bug fixes... It kept going for a long time. Today I received the Developer role in the Nous Research Discord. 🎉 Special thanks to @Teknium for reviewing and valuing every contribution throughout this journey. For anyone thinking about contributing to open source: the best starting point is reading the code. The rest follows. https://t.co/8baosGeEwS 🤖

@I3osio @NousResearch You can use a https://t.co/SBV4zbHZxJ key directly or a Nous Portal oauth login, whichever you like. You can use cheaper/alternative models but it definitely shines with Nano Banana :)

@Xclusiv @ironsoll Yea I grab 40,000 every day so costs $40 a day to build https://t.co/kiuZ7QXLzb

@realahart @blevlabs @grok Yes I grab 40,000 every day to build https://t.co/kiuZ7QXLzb so $40 a day and @Pokee_AI includes all X API calls for free

@cihatkaya I could teach anyone to do something like https://t.co/kiuZ7QXLzb in five minutes. It isn’t that hard.

Honored to announce we are partnering with Jim Liu to port over his wildly popular skills for infographics and design to work best in Hermes Agent using our native tooling! The first skill ported today, the Infographic Skill, is available after updating hermes. Just start a new chat and type `/baoyu-infographic <topic>` to get started! Recommended image generation model is Nano Banana.

@NousResearch PR for those interested: https://t.co/vcxCVnybGL

Cloud Gen — The next-generation 3D cloud software Over the last 1.5 months, I’ve been secretly working on a cloud-generation software project, where the entire software was written completely by AI. This software is still under development, but this Blender Cycles render was created using exported VDB clouds from this next-generation software.

@ozalabCP The ligand-bound structures had both been determined experimentally and were already up on https://t.co/YrUXpMbiIU, so it went pretty much straight to pymol for the animations

@Eu1583 @openclaws It depends how big your list is. And how active it is. A football team list probably would cost a few cents per day. My app at https://t.co/kiuZ7QXLzb costs about $30 a day to grab 30,000 posts a day

today in the Starbucks mobile app: https://t.co/nxn0vruk32

Free UI suggestion for anyone building a model picker: https://t.co/678L4McAID

@TradeTexasBig Oh, it wasn't even CL, it was its own language! https://t.co/7QAUsbCLd2 https://t.co/M8TCuI8Czq

Tesla officially fully opened their new Montebello location today. The largest @Tesla sales/service/delivery location in California. - 140,000 square feet - 50 service bays - Massive delivery space with dedicated detail area - 100+ Service Loaners - Beautiful showroom https://t.co/DminqJGrh7

+2 more

Comic: https://t.co/7s7hW4Cjt6

Nice paper from Google. And a great application of AI agents. Wearables capture a staggering amount of physiological signals every day. CoDaS is an AI co-data-scientist that turns raw wearable sensor data into clinically relevant biomarkers through an iterative loop of hypothesis generation, statistical analysis, adversarial validation, and literature-grounded reasoning with human oversight. Across 9,279 participant-observations, it surfaced 41 mental-health and 25 metabolic candidate biomarkers, including circadian instability features linked to depression (ρ = 0.252) and a cardiovascular fitness index linked to insulin resistance (ρ = -0.374). Why does it matter? Biomarker discovery is one of the slowest, most expert-bound workflows in medicine. An agentic system that can propose, test, and stress-test candidate biomarkers end-to-end changes the cadence of translational science and starts turning passive consumer sensor data into something clinicians can actually act on. Paper: https://t.co/jxoZARoI4G Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

NEWS: Europe is running out of people. EU’s population is projected to collapse by 50+ million this century as birth rates hit record lows. • Fertility is ~1.4–1.6 children per woman, far below replacement • Deaths outnumber births in many countries This is exactly the civilizational demographic collapse @elonmusk has warned about for years. Low Birth Rate = Decline of Civilization Humanity is dying.

Anthropic shut down an entire company's Claude access overnight 60+ employees. No explanation. Just an email. Want to appeal? Fill out a Google Form. Integrations gone. Histories gone. Everything built on Claude... gone. Never let one vendor own your workflow. https://t.co/196QCCnB4D

> grok4.20-beta1 is a much smaller model than opus but is #1 ranked in medicine and healthcare > 4.3 and 4.4 will be much larger models, and likely will have a significant boost in performance on complex medical cases > this is massively important in providing accurate diagnostic guidance and advice to both providers and patients

NEW paper from Apple. Interesting idea: "Attention to Mamba". The paper introduces a two-stage recipe for cross-architecture distillation from Transformers into Mamba. Naive distillation collapses teacher performance. Their trick: first distill the transformer into a linearized-attention student using a kernel adaptation, then transfer that student into a pure Mamba with no attention blocks. On a 1B model trained on 10B tokens, the Mamba student hits 14.11 perplexity against a 13.86 Pythia-1B teacher, nearly matching quality at linear-time inference cost. If you can reliably convert trained transformers into state-space models without retraining from scratch, the entire open-weights ecosystem becomes cheaper to serve at long context. This is the kind of quiet infrastructure work that decides which architectures actually get deployed in agent stacks. Paper: https://t.co/h7k7OrG8Qj Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c

NEWS: Grok hits an all-time high in monthly active users on the App Store. 🚀 • Highest MAU ever recorded • Strong acceleration into 2026 https://t.co/KxInAh1fRu

"Assuming the current trend of AI and robotics continues, which seems likely, the AI and robots will be able to do anything that that humans want them to do, essentially, so hopefully not more than that, but AI and robotics will be able to provide us all the goods and services that anyone could possibly want so you wouldn't need to work. People will be able to wherever they want with their free time. Work will be optional. I just want to separate out from like what I wish would happen versus what I predict will happen. Because people get confused about that. They think that what I predict will happen is what I wanted to happen. What I predict to happen is not the same as what I want to happen." 一 Elon Musk

@jaredsuniverse I have 50,000 in tech in lists here (8,400 AI Companies too): https://t.co/fasUz7PuHq And my AI finds all the best for you: https://t.co/kiuZ7QXLzb Great ways to find new people to follow.

@nbZ3eIgjMQtBh6k @openclaws My AI at https://t.co/kiuZ7QXLzb reads 40,000 posts every day. You can't read that many. It's way faster than you are.

@Jason @elonmusk @steipete @openclaw It's how you can build an app to cut down how prolific I am. My AI at https://t.co/kiuZ7QXLzb only shows important posts. It reads 40,000 posts a day to make that.

@Xclusiv @MemesOfMars Yes. Way cheaper. My agents at https://t.co/kiuZ7QXLzb grab 40,000 posts a day. $40. Way better than the $300 I was paying.

Hermes Agent has entered the top 5 of highest ranking AI tools based on our compound trendscore! @Teknium @NousResearch Will they be able to dethrone the current #1 @openclaw? Follow us to see if the can!🚀 Our algorithm uses many different sources to rank the most popular AI tools, based on real adoption, community sentiment and many other indicators. Follow us to find the projects that actually offer real value, and are not only hype!

@NotPhilSledge @openclaws Me too! (DMd Elon about it a couple of weeks ago as I was building https://t.co/kiuZ7QXLzb

Agents that run code need a controlled workspace ready when work starts. @modal shares why scale matters for long-running agents built with the Agents SDK. https://t.co/7YdC5VR58Y

Codex Computer Use drawing a portrait of me! It called this a “bold little caricature.” I see the resemblance! https://t.co/tIr56KRNkT

The Justice Department just told French law enforcement authorities it wouldn’t facilitate their efforts to investigate @X. @TheJusticeDept accused France of abusing its criminal justice system to target an American company and censor free speech — in clear violation of the First Amendment. “This investigation seeks to use the criminal legal system in France to regulate a public square for the free expression of ideas and opinions in a manner contrary to the First Amendment of the United States Constitution.”