Today, our computer-use datasets crossed 50,000+ hours. Screen recordings... + synced mouse/keyboard actions + narrations across CAD, design, browser-use & more. Sourced from humans and available off the shelf today :) Samples below.show more

Today, we're launching the world's largest open-source CAD dataset... for computer-use. 1,000+ hours across SolidWorks, Siemens-NX, AutoCAD & more. Screen recordings, mouse/keyboard actions, input diagrams, output files, rubrics and narrations. Link in the comments :)show more

Today we're launching the most advanced computer-use dataset in... the world. 1,000+ hours of screen recordings along with mouse/keyboard inputs + annotations. Sourced from experts across coding, design, browser-use, research and more. Link in the comments :) Markovshow more

Today, we're launching the largest open-source dataset of gaming... data for computer-use. 500+ hours of gameplay screen recordings + keystrokes/mouse movements, across Valorant, Minecraft, GTA and more. Link in the comments :) @markov__aishow more

Today, we're launching the world's largest open-source dataset of... computer-use recordings. 10,000+ hours across Salesforce, Blender, Photoshop and more, to automate the next level of white-collar work. Link in the comments :) @markov__aishow more

Today, we're open sourcing the first computer-use dataset for... design. We captured 200+ hours and 3400+ trajectories of real design work in Figma, recording step by step how designers execute complex, long-horizon tasks. FigmaTrace dataset, paper, and blog below :) PatronusAIshow more

Connect with interesting people from across the world. Use... our country feature to select your country of choice and start meeting interesting people today over a live video chat #livu #livucoins #meetnewpeople #livevideochat #nobotsshow more

Today we’re releasing Code Llama, a large language model... built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools. Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use. More ⬇️show more

Today we’re introducing Copilot Mode in Edge, our first... step in reinventing the browser for the AI age. My favorite feature is multi-tab RAG. You can use Copilot to analyze your open tabs, like I do here with papers our team has published in nature journals over the last year. And there is a lot more to come, including built-in actions so you can delegate tasks as you browse.show more

It’s Restart a Heart Day 2023! This year, we... are promoting the use of public access defibrillators and highlighting health inequality around access. Keep a look out for more from us and our partners today and throughout the rest of this month. #RestartAHeartshow more

Our first official ActionFi partner is here. We're kicking... things off with SIXR Cricket and a massive $100K reward pool. And you don't have long to wait. SIXR goes live on ActionFi in 4 hours time. Want to be ready from the moment it drops? Sign up to Action Model. Download the Browser Extension. Join our Discord. Get ready to take action. $100K. SIXR Cricket. 4 hours time. ActionFi starts today 12pm UTC.show more

What is the best video editing agent for short... form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!show more

Since many of you asked yesterday: Unkey paid us... $90k for this rebrand and design. If you think that’s a lot, it really isn’t once you see how much was delivered. Good branding is not just a logo and a few gradients - it’s a huge system built to help a brand evolve across materials without relying on the same visual trick over and over. That’s exactly the kind of system we build for companies. And while today you’ll probably see another round of scary posts about design being eaten by GPT Image 2.0, remember: there are still companies willing to pay a lot for branding done by humans with taste. Those humans may use AI. AI may help speed things up. But it’s still just a tool - and like any tool, you need to learn how to use it.show more

You mine Bitcoin. Soon you can carry the brand... too. The first of our merch reveals drops today, and it starts with the GoMining Bottle. Limited, clean, and made for daily use. More drops are coming soon, and the launch date will be revealed shortly. So keep your eyes open, because this is only the start 👀 If you could put one GoMining design on your desk every day, what would it be?show more

Colder weather is here, SWEP is being activated across... the country, if you see a rough sleeper please make sure you use the link below so the charities in your area are notified where they are so they can get emergency support to them during these freezing conditions, we also have a room available and will be out there offering as much support as possible over the next few weeks. If you see anyone that needs support locally please drop me a DM or use the streetlink below to get them emergency support from local charities in our/your area 🙏🏻show more

Today we celebrated the topping off of Cosm Cleveland,... right here in Cleveland's Gateway District, across the street from Rocket Arena. Set to open in Summer 2027, Cosm Cleveland will be Cosm's fifth venue and its largest nationwide. The immersive entertainment destination will anchor Bedrock's Rock Block development and add even more vibrancy to our city's urban core. To every tradesperson who has put in the hours, the skill and the energy to get this project here: thank you.show more

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND... LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇show more

Stellar House Miami kicks off today 🦩 Inspired by... the vibrancy and international culture of the city, this exhibition features never-before-seen pieces from artists tabithaswanson_, Dina Chang, ellie pritts 🐸, Saeko Ehara / Artist and VJ, Genki Nishida, occulted, andy rolfes, and nygilia All artworks are available to collect using your Meridian Pay wallet, exclusively for event attendees. Today also marks the soft launch of the IRL wallet on Stellar — use the IRL Touchpoint & create your wallet on Privy to earn points for supporting the art.show more

Introducing ml-intern, the agent that just automated the post-training... team Hugging Face It's an open-source implementation of the real research loop that our ML researchers do every day. You give it a prompt, it researches papers, goes through citations, implements ideas in GPU sandboxes, iterates and builds deeply research-backed models for any use case. All built on the Hugging Face ecosystem. It can pull off crazy things: We made it train the best model for scientific reasoning. It went through citations from the official benchmark paper. Found OpenScience and NemoTron-CrossThink, added 7 difficulty-filtered dataset variants from ARC/SciQ/MMLU, and ran 12 SFT runs on Qwen3-1.7B. This pushed the score 10% → 32% on GPQA in under 10h. Claude Code's best: 22.99%. In healthcare settings it inspected available datasets, concluded they were too low quality, and wrote a script to generate 1100 synthetic data points from scratch for emergencies, hedging, multilingual etc. Then upsampled 50x for training. Beat Codex on HealthBench by 60%. For competitive mathematics, it wrote a full GRPO script, launched training with A100 GPUs on watched rewards claim and then collapse, and ran ablations until it succeeded. All fully backed by papers, autonomously. How it works? ml-intern makes full use of the HF ecosystem: - finds papers on arxiv and reads them fully, walks citation graphs, pulls datasets referenced in methodology sections and on - browses the Hub, reads recent docs, inspects datasets and reformats them before training so it doesn't waste GPU hours on bad data - launches training jobs on HF Jobs if no local GPUs are available, monitors runs, reads its own eval outputs, diagnoses failures, retrains ml-intern deeply embodies how researchers work and think. It knows how data should look like and what good models feel like. Releasing it today as a CLI and a web app you can use from your phone/desktop. CLI: Web + mobile: And the best part? We also provisioned 1k$ GPU resources and Anthropic credits for the quickest among you to use.show more

One idea, a playable game. Nex-N2.5 Pro drove the... whole thing rough idea →2D sketch →Blender 3D scene →finished game. It wasn't prompting from a distance it opened the tools, watched what changed on screen, and kept going the demos keep landing on the same question: can it actually use a computer? not generate an image of a kitchen call Blender MCP, build the kitchen, render it, read the result. Not describe a CAD part script it, adjust parameters, hit an export wall, switch to the GUI, hand off the drawing try it free on openRouter for a limited time: #NexN2 #Blender #ComputerUse #OpenRoutershow more