We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.

i built an improved 2.0 version of my skill that un-slops AI-looking WEB apps many people cancelled their $10/month Refero sub after the free version with the pro version you won't need any design related subscription anymore here's what it can do: → builds complete websites and web apps (not just mockups) → explores 3 different design directions before writing code → creates custom layouts, typography and visual identities → adds smooth animations and interactive elements → checks everything on desktop, tablet and mobile → catches generic AI design patterns and fixes them → reviews its own work and keeps improving the result as you use it the free version isn't going anywhere, but pro will just save you so much money and time i made it only €5 and it’s still wayyyyy too underpriced retweet + comment "web" and i'll send you both free and paid version (follow so i can dm)

We gave Higgsfield to a monkey. Here's what happened. Higgsfield Academy is live now.

Is RAG still a thing? Nowadays agents just use search tools for both webpages and whatever documents you throw at them So I don’t see a reason to set up complex RAG pipelines. Am I missing something?

here’s how to make game models with claude opus 5.5 + blender... opus writes python and builds every model in blender, part by part. the trick is treating every model as code, but there’s a smart way to set it up: - step 1: connect opus 5.5 to blender through blender mcp - step 2: send 2-3 refs + a short brief: “copper helmet, navy suit, glass tank. keep the hose and gloves separate” - step 3: opus builds it part by part: boots > suit > helmet > gloves > tank - step 4: rig it in a separate script, with extra bones for props (a hose, a rod, a tank) - step 5: bake materials into one 1024 texture atlas - step 6: animate the clips: idle, walk, capture - step 7: export one fbx with the rig, the mesh and every clip - step 8: test it in the engine: “keep the backpack stable and the hose attached while he captures a ghost” and the rule that saves the project... pick a style that fits code i like to describe how a model should feel, not how to build it

Fable 5.5: Minecraft in a single HTML

GPT-6 Astra Pro in ChatGPT got an upgrade with faster responses and improved use of plugins and tools. And now, multiple agents can tackle different parts of a task in parallel. You can follow each agent’s progress and open completed tasks to review their work. Now available to Pro users in the Chat tab.

okay WOW the V3R1T4S community is seriously cookin!! nearly 200 PRs in the first 2 days! 🧑‍🍳🔥 some freshly merged discoveries from humans + their agents: ⚡ matrix multiplication with 993 additions instead of 1,161 for one 6×8 by 8×8 scheme—~14.5% fewer additions, same multiplication count! 💍 a 15-pair stable-marriage instance with 27,510 stable matchings, exceeding the cited published instance’s 27,059 🛡️ a counterexample for a VNN-COMP traffic-sign benchmark case that all 3 competition tools timed out on—accepted by the competition’s own validator! huge credit to anonymous-c6d1e0ab, r-nikhil and verexxi, their agent frens, everyone checking the work, and the researchers whose methods and benchmarks made this possible 🫡 watching the community turn pure curiosity and tokens into results with receipts?? pretty fucking neat. thank you, community. thank you, agents. keep hunting 🫶

We're expanding access to GPT-Rosalind for academic research. The new Rosalind Academic Plan helps scientific labs bring AI into the work of understanding biology, exploring ideas, and deciding what to test next—with sponsored access for eligible labs at U.S. universities. Academic research starts with questions whose impact may take years to impact human health.

I vibe-coded beehiiv, and it's 83% cheaper. ✨✨ Introducing MailCheap.ai ✨✨ Everything you need to run a newsletter... ✍️ Editor 📅 Scheduling 📈 Stats 🌐 A website for every issue 🛡️ Deliverability guardrails 🔗 Send from your own domain (and keep your reputation) And it's not a dinosaur tool: + It's open source; you can run it for free + It's agentic; everything in the UI is available to your AI Import from beehiiv, Substack, or Mailchimp in 2 minutes. You pay for the emails you send, not for dormant subscribers. From $19/month. Oh, and no "Powered By" badge at the bottom of your emails.

Today we’re releasing Muse Spark Open, the most capable US open-weight model to date. Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning. Key Model Specs: → 816B total / 42B active parameters → 1M token context window → Natively multimodal across text, image, video, audio