If you are using AI for your design, this is someone you must follow

16 minute tutorial on how to build $50,000 cinematic websites (step by step) with Claude Fable 5 Save this before you lose it 🔖

Calling all fans of Google Play 📣 You can help shape the future of Google Play Games! Sign up for user research and, if chosen, your feedback could earn you rewards (and a sneak peek at what’s coming) 👀 goo.gle/45xO67L

Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.

Thank you, Tulsi, for documenting Dr. Fauci's central role in causing the COVID-19 pandemic — among the most consequential crimes in human history.

Andrej Karpathy once said: "You literally have to put in 10,000 hours to learn Claude" In this 11-minute workshop, he shares how he actually uses Claude, the features he relies on & the workflows behind his productivity

Opus Claude Is Insane. This is a tutorial a 12 min on how Build 3D Websites in Minutes with Al (0 Design + 0 Coding) with Claude Opus 4.8

New in Claude Code: Artifacts. Interactive pages built from your session, like a PR walkthrough or a living project dashboard, shared with your team at a private link. Available in beta on Team and Enterprise plans.

An Anthropic engineer gave Claude one sentence and walked away for 6 hours. The sentence was: “build a retro game maker.” Cost: $200. No second prompt. No fixes. No hands on the keyboard. When Claude builds alone, it makes something that looks finished. A clean sprite editor. A color palette. A play button. Press an arrow key. Nothing moves. Press space. Nothing happens. The model thought it was done. It had no idea how to play its own game. So they tried something else. 3 Claudes instead of 1: a planner that decides what to build a builder that writes the code an evaluator that opens the app and actually plays it The evaluator launches the game. Presses the keys. Watches what breaks. Then hands the bugs back and says one word: no. 6 hours later. Same prompt. Same model. This time it named itself RetroForge. 45-color palette. Working physics. A play mode where the player moves, collides with walls, takes damage. And one thing nobody asked for: an AI assistant built inside the app, so you can type “castle with a dragon guarding it” and watch it appear. The prompt never mentioned that. Same model. Same single sentence. The only difference was a second Claude whose entire job was to be the harshest critic in the room. 1 year ago Claude lost the thread after 20 minutes of coding. Now it runs for days. The full 6-hour build is in the video. Watch the moment it starts grading its own work.

Unreal Engine 5.8 ships today with experimental MCP server support: Your sources, your pipeline and your workflow—simply configure the MCP plugin and connect to any agent. Get familiar with the MCP server and the PCG Primitive Plugin today and see what teams can build together: epic.gm/ue-5-8-blog

Unreal Engine 5.8 has AI integration with Claude and Codex. Runs in terminal beside the engine, connected via MCP to fully control the Editor. Place props, generate cities procedurally, and even art direct the lighting. Unreal Engine 5.8 available today. Pretty much any Unreal game from now on is gonna need an AI label.

Anthropic Claude Code engineer: "If you're watching Claude write code, you're the QA tester. That's not what you're paid for." In 37 minutes he lays out how to get your keyboard out of the hot path entirely. The shift is /loop. You tell Claude to wake up every 10 minutes and babysit your PRs, and it just does it, while you're nowhere near the laptop. Routines do the same in the cloud, so the work keeps running with your machine closed. He caps it with remote control: any session, on any surface, driven from your phone. Watch the full talk, then grab the setup below.

OpenAI co-founder Andrej Karpathy: "You literally have to put in 10,000 hours to learn Claude" 11-min workshop from Goat of AI - how he's actually uses it He reveales all the features that he use in this video bookmark & watch - the most prodactive way for your evening

Anthropic Product Lead: "At Anthropic, our engineers are running swarms of 300+ agents daily. Give your agents 100+ tools - just don’t load them all into context." In a 30-minute talk, the Anthropic team shows how to deploy agents to production. Claude + loops + routines + dynamic workflows - that’s the secret. Watch the talk, then save the playbook below.

This model is insane at design. I asked GLM 5.2 (left) and Opus 4.8 (right) to build me a landing page and you can't even tell the difference. GLM cost $0.06 while opus cost $0.49. More than 6x cheaper while being faster + more token efficient. Another win for open source AI.

Introducing GLM-5.2: Frontier Intelligence, Open Weights - Significant improvements in coding and agentic tasks - Strong long-horizon capabilities with a 1M context window - Two levels of reasoning effort: GLM-5.2 (max) pushes the limits, while GLM-5.2 (high) strikes a strong balance between performance and token efficiency - MIT-licensed open weights - Same API pricing as GLM-5.1 Tech Blog: z.ai/blog/glm-5.2 Weights: huggingface.co/zai-org/GLM-5… API: docs.z.ai/guides/llm/glm-5.2 Coding Plan: z.ai/subscribe Chat: chat.z.ai

ANTHROPIC QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE BUILD ITS OWN TEAM OF AI AGENTS INSIDE CLAUDE CODE Not subagents reporting to a manager but actual agents that message each other, review each other's work and collaborate like a real team. In the demo a team lead created a QA engineer, a frontend developer and a backend developer. The QA agent found three bugs, sent feedback directly to the developers, they fixed the issues and the app shipped in a single pass. It's called Agent Teams and it's available in Claude Code v2.1.32 and newer.

Amazing features more from @claudeai

Claude FULL COURSE 1 HOURS (Build & Automate Anything)

Context engineering works because agents perform better when they can build on prior knowledge. The next challenge is making that knowledge survive the next session, workflow, or model change. Memory belongs to the workflow, not the model.