🚨Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude.
Taught by the people who built it.
Free. No registration. No paywall.
I've seen $300 courses that don't cover what they teach in the first 8 minutes.
Watch it and bookmark it now.
We’re thrilled to announce the Antigravity CLI, a lightweight way to spin up the same Antigravity agents right from the terminal. 💻
It gives you the exact same harness and same models, with a product experience tailored for the command line. It adapts entirely to you: your keybindings, your themes, your workflows.
Full Antigravity CLI Walkthrough:
This just in: Gemini Omni is now available for everyone to try in Google Flow! 🥳
Earlier this week, we introduced Gemini Omni, our new model that lets you edit your videos using natural language (it’s like Nano Banana, but for video!). We have loved seeing your video edits so much that we are opening up access to everyone! If you are not a Google AI subscriber, you can still create two Omni videos free of charge each day.
Check out how we created this video with a one-shot prompt (🤯), and try it for yourself with Omni now.
https://t.co/N6P2Oj4841
Condensed notes from our episode on vibe coding:
‘A Return to Code’
1. Vibe coding is addictive because it gives you feedback and rewards like a video game, except it is unbounded because there is a Turing machine running underneath.
2. With a coding agent, you don’t feel self-conscious about your own idiosyncrasies, so you can create exactly what you want.
3. Coding agents remove the social cost of iteration: “Move this icon left. Now move it right. No, move it back again.”
4. Pure software is uninvestable if your whole advantage is just building cool software that other people don’t know how to build.
5. Training AI models is the new building software, at least until autoresearch and autotraining start working.
6. Models are like a dog that is always trying to please you: it’s better than you at some things, but you still have to guide it.
7. Models work in domains where there is a lot of data and verification is tractable, like coding, mathematics, and self-driving.
8. You need high-taste feedback loops to improve these models, and those are harder to develop than they look.
9. Software development will become a collaborative process with the users, where agents handle bug reports, feature requests, customer service, and code.
10. The activation energy to writing code is gone.
Claude Managed Agent
Most “agent” tools either oversimplify… or overwhelm.
Managed Agents gets the balance right.
It abstracts the heavy lifting like sandboxing and infra, so you can focus on building, not plumbing. But at the same time, it gives you real control over how the model runs and behaves.
This is what founders actually need: speed without losing control.
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.
It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.
Now in public beta on the Claude Platform.
Best GitHub repos for Claude code that will 10x your next project:
1. Superpowers
https://t.co/U5Y4BK9Lap
2. Awesome Claude Code
https://t.co/qcgoxU3Up2
3. GSD (Get Shit Done)
https://t.co/WfAhllWnTR
4. Claude Mem
https://t.co/XLQpwdnIWN
5. UI UX Pro Max
https://t.co/aQtGjMzKus
6. n8n-MCP
https://t.co/7le1aluZXH
7. Obsidian Skills
https://t.co/MUaoyUnasw
8. LightRAG
https://t.co/ye8z4UqaMc
9. Everything Claude Code
https://t.co/OAU9JE46Uz
🚨 BREAKING: Google Gemini can now analyze any stock like a Wall Street analyst (for free).
Here are 10 insane Gemini prompts that replace $4,000/month Bloomberg terminals:
Save for later🔖