https://t.co/1ehWJY2zsb by @KentBeck

🚀 Introducing Strands Agent SOPs: Natural language workflows for reliable AI automation! From code reviews to feature development, meeting notes to incident response. Author new SOPs in minutes, chain for complete automation sequences. https://t.co/MEHjFHXLen Born from Amazon's

This killed me.

This story is wild Chinese state-backed hackers hijacked Claude Code to run one of the first AI-orchestrated cyber-espionage Using autonomous agents to infiltrate ~30 global companies, banks, manufacturers and government networks🤯 How the attack was carried out in 5 phases

If you saw how people actually use coding agents, you would realize Andrej's point is very true. People who keep them on a tight leash, using short threads, reading and reviewing all the code, can get a lot of value out of coding agents. People who go nuts have a quick high but

Bob Ross vibe coding was the AI slop I never knew I needed in my life

$24,000 per year from this simple AI Dentist Voice Agent (and why I'm crazy for giving it away for free) A dental practice was losing $6,000+ in revenue every month from missed after-hours calls. That's 20-25 potential patients walking away because no one was available to book

Multi-agent AI is a $50B lie. 99% of "multi-agent" systems are just single agents with fancy marketing. I just read the paper that exposes what real multi-agent intelligence actually looks like. Most people think multi-agent AI is just "multiple ChatGPTs in a room. That's

Complex orchestration frameworks for AI agents - state machines, workflows, error handling - seem necessary. But what if they're actually holding back what modern LLMs can do?

We recently ran a successful live failover of our control plane database from Azure West US to East US 2. Our goal was to validate that Vercel can survive a complete regional failure of its core database. Here's the full breakdown: https://t.co/5ng7adhZLc

AI has done something no human ever could. It got developers to pay for software.

More visual info (architecture and sequence diagram) on the Strands A2A Demo I shared yesterday – How to run multiple AI agents using A2A (agent-to-agent) with the Strands Agents SDK, including interacting with a CLI, web, and speech interface. https://t.co/zeoKj3k09M

Just published an extensive demo showcasing how to build multi-agent AI systems using the A2A (Agent-to-Agent) protocol with the Strands Agents SDK. Check it out:

Presenting VIBECODR - the ultimate vibe coding keyboard.

As we used to say “a fool with a tool is still a fool…”

The Model Context Protocol (MCP) is not just "another API lookalike." If you think, "Bro, these two ideas are the same," it means you still don't get it. Let's start with a traditional API: An API exposes its functionality using a set of fixed and predefined endpoints. For

Anthropic's MCP is a thing of beauty. This makes AI agents 100x more powerful. MCP stands for "Model Context Protocol." It's an open standard for connecting AI with data. Instead of worrying about 10,000 different ways to do the same thing, MCP provides a standard approach. •

Once a week I tell young developers: "stop trying to compete in crowded spaces, go build & monetize MCP servers instead." The opportunity is insane right now. No competition, wide open space, and VCs are begging to throw money at solo founders who get there first.

I'm amazed by how useful MCPs are. They're going to explode, along with all the dev tooling for sure. I set up a DB function in Supabase and couldn’t figure out why it wasn’t running. I connected a Supabase MCP, asked Cursor to troubleshoot, and watched it: - Find the DB

llms.txt and MCP feels like the beginning of the AI internet protocol stack. As these conventions proliferate, the network gets more powerful and intelligent, and a lot more applications become possible.