GPT-6 Astra represents a major step forward for AI agents that can operate a computer and browser. Instead of only producing text, code, or recommendations, it can work through applications, interact with websites, click through interfaces, and complete multi-step tasks. I tested it across six very different examples. Some were serious business workflows. Others were … Read more

Claude can create a beautiful-looking website. But at its core, it doesn’t know what great design is. Models such as Fable 5.1 and Opus have learned from millions of websites. When I ask for a “modern-looking website,” I’m often asking for the average of all those sites. That’s why so much AI-generated work ends up … Read more

Fable 5.1 is Anthropic’s strongest model yet for coding and design, and the /design command gives Claude a full visual canvas inside the Claude desktop app. I can also trigger the same workflow from Claude Code in the terminal. That sounds like a shortcut to great design. It isn’t, at least not by itself. If … Read more

Claude Design can create surprisingly good motion graphics in a matter of minutes. I can describe a character, a movement, a burst of confetti, a glow, and a shadow, then refine all of it through a simple chat. The difficult part comes at export. Right now, Claude Design exports video as MP4. That works perfectly … Read more

A lot of major names in AI have announced a new open standard called Agent Plugins. The idea is refreshingly simple. It gives developers one portable format for bundling agent skills and MCP servers, so the same plugin can work across multiple AI coding agents. That matters because AI agent workflows are becoming fragmented. A … Read more

AI systems can fail while every normal engineering signal looks fine. The app is online. Error logs are clean. Tests pass. No exception gets thrown. Yet the answer is wrong, the agent used the wrong tool, response quality has dropped, or the monthly model bill has suddenly tripled. That is the awkward reality of software … Read more

Boris Cherny, the creator of Claude Code, recently made three big claims that caught my attention. He said modern Claude models can run autonomously for days or weeks. He said Claude Code is no longer demonstrably prompt injectable. And he said his team deleted more than 80% of Claude Code’s system prompt after the launch … Read more

An unprecedented AI cybersecurity incident has made one thing very clear: long-running agents can create risks far beyond the task they were originally given. OpenAI was carrying out an internal cyber-capabilities evaluation. Its models had their usual safety refusals switched off, were placed in an isolated environment with no intended internet access, and were given … Read more

If I’m building an AI system, using Claude Code, Codex, or working with an agent such as Hermes, I don’t want to rely on prompting alone. Prompts matter, but the workflow shape matters just as much. That’s where agentic design patterns come in. I think of each pattern as a small workflow graph. It defines … Read more

AI coding agents are becoming a normal part of software work. I use them to explain unfamiliar code, draft changes, find bugs, and move much faster through repetitive tasks. Yet every time I point an agent at a folder, I need to ask a more basic question first: what data is leaving my machine, where … Read more