I spent a day trying out Claude’s new agent capabilities. Cowork, Dispatch, and computer usage with Claude Code in the desktop application. All of it.. My honest take: Anthropic is getting close. Almost there, but not quite. And they’re heading in precisely the right direction. For context, I’ve been developing my own AI agent for months. It runs on a dedicated Mac Mini, maintains 25 background processes, handles my email, conducts research, drafts documents, and communicates with me via iMessage. So when I look at what Anthropic just shipped, I’m not comparing it to ChatGPT or some chatbot. I’m comparing it against my existing 5/224 setup, which definitely shifts the perspective. Before sharing my hands-on impressions, let me take a step back for a moment.
Hacker News – Newest: „claude cowork“