Six months ago, building an AI agent meant knowing Python, understanding API calls, and spending a weekend debugging JSON errors. Today, someone with zero coding background can spin up an agent that...
Posts by Ty Sutherland
Multi-Agent Systems: What Really Happens When AIs Collaborate
Last year, OpenAI’s internal research team used a multi-agent setup to autonomously replicate and extend published machine learning research — not by having one model grind through it, but by...
Devin AI: What It Actually Does and Why Developers Are Divided
In March 2024, Cognition AI posted a demo video of an AI agent called Devin completing a full software engineering task — reading docs, writing code, running tests, fixing bugs, deploying a project...
OpenAI Operator: What It Can Do and Where It Still Falls Short
Operator is OpenAI’s bet that the next big thing isn’t a smarter chatbot — it’s an AI that actually does things for you. Not summarizes, not suggests, not drafts. Does. Books the...
Claude Computer Use: Tested Capabilities and Real Limitations
In late 2024, Anthropic quietly shipped something that most AI coverage missed the actual significance of: Claude gained the ability to look at your screen and use your computer. Not describe what it...
Anthropic quietly shipped something that changes how Claude works — not in the cloud, not through a browser tab, but directly on your desktop. Cowork is a native macOS application that gives Claude...