{"articles":[{"_id":"article-signal-noise-march-2026","articleType":"signal-noise","publishedAt":"2026-03-18T10:00:00Z","readingTime":5,"slug":"signal-noise-2026-w12","subtitle":"March 2026, Week 3","tags":["weekly","news","analysis","signal-noise"],"title":"This Week in AI: What Actually Matters","tldr":"Claude 4 benchmarks are impressive but the real story is the pricing. Google's agent protocol proposal competes with MCP. OpenAI's memory API is now in beta. Ignore the 100 'AI wrapper' launches this week.","topicCluster":{"color":"topic-llm","name":"LLM Architecture","slug":"llm-architecture"}},{"_id":"article-agentic-memory","articleType":"deep-dive","publishedAt":"2026-03-15T10:00:00Z","readingTime":14,"slug":"the-architecture-of-agentic-memory","subtitle":"How AI systems will remember","tags":["agents","memory","architecture","context-windows"],"title":"The Architecture of Agentic Memory","tldr":"AI agents need three types of memory to be truly useful: working memory (current context), episodic memory (past experiences), and semantic memory (world knowledge). This article explores how each type maps to technical implementations and why getting memory right is the key unlock for production agents.","topicCluster":{"color":"topic-agents","name":"AI Agents","slug":"ai-agents"}},{"_id":"article-context-window-scaling","articleType":"primer","publishedAt":"2026-03-12T10:00:00Z","readingTime":9,"slug":"context-window-scaling","subtitle":"Understanding the tradeoffs of expanding context","tags":["context-windows","scaling","rag","performance"],"title":"The Context Window Arms Race: Why Bigger Isn't Always Better","tldr":"Context windows have grown from 4K to 1M+ tokens in two years. But bigger context doesn't mean better performance — attention dilution, cost scaling, and latency tradeoffs mean the optimal context size depends on the task. RAG often outperforms brute-force large context.","topicCluster":{"color":"topic-llm","name":"LLM Architecture","slug":"llm-architecture"}},{"_id":"article-what-is-ai-agent","articleType":"primer","publishedAt":"2026-03-10T10:00:00Z","readingTime":8,"slug":"what-is-an-ai-agent","subtitle":"Moving beyond the hype to a precise, useful definition","tags":["agents","definitions","fundamentals"],"title":"What Is an AI Agent? A Rigorous Definition","tldr":"An AI agent is a system that uses an LLM to perceive, reason, plan, and act autonomously. Unlike chatbots, agents maintain goals across multiple steps, use tools, and adapt their approach based on feedback from the environment.","topicCluster":{"color":"topic-agents","name":"AI Agents","slug":"ai-agents"}},{"_id":"article-agentic-web-primer","articleType":"deep-dive","publishedAt":"2026-03-08T10:00:00Z","readingTime":11,"slug":"the-agentic-web","subtitle":"Building for the next consumer of information","tags":["agentic-web","mcp","llms-txt","protocols","web-standards"],"title":"The Agentic Web: Why the Internet Needs a Machine-Readable Layer","tldr":"The web was built for human browsers. AI agents are the next primary consumer of online information, but the current web is hostile to machine consumption. The agentic web is an emerging set of protocols (MCP, llms.txt, structured APIs) that make content natively accessible to AI systems.","topicCluster":{"color":"topic-agentic-web","name":"The Agentic Web","slug":"the-agentic-web"}},{"_id":"article-ai-personal-computing","articleType":"deep-dive","publishedAt":"2026-03-05T10:00:00Z","readingTime":10,"slug":"the-end-of-apps","subtitle":"From app-centric to agent-centric personal computing","tags":["personal-computing","ai-assistants","mobile","ux"],"title":"The End of Apps: How AI Assistants Will Replace Your Home Screen","tldr":"The app model is breaking down. Instead of switching between 30 apps to get things done, AI assistants will orchestrate tasks across services on your behalf. This isn't science fiction — it's the trajectory of every major platform in 2026.","topicCluster":{"color":"topic-daily-life","name":"AI in Daily Life","slug":"ai-in-daily-life"}}],"total":6}