Cameron

🫆 Hoodmaps.com now also has crime data! Very important in European capitals nowadays to tell you which neighborhoods to avoid The terrorist attack of yesterday in Modena, Italy was just on the edge of a set of three very unsafe neighborhoods Now available for most cities!

In the future, you’ll be able to accomplish a goal by just giving Claude an outcome and a budget. That’s the direction Anthropic is building in with its new Managed Agents features, announced at this week’s Code with Claude developer event. The basic idea: Claude, wrapped in a computer in the cloud, that you can spin up, scale, and manage as needed. Anthropic is taking on the infrastructure that kills most agent products, and making sure that it scales to meet the needs of agents running 24/7. On this week’s AI & I from @every, I talk with Angela Jiang (@angjiang), head of product for the Claude platform, and Katelyn Lesse (@katelyn_lesse), head of engineering for the Claude platform, about what Anthropic is building and what it takes to make agents reliable in production. We get into: - Why the "build a generic harness, hot-swap any model behind it" playbook is already outdated. Angela points to eval data on Memory where the same task across different harnesses performed drastically differently. - The infrastructure wall every team hits in production—and why Katelyn thinks “my sandbox died and took the agent with it” is the real reason internal agents don't ship. - Why Anthropic is so bullish on using file systems and skills within Claude, including Angela's argument that those early design choices can compound for years. This is a must-watch for anyone trying to take an agent past the demo and into production. Watch below! Timestamps: How the Claude platform evolved from API to agents: 00:01:48 The primitives that make up Claude Managed Agents: 00:04:09 Why the harness and the model are becoming a single unit: 00:10:37 The infrastructure wall that kills most agent projects in production: 00:18:49 Why team agents need a different shape than individual productivity tools: 00:24:49 How Anthropic's legal team uses an agent to review marketing copy: 00:26:36 Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms: 00:34:24 How to measure agent success with outcome and budget as the end state: 00:35:50 What the platform looks like a year from now, when Claude writes its own harness: 00:39:11

@herrmanndigital Meta support was transparent enough to give me this explanation

🦣 Logan Cooley scores again as the Utah Mammoth earn their first playoff win in franchise history in Vegas. Cooley is the youngest US-born player to score in both of his first 2 playoff games. #TusksUp

OpenAI Acquires TBPN x.com/i/broadcasts/1…

🚨 How Google Click Signals Drive SEO Rankings and AI Answers - A must read piece by @CyrusShepard going through how Google is trying to answer three broad questions from user click data: * Is this result relevant? * Is the content useful to answer the question? * Does this completely satisfy the user search? ... and what can we do about these! Check it out: signal.zyppy.com/p/google-click…

@levelsio Why not use a site like Booking com?