Radar
Articles about Radar
Zero to Agent in 30 Minutes: Build a Personal Assistant on OpenClaw
In the final episode of Zero to Agent in 30 Minutes, AI engineer Sajal Sharma showed how to build a personal assistant on OpenClaw that tracks your tasks and notes and handles scheduled work on its own.
Designing Websites for People and AI Agents with WebMCP
The following article originally appeared on the Agentic AI Foundation blog and is being reposted here with the author’s permission. Websites are designed for people. We can look at a page and quickly understand where to enter information or which control will complete an action. AI agents don’t see or use the web the same
This Week in AI: More Capability, More Responsibility
AI systems are gaining more autonomy while governments, companies, and researchers are still working out how much oversight they need. On the latest episode of This Week in AI, we covered the US debate over AI governance, new frontier models, persistent agents, world models, and practical uses for AI in healthcare and disaster response. AI
Intent, Not Identity
On a recent episode of This Week in AI, we discussed that the number of nonhumans on the internet is greater than humans, 144 to 1. It’s an estimate, and the order of magnitude is more important than the number itself. What matters is what a ratio anywhere in that range does to a security architecture. For more than two decades, systems were engineered around two foundational assumptions: either verifying a human user exercising discretionary judgment or validating the account executing hardcoded predictable logic.
Radar Trends to Watch: October 2026
In addition to the nearly constant stream of model releases, in September we’ve seen price drops, new kinds of models, proofs of long-standing problems in mathematics, and continued investigations into models escaping their sandboxes. (Axios reports investigations into over 10,000 incidents.) AI has infinite patience and is fundamentally probabilistic. Given a difficult or impossible task
Zero to Agent in 30 Minutes: Build Your First Agent with MCP
Developers already have useful capabilities exposed through REST APIs. The Model Context Protocol (MCP) lets developers make those capabilities available to AI clients without rebuilding the underlying application.
How to Build Reliable AI Agent Systems for Production
The following article was originally published on the Agentic AI Foundation blog site and is being republished here with the author’s permission. A customer asks your company’s AI agent to update the shipping address on account 123. The agent relies on a support ticket with a typo and updates account 132 instead. The customer relationship
This Week in AI: Agents Are Outrunning the Systems Around Them
On the latest episode of This Week in AI, host Vicki Reyzelman, a senior solutions engineer at Akamai, traced a common problem across cybersecurity, energy, model releases, consumer hardware, and regulation. AI agents can now probe networks, coordinate with other agents, make purchases, and interact with real-world systems faster than many organizations can respond. We’re
Coding Agents Love Decision Records
The following article originally appeared on Duncan Davidson’s blog and is being republished here with the author’s permission. Decision records give coding agents durable project context—as long as they don’t turn every decision into a courtroom transcript. Architectural Decision Records (ADRs) help human teams establish rules and carry context forward in software projects. They capture
The Future of Software May Be Conversational Rather Than Autonomous
The following article originally appeared on Robert Englander’s blog site and is being reposted here with the author’s permission. The software industry has become deeply focused on autonomous AI systems. Agents that can replace workers. Agents that can write software. Agents that can operate applications on our behalf. Entire startups are now built around the
The Agentic Data Science Playbook
The following article originally appeared on Vanishing Gradients and is being republished here with the authors’ permission When an AI agent can explore a dataset, choose a modeling approach, run the analysis, and explain its findings, what should the data scientist do? Traditionally, data scientists chose each step and implemented much of the analysis themselves.
Evaluating AI-Generated Frontend Code: What Should We Actually Test?
AI can now generate a surprising amount of frontend code from a short description. A developer can ask for a form, a table, a modal, a settings page, or a dashboard view and get something that looks usable almost immediately. It may compile, render, and even arrive with a few tests. That is useful, but
Superpowers for Humans
I’ve known Jesse Vincent for more than 20 years, since the days when I was still editing and publishing Perl books and organizing the Perl Conference and he was the chief maintainer of Perl 5 and the project manager for Perl 6. We’d lost touch, but he rocketed back into my consciousness last October when
Not About Navier-Stokes
This post isn’t about OpenAI’s use of AI to solve the Navier-Stokes problem, one of the Millennium Prize problems, at least not directly. I’m not a mathematician; I have a vague understanding of the problem and certainly no understanding of the proof. But the discussion surrounding the solution crystallized some of my own thoughts about
A Data Center Is a Dependency Graph Before It Is a Building
The buildings and physical infrastructure for a new hyperscale data-center region are complete. Power is live and redundant, the cooling loops are balanced, the network fabric is up, and tens of thousands of machines are racked, cabled, and reporting healthy. Every milestone on the construction schedule is closed. The region will not carry production traffic
Zero to Agent in 30 Minutes: Give Your Agent Its Own Computer
In the most recent episode of Zero to Agent in 30 Minutes, AI engineer Sajal Sharma showed how to use a remote sandbox to let your agents install software, run commands, and control a browser without endangering your everyday machine. In effect, you’re giving your agents a computer of their own. Sajal demonstrated both approaches
From Raw Data to Graph-Native AI
I’ve been thinking about a gap in the way we discuss graphs in AI. Most of the conversation starts after the graph already exists. We talk about graph neural networks, GraphRAG, graph agents, and graph foundation models. We spend much less time on the step that determines what all of them can do: turning raw
Human Judgment Doesn’t Leave the Software Factory, It Relocates
The following article originally appeared on Elevate and is being reposted here with the author’s permission. A software factory is a repeatable loop around software work. If you’re building a software factory, code good enough to ship still needs human taste and ownership. We’ll discuss this including whether you need a factory just yet. If
This Week in AI: AI’s Safety Problem
AI systems are gaining access to more tools and data, raising new questions about oversight and accountability. This Week in AI host Christina Stathopoulos spent this episode examining how those questions are playing out in model safety, government oversight, and even digital marketing. Safety needs more than safer models Anthropic’s latest threat report documented misuse
When Software Subscriptions Become Public Policy
My conversation with Dan Gookin, the original For Dummies author and now mayor of Coeur d’Alene, Idaho, started as a publishing reunion. It ended with a much larger question: What happens when the software you rent becomes infrastructure you can’t leave? There was something wonderfully circular about hearing Dan Gookin tell me that, after he
Will TypeSafe’s Jev Change How We Build AI Applications?
The following article originally appeared on Arize’s blog and is being reposted here with the author’s permission. This week the AI community was in uproar about Jev from TypeSafe, not just a new model but a new kind of model: one that classifies, scores, and routes but can’t write a sentence. The reason for the
MCP Is Not Just Another API Standard
Ask most engineers what MCP is and you’ll get the same answer: a way to plug tools into an LLM. Fair enough, as far as it goes. But that description treats MCP like plumbing, and after months building MCP-based integrations for large enterprise platforms, I don’t think plumbing is the right metaphor. Plumbing moves water
The Accelerationist Case for Frontier Pacing
The following article originally appeared on Venkatesh Rao’s Substack, Contraptions, and is being republished here with the author’s permission. The sole athletic achievement of my life came in 1993: winning the IIT Bombay freshman 50m freestyle race with a time of 41s. That got me into the college swim team (it was a bad recruitment
AI Sovereignty: Bargaining with Big Tech and the Promise of Full Stack Open Source AI
The early rapid expansion of AI capabilities that focused on frontier models was largely ushered into the world by a few powerful, US-based AI labs. Open-weight models released from labs in China, early on from DeepSeek, and later from Moonshot, Z.ai, and others, have in part disrupted that dominance. But growing concerns about the concentration
Zero to Agent in 30 Minutes: Build a Sports Concierge Agent with Chester Ismay
Chester Ismay, a data science educator and AI consultant, created schedule viewers to keep up with the sports he follows, including the WNBA, NFL, NBA, and Premier League. But he still had to decide which games deserved his attention each week. In this episode of Zero to Agent in 30 Minutes, Chester built a sports
The Post-training Process OpenAI Used for ChatGPT
This is the third post in a four-part series about post-training. If you missed them, read part 1 and part 2. The final post, on implementing your own pipeline, will be coming October 7. Now that you understand the gist of reinforcement learning and supervised fine-tuning, it’s time to explore what post-training has actually accomplished
How to Get from AI-Assisted to AI Native
When considering the history of AI, Richard Sutton observed that brute force and compute scale has always trumped human expertise, and when you look for it, you can see this “bitter lesson” play out throughout tech history. In his keynote at Ai4 2026, Tim O’Reilly explains why grappling with the bitter lesson is the forge
Software Factories, Light and Dark
The following article originally appeared on Addy Osmani’s blog and is being republished here with the author’s permission. A software factory harnesses loops at scale. You can run the loop with humans in it (light factory), trading judgment and concentration against speed and breakage. Or you can ignore the humans (dark factory) and let those
This Week in AI: Capability, Capital, and Consequences
OpenAI expanded into software control, scientific reasoning, and financial services this week, and investors committed billions more to AI companies across the stack, while AI researchers went public with warnings. This Week in AI host Christina Stathopoulos looked at what those developments mean for an industry already wrestling with questions about safety and control. Models
Navigating the Modern Data Lexicon: A Working Vocabulary for the Semantic Era
The way we talk about data is changing faster than the way we build it. Every quarter a vendor ships a new approach, coins a new term for it, or quietly adopts a term someone else has been using and redefines it to fit the shape of their product. None of this is malicious. Every
Architecting for the Knowledge You Can’t Capture
Every knowledge program seems to begin with the same request. A senior engineer is leaving in six weeks, and someone asks her to document the process she’s carried for years. She returns a clean flowchart of the happy path. The drawing is accurate and may even be elegant. It leaves out the thresholds she watches,
What AI Can Teach Us About Being Human
My guest on this past week’s Live with Tim O’Reilly was Emmanuel Ameisen, a researcher on Anthropic’s AI interpretability team. I’d heard him give a short talk at Foo Camp on Anthropic’s research into what is going on inside an LLM while it is processing, and I wanted him to reprise the talk and then
Beyond Navier-Stokes: Who Controls Scientific Discovery?
Is the current furore in mathematics the canary in the coalmine for experimental science and knowledge work? This post was originally published in Vanishing Gradients on September 11, 2026. It’s been updated to address the subsequent declaration by 25 Fields Medalists and the debate about AI, mathematical progress, and research incentives. Science without understanding? “For
Zero to Agent in 30 Minutes: Build a Shared Knowledge Base for All Your Agents with Sajal Sharma
Every AI agent you run keeps what it learns to itself. Work through a problem with Claude Code in the morning, then ask Codex about it that afternoon, and the second agent has no idea the first one exists. Add a home-server agent like OpenClaw or Hermes into the mix, and you end up reexplaining
Enterprise Analytics Beyond Dashboards: Intelligent Data Orchestration with LLMs
In 17 years of building enterprise data platforms, I’ve watched every organization eventually ask the same question: “Can I ask one question and get one answer across everything my company knows?” A finance analyst wants actual revenue from the warehouse, pipeline data from the CRM, commentary from planning documents, and market signals from external providers.