标签：#ai

Google must change AI Overviews after claiming users don't want "lots of sources."

If Alphabet's record-breaking $85 billion stock sale signals investor appetite for AI-related offerings, we can see that investors are ready to chow.

Gemma 4 12B uses a new encoding scheme and token prediction to punch above its weight.

Dreambeans is a curated list of AI-illustrated "stories" culled from the personal data in your Google account.

Most teams don’t have a documentation shortage. They have a context shortage. The average developer spends 20 minutes hunting for context before a one-line change. Their AI pair-programmer spends that same time hallucinating. I’ve been thinking a lot about what documentation actually needs to become in an AI-assisted world. The answer isn’t “more docs.” It’s not even “AI-generated docs.” It’s Atomic Context Documentation : smaller, sharper, verified context that stays near the code and helps both humans and AI work on the system safely. In my new article, I break down: Why traditional docs fail the “second reader” (AI) From context to results 👉 Full Article If you’ve ever watched AI confidently guess wrong about your codebase, this one’s for you.

Cursor's Developer Habits Report is one of the clearest signals yet that AI coding has crossed from individual productivity into software-delivery infrastructure. The headline numbers read as a story about speed: more code per week, larger PRs, deeper agent sessions, more changes committing without manual review. The deeper implication is governance -- whether teams can preserve architectural intent while generation, review, automation, and commit flows all accelerate at once. The velocity curve is now measured, not anecdotal. For two years the claim that AI coding is accelerating rested mostly on vibes and vendor decks. Cursor's data turns it into telemetry. And read as an operations document rather than a marketing one, that telemetry describes a structural shift: software delivery is getting harder to govern, not just faster to produce. This is not a critique of Cursor. The report is strong validation. Cursor proves the velocity curve with numbers most of the industry only gestured at. The point of this essay is what sits on the other side of that curve. What the Cursor Developer Habits Report Shows The inaugural Cursor Developer Habits Report (Spring 2026 edition), published by Cursor (Anysphere, Inc.), draws on Cursor usage data rather than survey responses. It captures the transformation across five themes -- developer acceleration, the economics of intelligence, the power user gap, the rise of context, and the shift to automation. The headline figures: 3.6K -> 8.6K lines added per developer per week -- the per-developer code volume rose from 3.6K (Jan 2025) to 8.6K (May 2026), with growth accelerating since the start of 2026. 125.86 -> 345.02 lines per PR at p75 -- lines added per pull request at the 75th percentile rose roughly 2.5x year over year (Jan 2025 to May 2026). Developers are taking on larger units of work in a single PR. 8% -> 13.8% mega PRs -- the share of PRs with at least 1,000 changed lines grew from 8% (Jan 2025) to 13.8% (May 2026). ~30% mor

Microsoft's Agentic Transformation Patterns Playbook is a useful signal because it does not treat AI agents as another productivity tool. It frames agentic AI as an enterprise operating-model shift: agents are moving from assisting humans to executing work across processes, systems, and teams. The implication for software teams is sharper than it looks -- coding agents are on the same trajectory, and architectural governance becomes part of the infrastructure stack the moment agents start executing. Microsoft's playbook describes six transformation patterns and emphasizes that each pattern requires different ownership, governance, and operating discipline. That is the move worth paying attention to. It reframes agentic AI from a model question into an enterprise operating-model question. That shift matters for software teams because coding agents are following the same path. They are moving from autocomplete to execution. Once agents edit files, open PRs, modify infrastructure, or coordinate multi-step changes, architectural governance becomes infrastructure. What is Microsoft's Agentic Transformation Playbook? Microsoft's playbook is a practical guide for choosing, scaling, and operating AI agents across the enterprise. Public summaries describe it as a 52-slide guide covering six transformation patterns, from employee productivity to core business processes and customer-facing agents. The throughline is that agents are not a single category -- they are a family of patterns with different ownership models, different risk surfaces, and different requirements for governance. That framing matters because it cuts against the dominant adoption narrative. Most enterprises are still treating AI as a per-team productivity story: this team gets Copilot, that team gets an internal assistant, another team is piloting an agent for support tickets. Microsoft is arguing that the pattern of deployment determines the operating discipline required, and that ad-hoc deployment does n

Google's Managed Agents announcement is one of the clearest signals yet that the AI industry is moving beyond stateless tool calling toward persistent execution environments and long-running agent systems. That shift expands what models can do. It also expands the governance surface -- from prompt and PR review into the runtime itself. We spent two years building brains in jars For most of the current AI cycle, the system around the model has been thin. Models could reason, propose commands, and orchestrate small tool calls. But they ran in short sessions, against narrow APIs, under human supervision, with ephemeral state. The model was a brain; the body was a few HTTP requests and a JSON tool schema. That assumption is ending. The frontier is not just better reasoning. It is a body for the brain. The brain finally has a body. Now it needs governance. The runtime layer for AI agents is arriving Google Managed Agents (and the parallel motion across the ecosystem -- OpenAI's containerized execution work, Claude Code's persistent sessions, MCP-based tool ecosystems, hosted agent harnesses) formalizes the runtime as a product: Sandboxed execution Persistent state across sessions Orchestration loops Infrastructure-native agents Agent-as-a-service lifecycle Long-running sessions Mid-session tool injection Managed runtime lifecycle This resembles the transition from scripts -> applications -> cloud platforms. Agents are no longer just calling tools. They are beginning to inhabit programmable environments . Why persistent agent systems change governance Once agents can continuously modify filesystems, maintain state across sessions, autonomously remediate, inject tools dynamically, operate against production systems, and coordinate across workflows, governance failures stop being one-off review misses. They compound over time . What that compounding looks like: Architectural drift -- small deviations accumulate across long-running sessions Policy propagation failures -- con

The Faros AI Engineering Report 2026 is not a survey of developer sentiment. It is two years of telemetry from 22,000 developers across 4,000 teams, measuring what AI adoption actually produces downstream. The findings have a name: the Acceleration Whiplash. The structural explanation has one too. What the telemetry actually shows The output numbers in the Faros report are real and worth stating plainly. Epics completed per developer are up 66.2%. Task throughput per developer is up 33.7%. PR merge rate per developer is up 16.2%. These represent genuine delivery acceleration, and dismissing them would be dishonest. AI coding tools are producing real productivity gains at the business level. The production quality numbers are also real: Metric Change Incidents per PR under high AI adoption +242.7% Median time in code review +441.5% Code churn (lines deleted to lines added) +861% PRs merged with no review at all 31.3% Source: Faros AI Engineering Report 2026: The Acceleration Whiplash . Telemetry from 22,000 developers across 4,000+ teams. Figures represent metric change from lowest to highest AI adoption periods within each organization. Both sets of numbers are true simultaneously. That is the whiplash. Throughput accelerated. The downstream systems built to validate that throughput did not. Plotted together, generation throughput rises steeply while control capacity stays nearly flat -- and the gap between the two curves is the governance debt. Why the systems did not scale Code review, incident response, and architectural validation were all designed for a world where development velocity was human-paced. A senior engineer could review the meaningful PRs in a sprint. An incident postmortem could trace a failure to a specific change and a specific decision gap. Architectural drift was visible because it moved slowly enough to catch. AI-generated code broke these assumptions quietly. Not because the code was obviously bad, but because it was often superficially conv

I built Xaloia AI , a privacy-first AI platform focused on trust and human interaction. And now, I’m shutting it down. Not because the idea was empty. Not because the tech didn’t work. But because I tried to build it from Romania. The Problem Wasn’t the Product Xaloia was built around things that are becoming increasingly important: privacy secure communication human-centered AI But building something meaningful isn’t enough. It needs the right environment to grow. And that’s where things started to break. What I Ran Into Trying to build in Romania, I kept hitting the same walls: Lack of early adopters willing to pay - People are curious about tech, but not ready to invest in new products. Limited startup ecosystem - Fewer accelerators, fewer investors, fewer people who understand what you’re building. Cultural friction around ambition - If your idea isn’t small or conventional, it’s often questioned instead of supported. Low exposure to global markets - Even if you build something good, getting it in front of the right audience is much harder. None of these stop your project instantly. But together, they slowly drain momentum. Why the US Is Different From everything I’ve seen and experienced, the US offers something fundamentally different: Access to capital — people invest earlier Distribution opportunities — platforms, networks, visibility Cultural support for big ideas — ambition is expected, not questioned Faster feedback loops — you know quickly if something works It’s not that success is guaranteed there. It’s that the conditions for success actually exist. The Real Lesson Talent is everywhere. Ideas are everywhere. But opportunity is not evenly distributed. And trying to ignore that reality cost me time, energy, and a product I genuinely believed in. What’s Next Shutting down Xaloia isn’t the end. It’s a reset—with better clarity. Next time, I won’t just focus on building something good. I’ll focus on building it where it actually has a chance to grow.

Critics say Trump plan to test AI models is short-sighted, performative.

Spencer Huang, Nvidia’s robotics lead, tells WIRED that the new bot combines the best of both worlds.

This week we've got tandem hands-ons with Google's new Gemini AI agent - Spark - from my colleagues David Pierce and Jay Peters. Their takeaways are similar: It's so effective that it's scary. Spark knew that David's dog is named Frida and knew the first name of Jay's wife, even though neither of them explicitly […]

Hackers appeared to take over victims’ accounts even after Meta said it fixed its AI-powered support chatbot, which granted hackers access to victims’ accounts.

Amazon's updated search bar will now show you AI-generated images of products as you describe them. For now, the in-app feature only surfaces AI images of clothing and home goods, allowing you to tap on the image that best matches what you're looking for and search for similar-looking items. In a blog post, Amazon positions […]

Amazon will use visual search and AI to show AI generated product images that match your search queries. The retailer says it will help guide users to products.

1. Introduction to Docker One of the biggest historical challenges in software engineering has been environment inconsistency , the frustrating situation where an application works perfectly on one machine but unexpectedly fails elsewhere. And this is precisely the problem Docker was designed to solve. Docker is a containerization platform that packages applications and their dependencies into isolated environments called containers . Its goal is simple: Run applications consistently everywhere. Instead of configuring every machine manually, Docker packages everything an application needs to run. 1.1 What is Docker? Docker is a platform used to build, package, and run applications inside containers. A container includes: Application code Dependencies Runtime Libraries Configuration Simple mental model: Code + Dependencies + Runtime = Container This ensures applications behave the same way across development, testing, and production environments. 1.2 VMs vs Containers VMs (Virtual Machines) package: Application Dependencies Full Operating System Containers package only: Application Dependencies Runtime Containers share the host operating system kernel, making them much lighter and faster. Feature Virtual Machine Docker Container Includes OS Yes No Startup Speed Slow Fast Resource Usage Heavy Lightweight Size Large Small Simple analogy: Virtual Machine = Full House Container = Apartment in a Building 1.3 Docker Ecosystem Overview Docker includes multiple tools: Docker Engine The core service that runs containers. Docker Desktop A local GUI and development environment. Docker Hub A cloud registry for storing and sharing Docker images. Docker Compose A tool for running multiple containers together. Example: docker compose up Can start an entire application stack: Backend API Database Redis Frontend with a single command. 2. Docker Architecture & Fundamentals To use Docker effectively, it is important to understand how its core components work together. Docker follows a

Syndicated from the FavCRM blog . The old quote was two weeks. With an agent on the UI and a headless backend, it's an afternoon. A client needs a booking site. The old quote was two weeks: a calendar, a database, an availability engine, payments, a customer table. With an AI agent building the frontend and FavCRM as the headless backend , the real work is an afternoon. Here is the whole job, start to finish. The scenario A small clinic. Three services, one practitioner, online booking with deposit. You are the agency; you have an AI agent in your editor and a terminal. The plan: Register the clinic's FavCRM workspace Configure services and availability Wire one server route that talks to FavCRM Let the agent build the booking UI against that route Test a real booking end to end Step 1 — Register the workspace (~5 min) The favcrm CLI registers a workspace and issues an API key. No dashboard. favcrm signup request --email clinic@example.com \ --organisation-name "Bright Smile Clinic" favcrm signup verify --request-id < id > --code <6-digit-code> The verify step prints a fav_mcp_* key. Put it where your build can read it — never in the repo: export FAVCRM_API_KEY = fav_mcp_... Step 2 — Configure services and availability (~30 min) Hand the brief to your agent and let it call the tools. Inspect a schema first: favcrm tool describe create_service Then create each service: favcrm tool call create_service '{ "name": "New Patient Exam", "durationMinutes": 45, "price": "80.00" }' favcrm tool call create_service '{ "name": "Cleaning", "durationMinutes": 30, "price": "60.00" }' Set when the practitioner works, so availability is real: favcrm tool call set_staff_availability '{ "weekday": "mon", "start": "09:00", "end": "17:00" }' Repeat per weekday. At this point the backend is done — services, hours, an availability engine that knows about clashes. You wrote no schema. Step 3 — One server route (~30 min) The browser must never hold the API key. Put it in one server route tha

Syndicated from the FavCRM blog . The number that predicts whether an agent is safe to let loose isn't the tool count. When people compare agentic CRMs, they count tools. The number that actually predicts whether an agent is safe to let loose is a different one: annotation coverage . An MCP tool annotation tells the agent what a tool does to the world — whether it reads or mutates, whether it's safe to retry, whether it reaches an external service. Without annotations, the agent is guessing. This is what they are, and why a catalog's annotation coverage matters more than its tool count. What an MCP annotation is Every MCP tool can carry hints alongside its input and output schemas: readOnlyHint — the tool only reads; it changes nothing. Safe to call freely. destructiveHint — the tool mutates or deletes. The agent should confirm before calling. idempotentHint — calling it twice with the same input has the same effect as once. Safe to retry on a timeout. openWorldHint — the tool reaches an external service (sends an email, charges a card), so its effects leave the system. These are not documentation for humans. They are machine-readable signals the agent reasons over before it acts. Why they prevent the worst failures The dangerous class of agent failure is not "the agent couldn't do something." It's "the agent did the wrong destructive thing because it misread an ambiguous instruction." Delete the customer instead of the tag. Refund the wrong invoice. Cancel every booking instead of one. Annotations let the agent self-gate. A well-annotated catalog means the agent calls list_members without ceremony but pauses to confirm before cancel_booking , because one is marked read-only and the other destructive. Pre-MCP function-calling had no equivalent — every tool looked the same to the model, so safety lived entirely in the prompt. Why coverage matters more than count A 190+ tool catalog with 100% annotation coverage is safer than a 30-tool catalog with none. A tool that l

The hidden cost of AI isn't generating code. It's understanding your codebase. For a long time, I assumed AI coding tools became expensive because they generated a lot of code. These tools can produce components, tests, SQL queries, documentation, and sometimes entire features on demand. If costs were climbing, the output volume must be the reason. The more I used these tools, the more I realized I was measuring the wrong thing. The expensive part isn't writing code. The expensive part is understanding what code should be written — and that work is mostly invisible. That realization changed how I think about AI-assisted development entirely. Two Prompts, Two Very Different Problems Consider these two requests: "Create a utility function that formats dates" and "Review this feature and suggest improvements." At first glance, both look ordinary. Both might even produce short answers. But they require completely different levels of understanding. The first is narrow and well-defined. The AI needs very little information before it can produce a useful answer. The second is open-ended. Before suggesting a single improvement, the AI may need to read multiple files, understand dependencies, follow existing patterns, compare implementations, and build a mental model of why the feature exists at all. The output might still be small. The work required to reach it is not. Why Agent Workflows Feel Different From Autocomplete This became much clearer when I started using AI agents. Traditional autocomplete is predictive — you type, the AI guesses what comes next. It's fast, cheap, and deliberately context-light. Agents behave differently. When you ask one to improve a feature or review a workflow, it doesn't immediately start generating code. It starts reading. It follows imports, finds related files, and tries to understand the system before touching it. That is exactly what makes agent workflows feel slower and more resource-intensive than autocomplete: they are spending effor