标签：#ai

Over the past few months, I’ve increasingly noticed something through my network: more people from non-technical backgrounds are building software as AI tooling improves. Designers are prototyping product ideas. Product managers are testing workflows. Founders are building MVPs. Operators are creating internal tools. People who would not have called themselves “technical” a year ago are now using AI to make ideas tangible. I think this is genuinely exciting. It has never been easier to create. I even attended a hackathon where participants only had 20 minutes to build a demoable product! This raises the question: When AI makes building easier, how do we make sure understanding does not disappear? I recently published Thinking in the Age of AI , a guide for software engineers (you can check out my previous post here ). That guide focused on individual reflection for engineers: how to keep developing technical intuition, reasoning, and judgment while using AI tools. But the landscape has changed quickly. AI-assisted building is no longer only an engineering workflow. It is becoming a builder workflow accessible to all. And by builders, I mean anyone using AI to turn ideas into software-like artifacts: vibe coders designers product managers founders operators marketers students non-engineering team members So I wanted to create a new version of the system for this wider builder audience. Thinking in the Age of AI: Builder Edition The opportunity is real I do not think we should dismiss this shift. I have spoken with people from all kinds of backgrounds who are actively building now. People who previously had to wait for engineering time can now create something concrete. That changes the conversation. Instead of describing an abstract idea, you can show a flow. Instead of writing a long product spec, you can prototype the interaction. Instead of asking “would this work?”, you can test a rough version. That is powerful. But there is a trap. A prototype can look much mor

I recently launched SpotClause, a small AI contract review and reader tool. The idea came from a simple problem: contracts are often difficult to read, especially for freelancers, consultants, and small teams who receive agreements but do not work with contract language every day. SpotClause helps users: summarize contracts in plain language identify key clauses understand payment terms, renewal terms, cancellation language, obligations, and deadlines compare two contract versions and see added, removed, changed, and unchanged wording I also added a Contract Clause Library with plain-language explanations of common clauses like cancellation clauses, renewal clauses, payment terms, confidentiality clauses, and notice periods. You can try the AI Contract Review Tool here: AI Contract Review Tool You can explore the Contract Clause Library here: Contract Clause Library SpotClause is not a law firm and does not provide legal advice. The goal is to help people understand contract language more clearly. I would appreciate feedback on: whether the homepage explains the product clearly whether the AI contract review page feels understandable what clause explanations would be useful to add next

OpenAI breaks ground on a 1GW data center project in Michigan as part of Stargate, building AI infrastructure to expand access, create jobs, and support communities.

Shopify Staff Engineer Guilherme Carreiro discusses building and scaling highly customizable platforms. Using Shopify’s Liquid theme system as a case study, he explains how to balance extreme design flexibility with low-latency performance under massive traffic. He shares insights on implementing secure domain-specific languages, native code extensions, and resilient developer tooling. By Guilherme Carreiro

I tried to explain OpenAI’s solution more clearly than OpenAI did.

Dozens of people have complained to the Federal Trade Commission about Norse Atlantic Airways’ tech-first customer service operation. Some said they lost thousands of dollars.

Michael Stiefel spoke to Sonya Natanzon, about the intersection of technical and social aspects of software architecture. Understanding the business and how a company operates is more important than the specific technologies used. Effective requirements analysis requires focusing on problems to be solved that describe good and bad outcomes, rather than statements of need or solution statements. By Sonya Natanzon

If you run a website that serves European users — or if you’re based in the EU yourself — hosting location is no longer just a technical detail. It has become a strategic and legal consideration. In 2026, questions around data residency, GDPR compliance, and digital sovereignty are front and center for businesses of all sizes. Choosing where your website and its data live can affect everything from legal risk to user trust and even search engine performance. The core issue: Where does your data actually live? When you choose a hosting provider or CMS, your content, user data, images, and analytics often get stored on servers in a specific country or region. This matters because different jurisdictions have different laws regarding data access, privacy, and government requests. Key concerns include: GDPR compliance : The EU’s strict data protection regulation requires that personal data of EU citizens be handled with strong safeguards. Transferring data outside the EU/EEA can trigger additional legal requirements (such as Standard Contractual Clauses). Schrems II and data transfers : Following court rulings, simply relying on old mechanisms for transferring data to the US became more complicated. Many organizations now prefer to keep data within the EU to reduce legal complexity. Data sovereignty : Some companies and public sector organizations want (or are required) to ensure their data is stored and processed under EU jurisdiction. Performance and latency : Hosting closer to your users generally means faster load times — which also helps SEO and user experience. For many European businesses, especially those handling any form of personal data (even something as simple as contact forms or newsletter signups), EU-based hosting has become the safer, simpler default. Why traditional hosting often falls short Many popular CMS platforms and hosting providers are headquartered outside Europe. While they may offer data centers in the EU, the company’s legal jurisdiction, d

Mañana cambia el billing de Copilot: las premium requests dan paso a AI Credits calculados por tokens. Esto es lo que debe revisar un equipo técnico. El 1 de junio de 2026 GitHub Copilot empieza a migrar desde el modelo de premium requests hacia billing por uso con GitHub AI Credits. La unidad deja de ser una petición premium más o menos abstracta y pasa a reflejar consumo de tokens: entrada, salida y tokens cacheados, con precios vinculados al modelo usado. Decisión rápida Qué cambia mañana La idea de GitHub es alinear precio con coste real. Una pregunta rápida a un modelo ligero y una sesión larga de agente sobre varios archivos ya no son equivalentes. Para equipos técnicos, eso obliga a tratar Copilot como infraestructura de IA, no como una extensión de editor de coste fijo. Este artículo complementa la guía previa de AI Credits, pero se centra en el cambio operativo inmediato: qué mirar antes de que el modelo entre en vigor mañana. Briefing Qué es un AI Credit GitHub define AI Credits como una unidad de billing donde 1 AI Credit equivale a 0,01 USD. Cada interacción que usa modelos consume tokens. Esos tokens se valoran según el modelo y se convierten a créditos. En planes individuales, Copilot Pro, Pro+ y Max incluyen asignaciones mensuales de AI Credits. En organizaciones y empresas, cada licencia aporta créditos que se agrupan en un pool compartido a nivel de billing entity. La diferencia clave con el sistema anterior es que el consumo puede variar mucho dentro de una misma función. Dos sesiones de chat no cuestan igual si una es una pregunta corta y otra arrastra contexto de repositorio, varias iteraciones y generación de código extensa. Lectura práctica Qué consume créditos y qué no GitHub documenta que consumen AI Credits funciones como Copilot Chat, Copilot CLI, Copilot cloud agent, Copilot Spaces, Spark y agentes de terceros. Las code completions y Next Edit suggestions no se facturan en AI Credits y siguen incluidas en planes de pago. Esta distinción es

Most multi-agent frameworks for software development organize agents around roles : a product manager agent, a developer agent, a tester agent. ChatDev and MetaGPT pioneered this approach, and it works well for monolithic tasks. But I ran into a wall when I tried to apply it to a real system with multiple independently-deployed services. The Problem with Role-Based Coordination Imagine you have a backend search service and a frontend management console. The backend team implements a new API endpoint. The frontend needs to adapt. In a role-based framework, there's no natural mechanism for this. Both agents are "developers" in the same simulated organization. There's no concept of service boundaries, no versioned contracts, no way to say "the backend changed, and the frontend needs to know exactly what changed." The coordination problem in multi-service development isn't "which role should handle this task" — it's "which service needs to know about this change, and what exactly changed." That reframing led me to build something different. AgentNexus: Coordinating Agents at the Service Granularity AgentNexus is a document exchange center that treats each service as a first-class citizen. Instead of roles, it uses service boundaries as the coordination primitive. Here's how it works: Each service registers as a sub-project with its own document namespace Services publish versioned Markdown documents: requirements, design specs, API docs, config Services subscribe to documents from other services they depend on When a subscribed document changes, the subscriber receives a diff-aware notification containing both the structured diff and the full latest content The whole thing is exposed as an MCP (Model Context Protocol) server running in streamable-HTTP mode, so multiple agents can connect simultaneously from different machines. The Diff-Aware Update Protocol This is the part I'm most proud of. When an agent calls get_my_updates_with_context , it gets back: { "update_id"

Hey everyone 👋 I'm exploring ideas for an AI-powered developer tool, but before building anything, I want to understand the real problems developers face every day. There are already plenty of tools that generate code. What I'm interested in is everything around coding: Debugging Code reviews Technical debt Documentation Dependency upgrades Testing Deployment Architecture decisions Learning large codebases I'd love to hear from you: A few questions: What's the most frustrating part of your workflow? What task takes more time than it should? What's something you wish AI could do for you today? Have current AI tools (ChatGPT, Claude, Cursor, Copilot, Gemini, etc.) failed you in any important way? If you could eliminate one developer headache forever, what would it be? I've also created a short 2-minute survey: 🔗 https://docs.google.com/forms/d/e/1FAIpQLSf1M5d2y-0RXEIhrbDBtS5gC900YuzWl43cJCxGUrU38MyeDQ/viewform?usp=publish-editor I'll happily share the survey results and key findings with the community once I collect enough responses. Thanks in advance for any feedback!

NVIDIA announced the new Isaac Gr00t reference design humanoid robot platform that combines humanoid robot, five-fingered hands and NVIDIA Jetson Thor compute.

The use of AI Agents creates a distinctive smell... One can tell the GH Repo owner was high on...

How to make LLMs deterministic, in plain English. The version I share with founders and product teams before they make decisions worth real money. You use AI tools every day. But can you explain what happens when you hit send? Most people cannot. And that gap is costing them. Bad prompts. Broken products. Decisions made on the wrong assumptions. The Hard Truth Every LLM explainer out there is written for researchers or so basic it tells you nothing useful. Neither helps you build better products or work with AI more effectively. This is the version I share with senior leaders, founders, and product teams before they make decisions worth real money. 1. It Is Not a Search Engine. It Is Not a Database. It Is a Prediction Machine. When you type a prompt and hit send, the LLM is not finding an answer from somewhere. It is predicting the most likely words to follow your input. Based on patterns it learned from billions of documents. That is the whole process. Wrong: "The AI knows the answer." Right: "The AI predicts the most likely answer based on what it has seen." This changes everything about how you use it. When an AI gives you a wrong answer confidently, it is not broken. It is doing exactly what it was built to do. Predict. Not verify. 2. The Autocomplete Comparison (And Why It Only Gets You Halfway) You have probably heard the phrase "autocomplete on steroids." It is not wrong. But it misses something important. Your phone autocomplete learned from your messages. An LLM learned from most of the written internet. Books. Research papers. Code. Billions of examples. At that scale, the patterns start to look a lot like real thinking. Not because the model understands in the way you do. Because it has seen so much that it can predict what a good answer looks like. When I was building AstroNayak I fed Vedic astrology principles into the system prompt. The LLM produced interpretations that genuinely surprised me. It did not know Vedic astrology. It had seen enough of it t

The row looked perfect. rating: 7 . Valid JSON, right type, no nulls, no missing keys. My schema check waved it through. The page had returned HTTP 200. The selectors hadn't moved. Everything green. A rating of 7 on a 5-star site is impossible. The model invented it, formatted it correctly, and handed it to me with total confidence. That's the failure I want to talk about. Not the scraper that breaks loudly. The one that hands you a clean-looking row that is quietly, plausibly false — and sails past every check you have, because your checks are all looking at the shape of the data, and the lie is in the value . TL;DR HTTP 200, intact selectors, and valid JSON tell you the form is fine. They say nothing about whether the value is true. When an LLM extracts from messy free-text, structured-output mode guarantees you get valid JSON. It does not guarantee the content is real. The model fills uncertain fields rather than leaving them empty — because the schema demands a complete row. A ~60-line value-level sanity gate (ranges, dates, cross-field, reference, language) catches the obvious lies before they hit your database. Real code and real output below. The honest catch: this gate catches rule violations , not plausible lies inside the allowed range . A rating: 4 where the truth is 2 slides right through. I'll be specific about where the gate stops. Two different ways a scraper lies to you I wrote about source drift last week — the case where the page changes underneath you and a 30-line schema check catches the structure shifting. That's an input problem. The source mutated; your agreement with the page broke; you detect it by watching the shape. This is the other end of the pipe. The source is fine. The page is intact, the selectors are correct, the structure is exactly what you expected. The thing that lied to you is the model , on the extraction step, when you asked it to pull structured fields out of a paragraph of human prose. Those two failures feel similar and t

Based on real system architecture decisions. About a $660K AI platform, three AI agents that kept the dashboard green, and a P0 incident that cost $3.15M over one weekend. Act 1 · The All-Hands Meeting Wang Lei, VP of Product, stood in front of the big screen, a smile on his face. Behind him, a dashboard rolled data from the "Axon AI Client Engineering Platform — Q1 Performance Report." Numbers cascaded across the wall: Metric Axon Platform Human Team (Last Q1) Improvement Avg daily tickets processed 847 312 +171% Avg first response time 12s 4h 17m ↓ 99.92% Customer satisfaction 4.8/5 4.1/5 +17% Monthly operating cost $52K $133K −61% Twelve department heads sat in the room. Dead silence. Wang Lei planted both hands on the table and scanned the room. His eyes landed on me. "Alex. Your team processed 312 tickets last Q1. Axon processed more than that in a single day last month." He smiled. Not a friendly smile. A sentencing smile. "And Axon costs less than a third of your team's operating expense." "We invested $660K in the whole platform. At current operating costs, it pays for itself in eighteen months." "After management review — the Client Engineering technical liaison function is being fully transitioned to the Axon platform." He clicked to the next slide. "Employees in replaced roles will complete exit interviews within the week." Someone inhaled sharply. I didn't. I opened my notebook to page 37. "Wang, what dimensions are these numbers from?" "What do you mean, 'what dimensions'?" His smile tightened. "Of those 847 daily tickets — how many are auto-tagging and routing, and how many are actual technical resolutions?" The room went quiet for about five seconds. Wang Lei looked at me. "Axon's ticket closure rate is ninety-three percent." "What's the reopen rate?" He paused. "What?" "After Axon replies — how many customers reopen the same ticket within twenty-four hours?" "We're still collecting that —" "Let me save you the trouble." I turned my notebook toward th

Last year I needed to ask for a raise. I knew my number, I'd read the guides, I had bullet points in my notes app. Then my manager said "let's chat about your goals for next quarter" and I said "sounds great, looking forward to it" and hung up. Never brought up money. Same thing kept happening elsewhere. Coworker taking credit for my work, I said nothing. Relationship that should've ended months earlier, I kept postponing. I always knew what to say. I just couldn't say it with someone actually looking at me. So I started building a thing to practice on. That thing became cosskill . What it actually is You pick a persona, tell it the situation in a sentence, and start talking. The persona doesn't help you. It holds position and pushes back. You practice not folding. Think of it as a flight simulator for hard conversations. You rehearse until your opener comes out steady, then go do the real thing. 20 personas across five categories: Operators (Musk, Jobs): first-principles thinking, harsh product feedback Strategists (Trump, Buffett): treat everything as a deal or a bet Relationship (Ex, Coworker): breakups, workplace friction, family money Philosophy (Socrates, Aurelius, Confucius, Sun Tzu, four more): each tradition frames problems differently Psychology (Rogers, Rosenberg, Ellis, Frankl, Kahneman, Jung): therapeutic frameworks on real situations These aren't celebrity impressions. The Buffett persona won't hype your startup idea. It'll ask "what's the downside?" and keep asking until you have something concrete. Tech stack Next.js 16 on Cloudflare Workers. DeepSeek for inference. Cloudflare D1 (SQLite at edge) for the bits that need to persist. No user accounts, chat history lives in localStorage. Monthly cost stays low enough that the free tier (10 messages/day) doesn't worry me. Why I made these choices DeepSeek instead of GPT-4/Claude. Each conversation is 10-30 messages. At GPT-4 pricing a free product bleeds money. DeepSeek gives maybe 90% of the quality for

There is a specific failure mode in AI-assisted QA work that most tooling discussions skip entirely, and it shows up earliest when you are working solo on a real engagement. Every new chat session is stateless. You paste the ticket, describe the feature, explain your severity logic, set up the context, and by the time the AI is actually useful, you have rebuilt your methodology from scratch for the third time that week. That is not a workflow problem you fix with better prompts. It is an architecture problem, and the fix is a skill file. QAJourney has a full breakdown of this system at qajourney.net/ai-qa-workflow-for-real-projects, including the actual skill files as free downloads. The short version: a skill file is a context document you load as a system prompt. It carries your test surface tiers, your three-path testing framework, your bug report format, your severity and priority logic, your Playwright conventions, and an explicit definition of what the AI does and does not get to call. Load it once per session. The AI operates inside your methodology from the first message instead of a blank slate. The local LLM layer solves a different problem. On a freelance or retainer engagement, tickets contain real product logic and real client data. Sending that to a cloud API on every session is a data exposure question whether or not it rises to a compliance issue. Running Ollama locally with the same skill file as system context keeps the engagement data on the machine. For the output quality required on QA tasks, current 7B to 14B models are sufficient. The cost at zero marginal per token makes it infrastructure rather than a service you pay by the session. The three-role setup in the workflow: engineer as judgment layer, cloud AI loaded with the skill file for complex reasoning and active session output, local LLM for lightweight tasks and client data work. The skill file is the constant across all three. The part that took time to internalize: AI dev teams already

RecursiveMAS (arXiv 2604.25917) showed that agents sharing internal reasoning state outperform agents that share only final outputs. The average accuracy gain across benchmarks was 8.3 points. The mechanism: each agent passes not just its answer but the latent embeddings from its own reasoning process, and the next agent conditions on both. The paper is a good result. The catch is access. RecursiveMAS requires open-weight models with hidden states exposed at inference time. That rules out Claude, GPT-4o, and Gemini. I built a Claude-native version using the Anthropic extended thinking API. The core idea transfers: instead of passing latent vectors, pass the full thinking text. The paper calls it internal state sharing; the Claude version calls it thinking-block relay. The architecture problem Claude's extended thinking blocks carry an encrypted signature tied to the originating conversation. You cannot pass a signed thinking block into a different agent's messages array. The API rejects it. The workaround: extract the text from the thinking block and inject it as a regular user message. # Extract thinking text from Agent 1 thinking_text = next ( ( b . thinking for b in response . content if b . type == " thinking " ), "" ) # Inject into Agent 2 as regular context, not as a thinking block context = f " Prior agent reasoning: \n { thinking_text } " The signature does not transfer. The reasoning does. relay-structured: what I built first The first architecture was a Planner > Critic > Solver loop where each agent emits a compact mental model JSON instead of raw thinking text. Raw thinking at a 1024-token budget is often compressed and fragmented. The hypothesis was that 150 tokens of structured signal carries more information per token than 1024 tokens of compressed prose. The schema each agent emits: { "interpretation" : "how the agent read the problem" , "key_steps" : [ "step 1" , "step 2" ], "rejected_approaches" : [ "approach tried and discarded" ], "confidence" :

I run Sola, a travel app for people who move differently from the traveller the industry was built for. While building it, I kept hitting the same wall. The data I wanted to query did not exist. Not because nobody collected it, but because the schema underneath the whole industry never had a field for it. So on 27 May 2026 I sat down and audited Booking.com. The homepage form, the currency selector, a Bangkok search results page. I wrote down what it accepts and what it refuses. Then I looked at the new AI travel agents shipping on top of it. Here is what I found, and why it matters to anyone building in this space right now. The form is the spec Booking.com's homepage search bar accepts exactly four inputs: A destination, as a single text field A check-in date and check-out date, as one range An occupancy counter, defaulting to "2 adults · 0 children · 1 room" A search button That is the spec. An online travel agency (OTA) is a CRUD app over this spec, and Expedia, Agoda, and Hotels.com run the same four fields. Airbnb lets you skip the dates. The destination stays a single field everywhere. Think about what a spec encodes. The default occupancy is a couple. Not a solo traveller, not a parent with one child, not three generations, not seven people eating from one host's kitchen. The form cannot accept a circuit ("Bangkok, then Hanoi, then Jakarta" forces three separate searches). It cannot accept an open date ("October, not sure which week"). It has no field for the part of a trip where you sleep at family but spend money in restaurants. When you fill that form, you have not searched. You have submitted to a schema. Most of the world's travellers fail the schema before they fail the search. The data receipts I am a builder, so I went for counts, not adjectives. Everything below rendered on the platform on 27 May 2026. Currencies: 52 offered, about 180 in circulation. Eight currencies sit featured at the top of the dropdown. On the day I ran it the order was EUR, US