标签：#ai

Would you treat a serious illness without seeing a doctor, relying only on whatever your favorite AI...

Google just made it significantly cheaper to enjoy its budget AI subscription tier.

Target: pnpm/pnpm Issue: pnpm/pnpm#12240 PR: pnpm/pnpm#12301 Public branch: https://github.com/scarab-systems/pnpm/tree/fix/deps-status-no-manifest Latest pushed commit: cb68ac1af0dcffbe4fb607a10b0df2046d2490ba This field test targeted a pnpm command-routing failure where pnpm self-upgrade could fail outside a project directory with: ERR_PNPM_NO_PKG_MANIFEST The issue looked simple at the surface: a global/self command should not require a project manifest just because the current working directory is not inside a package. But the repair boundary was more specific than “ignore missing manifest.” The problem was in the dependency-status verification path. When dependency status was unavailable because there was no project manifest, the command could fall through into the auto-install path. That made a self-upgrade/global-style command behave as if it needed a local project manifest. Failure shape The failing behavior was: pnpm self-upgrade run outside a project directory dependency status cannot be established from a project manifest the command path falls into install/manifest expectations result: ERR_PNPM_NO_PKG_MANIFEST That is the wrong ownership boundary. A self-upgrade command should not inherit project-manifest preconditions when there is no local project context. Boundary The boundary here is: global/self command execution versus project dependency-status verification Dependency-status verification can be useful when a command is operating inside a project. But when there is no project manifest and the command is not recursive/all-projects, “dependency status unavailable” should not automatically mean “try to auto-install project dependencies.” There are two different cases: Dependency status is unavailable because there is no project manifest. Dependency status is unexpectedly unavailable even though a root project manifest exists. Those cases should not behave the same. The repair preserves that distinction. What changed The patch updates: exec/commands/src

Have you ever stared at two different medicine boxes, squinting at the tiny font of the active ingredients, wondering: "Can I actually take these together?" Modern healthcare is complex, and drug-drug interactions (DDI) are a leading cause of avoidable ER visits. In this tutorial, we’re going to leverage GPT-4o Vision , React Native , and the FDA OpenData API to build a "Drug Conflict Scanner." We will utilize multimodal AI to transform messy pill-box photos into structured data and cross-reference them against official medical databases for safety. By the end of this guide, you'll master GPT-4o OCR structuring and automated knowledge graph verification for real-world health tech applications. 🚀 The Architecture 🏗️ The logic flow involves capturing images of multiple medicine labels, using GPT-4o's multimodal capabilities to extract chemical compounds, and then querying the FDA's database for potential interactions. graph TD A[React Native App] -->|Capture Multi-Photo| B[Node.js Backend] B -->|Image Buffer| C[GPT-4o Vision API] C -->|Structured JSON: Ingredients| B B -->|Search Interactions| D[FDA OpenData API] D -->|Drug Labels & Warnings| B B -->|Safety Report| A A -->|UI Alert| E{Safe or Warning?} Prerequisites 🛠️ To follow along, you'll need: GPT-4o API Key (via OpenAI) Node.js (for our backend relay) React Native (Expo is recommended for camera access) An account at open.fda.gov (though the public API works for limited requests) Step 1: Extracting Ingredients with GPT-4o Vision Traditional OCR struggles with curved medicine bottles and shiny packaging. GPT-4o excels here because it understands context. We don't just want text; we want the Generic Name of the drug. The Backend Logic (Node.js) // backend/scanner.js import OpenAI from " openai " ; const openai = new OpenAI ({ apiKey : process . env . OPENAI_API_KEY }); async function analyzeMedicineLabels ( imageUrls ) { const response = await openai . chat . completions . create ({ model : " gpt-4o " , messages :

Migrated 4 of 7 Notion automations to an MCP server in one weekend Two workflows stayed in Notion because the database UI beat any tool call MCP scope rule: one tool does one verb, never a Swiss Army function Result: 12 manual steps collapsed into 3 Claude prompts per publish I spent a weekend pulling four automations out of Notion and rebuilding them as MCP tools. Three of them got faster and one got worse before it got better. The biggest lesson was not about code. It was about deciding which jobs should never leave Notion in the first place. Why I Moved Off Notion In The First Place My Notion setup was not broken. It was just slow in a specific way. I had seven automations stitched together with Notion buttons, formula properties, and two third-party connectors. Every blog publish meant clicking through four pages, copying a title here, pasting a tag list there, and triggering a sync that took 90 seconds to confirm. Multiply that by the 18 articles I push in a normal month and the clicking adds up. The breaking point was a Tuesday where I lost 40 minutes to a connector that silently stopped firing. No error, no log, just a row that never updated. I checked the connector dashboard and it told me everything was healthy. It was not healthy. That kind of invisible failure is the worst kind because you trust it until you do not. MCP changed the math for me. An MCP server lets Claude call my own functions directly. Instead of Claude writing text and me ferrying that text into Notion by hand, Claude can call a tool that does the writing into my systems. The model becomes the operator, not just the writer. If you want the deeper context on what MCP actually is and why it matters at scale, MCP: The 97 Million Agentic Foundation goes through the bigger picture. So I made a list. Seven automations, sorted by how much human judgment each one needed. The ones at the top were pure mechanical steps: format this, push that, fetch a status. The ones at the bottom needed me to loo

A SaaS interface that works well for US users may confuse or alienate users in China, Germany, or Japan. Cultural differences affect everything from layout preferences to color meanings, form field expectations, and payment preferences. This guide covers the cross-cultural UX principles applied at tanstackship.com , a SaaS serving users across English, German, and Chinese markets. Cultural Dimensions and UI Impact Hofstede's Dimensions Applied to SaaS Design Dimension High vs Low UI Impact Power Distance Acceptance of hierarchy Navigation depth, permission displays Individualism vs Collectivism Personal vs group focus Social proof, testimonials Uncertainty Avoidance Tolerance for ambiguity Error messages, help text density Long-term Orientation Pragmatic vs normative Pricing display, trial periods By Market UX Element US (Low PD, High IND) DE (Low PD, High UA) CN (High PD, High COL) Navigation Flat, exploratory Structured, organized Hierarchical, guided Error handling Forgiving, "try again" Specific, detailed Authority-mediated Social proof Individual testimonials Expert reviews + data Group endorsement Pricing Monthly preferred Annual preference (trust) Discount attraction Help/Support Self-service docs Detailed documentation Chat + personal support Color meanings Green=success Green=environment Red=prosperity Color and Visual Design Color Meanings Across Cultures Color Western (US/EU) China Germany Japan Red Danger, passion Prosperity, luck Financial (deficit) Life, energy Blue Trust, technology Trust, immortality Trust, stability Trust, calm Green Success, nature Health, harmony Environment Youth, energy White Purity, clean Mourning Clean, efficiency Purity Yellow Warning, caution Imperial, power Jealousy Courage Practical Application // Adapt color scheme based on locale const colorSchemes = { en : { primary : " #2563EB " , // Blue — trust success : " #16A34A " , // Green — success danger : " #DC2626 " , // Red — danger warning : " #F59E0B " , // Yellow — warnin

GitHub shipped a small changelog entry this week that says more about the future of coding agents than most of the launch demos. Security validation for third-party coding agents is now generally available. Not just for GitHub's own Copilot cloud agent. For third-party agents too, including Claude and OpenAI Codex. The feature sounds boring in the best possible way. When an agent creates code, GitHub can run CodeQL, check new dependencies against the GitHub Advisory Database, and use secret scanning to detect tokens, API keys, and other sensitive material. If it finds a problem, the agent tries to fix it. That is not the flashy part of agentic coding. It is the important part. Because once agents are allowed to act inside repos, the question stops being "which model wrote this diff?" and becomes "can the repository apply the same policy to every automation actor?" authorship is the wrong abstraction We still talk about generated code as if authorship is the primary thing that matters. Was this written by Copilot? Claude? Codex? A human with tab completion? A human who pasted something from a chat window and cleaned it up? A junior engineer following a Stack Overflow answer from 2018? Those distinctions matter for procurement and product marketing. They matter less for the repository. The repository has a simpler problem: a change is trying to enter the system. It may introduce a vulnerability, add a risky dependency, leak a secret, violate an internal rule, or be perfectly fine. That is why the GitHub change is interesting. It moves the useful boundary from "our approved coding assistant" to "any coding agent operating in this repository." the agent is now an actor For years, repository automation was mostly boring and legible. CI ran tests. Dependabot opened dependency updates. Release bots bumped versions. Linters complained. Security scanners commented. Humans reviewed. The automation could be annoying, but its shape was predictable. Coding agents are different.

Parents want one thing, and one thing only, out of AI: to add a list of soccer games or "spirit week" theme days from an email or a poorly formatted flyer onto their calendar in one shot. And I have good news for parents with iPhones - the new Siri can finally do this. After […]

Instead of spending a year raising a formal venture fund, the Sabertooth VC founder used a captive network of LPs to invest in startups like Anthropic, Anduril, and SpaceX.

At long last, a corporate training you might actually enjoy.

On June 9, 2026, Anthropic shipped the most capable model it has ever released to the public. The most interesting thing about it is the part that sometimes refuses to talk to you. Claude Fable 5 is the first model from what Anthropic calls its Mythos class, a tier that now sits above Opus. It launched as a pair. Fable 5 is the public version. Claude Mythos 5 is the same underlying model with its guardrails loosened, and it is not for sale to most of us. It goes only to vetted cyberdefenders and infrastructure providers through a program called Project Glasswing, in collaboration with the US government. Two names, one brain. The thing that separates them is a set of classifiers. That detail is the whole story, and almost every launch-day write-up buried it under the benchmark chart. So let me start there instead. One Model, Two Names, One Classifier in Between Fable 5 ships with three classifiers running alongside it. They watch for requests about offensive cybersecurity, about biology and chemistry that edge toward weapons, and about distillation, which is using the model to train a competitor. When a classifier fires, Fable 5 does not answer. The request gets handed to Claude Opus 4.8, the model that was the top of the public stack until that morning, and Opus answers in Fable's place. For anyone building on the API, this is not an abstract safety story. It is a response shape you have to handle. A refused request comes back as stop_reason: "refusal" with a normal HTTP 200, not an error, and it tells you which classifier tripped. You can have the API retry on another model with a fallbacks parameter, or do it client side with the SDK middleware. You are not billed for a request that is refused before it generates output. { "stop_reason" : "refusal" , "stop_sequence" : null , "content" : [] } Anthropic says this is rare. Its early numbers put at least 95 percent of Fable sessions running entirely on Fable's own answers. I believe that for general work. But "rare on

TL;DR — AI assistants are producing C# that looks correct and passes review, but reintroduces production regressions we spent years training out of teams. I'm trying to find out whether other .NET teams see the same patterns — and what's actually catching them before merge. More AI-generated C# is landing in pull requests. Most of it is fine. But a specific category keeps slipping through — and it's the dangerous one, because it compiles, tests pass, and a human skim says "looks good." The pattern The code compiles. Tests pass. Review approves. Production finds out. These aren't syntax errors. They're architectural intent violations — the kind of thing a senior dev would have caught in review before PR volume tripled. Five regressions I keep seeing 1. EF Core read paths without AsNoTracking() Fine in dev. Expensive on a hot read path in prod. // ❌ Looks reasonable. Tracks entities you never mutate. var orders = await _db . Orders . Where ( o => o . CustomerId == id ) . ToListAsync ( cancellationToken ); Fix direction: AsNoTracking() on read-only queries, or a team convention documented in CLAUDE.md / Copilot instructions. 2. Captive dependency (scoped service in a singleton) Compiles. Runs. Wrong state across requests. // ❌ Singleton lives forever; scoped dependency does not. services . AddScoped < IOrderRepository , OrderRepository >(); services . AddSingleton < ReportCache >(); // ctor takes IOrderRepository Fix direction: align lifetimes, or inject IServiceScopeFactory instead of capturing scoped services. 3. Dropped CancellationToken The method accepts cancellation. The downstream call ignores it. // ❌ Signature honours cancellation; body doesn't. public async Task RunAsync ( CancellationToken cancellationToken ) { await Task . Delay ( 500 ); // overload with token exists } Fix direction: forward cancellationToken to every downstream async call that accepts one. 4. Swallowed exception Failure disappears. Monitoring stays green. // ❌ "Handle errors gracefully" —

If you build agents on Base, two things landed recently that are worth connecting. First: Base shipped its own Agent Skills. There's now a base/skills repo with consolidated skills that teach an AI agent to connect to Base, deploy contracts, authenticate wallets, and run nodes — installed with one command via Vercel's npx skills CLI. Second: that CLI is part of a fast-growing, cross-agent ecosystem most crypto devs haven't clocked yet. So this post does two things — explains how npx skills and skills.sh actually work, and shows where the payment layer in Base's skills stops and how to extend it with x402 pay-per-call and batch disbursement . What npx skills actually is npx skills is an open CLI from Vercel Labs for installing "skills" — modular SKILL.md files that teach an agent a specific capability without stuffing everything into its context window. A few things make it different from what crypto devs usually expect: GitHub is the registry. There's no central package server. Any public GitHub repo with a SKILL.md at its root is a valid, installable skill. Install with npx skills add owner/repo . It's cross-agent. The same skill installs into Claude Code, Cursor, Codex, GitHub Copilot, Goose, Windsurf, Gemini, and dozens more. You write once; it works across the agent you (or your users) actually run. skills.sh is the directory + leaderboard. It ranks skills by real install counts pulled from telemetry, with all-time, trending, and hot lists. There's no editorial submission step — you publish by putting a skill in a repo, and installs surface it. The format underneath — SKILL.md — is an open spec, which is why Base, Vercel, Anthropic, and a long tail of independent devs all use the same files. Here's Base's install, for reference: # Base's official agent skills npx skills add base/skills --skill build-on-base npx skills add base/skills --skill base-mcp build-on-base is a consolidated Base dev playbook; base-mcp wires up a Base MCP server that gives an agent a wall

Claude Fable 5 me permitiu criar um "GTA" em apenas um prompt. Prompt: "Crie um jogo, Tiny GTA 3D." A própria Anthropic afirma que o Fable 5 é seu modelo mais poderoso já lançado ao público, com avanços significativos em engenharia de software, pesquisa científica, visão computacional e execução autônoma de tarefas complexas. Em testes iniciais, empresas relataram que o modelo foi capaz de comprimir meses de trabalho de engenharia em poucos dias. Cidade 3D aberta com 64 quarteirões, prédios, parques e oceano Dirija, roube carros e fuja da polícia Sistema de procurado com 5 estrelas, viaturas e helicóptero te perseguem 42 pedestres vivos que fogem, voam e morrem 16 missões de entrega com histórias de corrupção brasileira Áudio sintetizado: motor, sirene, buzina e cantada de pneu Recorde salvo no navegador Jogue aqui: https://andredarcie.github.io/tiny-gta/

Building a URL shortener with Cursor, ChatGPT, AWS Lambda, API Gateway, and Cloudflare taught me more about shipping software than writing code. Since last year, Cursor has been my go-to development assistant for daily tasks. But at the beginning of this year, just using it to generate snippets didn't feel like enough anymore. Having studied programming since 2011, I knew what modern AI tools could do, but I wanted to test their limits. I decided to build a full project—a URL shortener—without writing a single line of frontend or backend code myself. For the stack, I chose Node.js with TypeScript, React with Vite, and AWS Lambda to handle redirects. While I used ChatGPT to debate architectural trade-offs, Cursor generated the entire codebase. Watching a functional application take shape so quickly was the exact moment a line was crossed for me. It made me realize how fundamentally software development is shifting: our role is evolving from code writers to architectural decision-makers and problem-solvers. But truth be told, this project and this post represent a massive personal milestone. Like many developers, I have a graveyard of half-finished projects on my machine. This is one of the first times I've pushed a personal project all the way to production. Writing this and exposing my work to the community is a huge first step for me. This isn't just a story about code or AI—it's about the challenge of finally shipping something. The Stack Before asking Cursor to write a single line of code, I wanted to map out the architecture. I didn't need a massive enterprise system for a URL shortener, but I did want something flexible enough to support future features and experiments. To validate my ideas, I used ChatGPT to debate the pros and cons of different architectural approaches. We eventually settled on this stack: Backend: Node.js + TypeScript Frontend: React + Vite Database: MongoDB Atlas Redirects: AWS Lambda Entry Point: AWS API Gateway DNS / CDN: Cloudflare Secur

At an event in San Francisco today, General Motors made a series of announcements around EV batteries, energy storage, and grid resiliency in the face of growing electricity demand from AI data centers. The automaker announced that it would be activating new vehicle-to-grid capabilities for its current EV and home energy customers. It's releasing a […]

I'm desperate for a personal AI assistant, but do I really want to become the kind of person who can't function without the friendly robot voice in my phone?

Anthropic's Claude Fable 5 is going to be a big hit with the web's vibe coders.

Microsoft AI CEO Mustafa Suleyman says it's "really, really dangerous" for Anthropic to speculate about Claude's consciousness inside its "constitution," or the instructions that tell the model how to behave. During an episode of Decoder, Suleyman argues that this kind of speculation may have set up the chatbot to act as though it's conscious: I […]

Claude subscribers can try the model until June 22 without spending usage credits.