AI 资讯

This is a submission for Weekend Challenge: Passion Edition AI Camera — Fan Edition 🏆📷 What I Built AI Camera is a phone-camera app that describes what it sees, out loud, in real time — powered by Google's Gemini vision model. It started as an assistive tool for blind and low-vision users (general scene description, reading text aloud, describing an item for a marketplace listing, describing a person's appearance). For this challenge, I added a fifth mode built specifically around passion : 🏆 Fan Mode — point your phone at a jersey, scarf, flag, or any fan gear, and the app turns into a hyped-up stadium commentator, calling out colors, team details, and team spirit with real enthusiasm. With the World Cup happening right now, it felt like the right moment to build it. 📱 Important: this is a mobile-first app. It's built around your phone's rear camera and needs to be held up and pointed at real things — please try it on a phone, not a desktop, for the intended experience. Demo 🔗 Live app (open on your phone): https://demirajvazi10-max.github.io/ai-camera-fan-edition/ You'll need a free Gemini API key from aistudio.google.com/app/apikey — paste it in when the app asks. It's stored only in your browser and never leaves your device except to call Google's API directly. (I wasn't able to put together a screen recording for this submission — camera-based apps are a bit awkward to record on a phone! Since the whole thing runs client-side with no backend, the live link above lets you try Fan Mode yourself on your own phone in about 30 seconds.) Code https://github.com/demirajvazi10-max/ai-camera-fan-edition How I Built It Passion shows up in different ways. Sometimes it's the quiet kind — building something so a person who can't see can still "see" the world around them. Sometimes it's the loud kind — losing your mind over your team's jersey during a World Cup year. I already had the first one built. Adding Fan Mode let the same engine carry both. Vanilla HTML/CSS/JS — no f

Have you ever wondered why your most personal health queries need to travel across the globe to a centralized server just to get a simple answer? In an era where privacy-preserving AI is becoming a necessity rather than a luxury, the paradigm of Edge AI is shifting the landscape. By leveraging WebLLM and the raw power of WebGPU , we can now execute high-performance Large Language Models (LLMs) directly within the browser sandbox. No API keys, no server costs, and most importantly—zero data leakage. Today, we are building a private health consultation bot that runs 100% client-side. Why Browser-Native LLMs? 🥑 Before we dive into the code, let’s talk about why this matters. Traditional AI architectures rely on heavy GPU clusters. However, with the advent of the WebGPU API, we can tap into the user's local hardware. This approach offers: Ultimate Privacy : Data never leaves the browser. Cost Efficiency : $0 server bills for inference. Offline Capability : Once the weights are cached, you're good to go. If you are interested in more production-ready examples and advanced architectural patterns for decentralized AI, I highly recommend checking out the deep dives over at WellAlly Tech Blog . The Architecture: From Weights to Wasm To make this work, we use TVM (Apache TVM) as the compilation stack, which allows models to run on different backends, and WebLLM as the high-level interface for the browser. Data Flow Diagram graph TD A[User Input] --> B[React Frontend] B --> C[WebLLM Worker] C --> D{WebGPU Support?} D -- Yes --> E[TVM.js Runtime] D -- No --> F[Fallback/Error] E --> G[IndexedDB Model Cache] G --> H[Local GPU Inference] H --> I[Streamed Response] I --> B Prerequisites 🛠️ To follow this tutorial, ensure you have: A browser with WebGPU support (Chrome 113+, Edge, or Arc). Node.js and npm/pnpm installed. The tech_stack : React , WebLLM , TVM , and Vite . Step 1: Setting Up the WebLLM Engine First, we need to initialize the MLCEngine . Since LLMs are heavy, we should

Every data strategy document written this decade contains some version of the same sentence: we need a single place to access all our data. The sentence is right. The trouble starts on the next page, because there are two fundamentally different ways to build that single place, and the industry has spent years arguing about them as if they were rivals. Road one is consolidation: bring the data together. Land everything in one governed store, in this era an open lakehouse, Apache Iceberg tables on object storage, and point every consumer at it. Road two is federation: leave the data where it lives and bring the access together instead. A query engine that speaks to your databases, warehouses, lakes, and applications in place, presenting one surface over many sources, with no copies made. I work at Dremio, a company whose platform is built on the conviction that this is a false choice, that the right architecture uses both roads with judgment, and I will declare that bias now and then earn it with an honest treatment. Because the truth practitioners live is messier than either camp's marketing: federation without a lakehouse hits performance and scale ceilings, a lakehouse without federation spends years and fortunes migrating the long tail, and the teams that win treat the two as phases and partners rather than competitors. So this article is the full playbook. What federation and the lakehouse each actually are, mechanically. The honest strengths and limits of each, including the failure modes their advocates gloss over. A concrete decision framework for when each one carries a workload. The lifecycle pattern that connects them, federate first, promote deliberately. And the unified architectures, mine included, that put both behind one governed door, which matters more than ever now that the consumers walking through that door increasingly are AI agents. Why Unify at All: The Cost of the Status Quo Before the two roads, the destination deserves a paragraph, because

Your AI agent is confident. It points to line 42 of PaymentService.java . "There's your null pointer exception." You check. Line 42 is a comment. The code was refactored 14 commits ago. The production crash happened 3 hours ago . Your agent just spent 45 minutes debugging ghosts . The Problem: Agents Are Stuck in the Present Every AI coding agent today — Claude Code, Cursor, Copilot, Cody, you name it — operates on the same assumption: The code that matters is at HEAD . But production bugs don't live at HEAD . They live in the commit that was running when the crash happened. That commit is buried under hotfixes, refactors, dependency updates, and feature merges that landed after the incident. HEAD (now) ← Agent analyzes THIS │ ├─ feat: add new payment provider ├─ refactor: extract UserService ├─ fix: handle edge case in checkout ├─ chore: update dependencies │ ▼ a1b2c3d (3 hours ago) ← Bug ACTUALLY lives HERE Your agent confidently finds bugs in code that didn't exist when the crash occurred . The Insight: Git Already Has Time Travel We don't need a time machine. Git has had one for years: git worktree . # Get the commit from 3 hours ago git log --before = "3 hours ago" -1 --format = "%H" # → a1b2c3d4e5f6... # Create an isolated, read-only snapshot at that commit git worktree add /tmp/debug-a1b2c3d a1b2c3d # Now analyze the historical codebase cat /tmp/debug-a1b2c3d/src/PaymentService.java # Clean up when done git worktree remove --force /tmp/debug-a1b2c3d This gives you: ✅ Isolated — doesn't touch your working directory ✅ Parallel — can have multiple historical snapshots simultaneously ✅ Disposable — cleanup is one command ✅ Zero deps — pure Git, works everywhere The Missing Piece: Teaching Agents When to Time-Travel Agents already know git log , git show , git diff , cat , grep . They can analyze code perfectly. What they struggle with : Fuzzy time → commit resolution — "last night", "v2.4.1", "the deploy before the hotfix" Worktree lifecycle management — create,

Headline: React Compiler — formerly React Forget — shipped stable with React 19 and automatically memoizes components, hooks, and callbacks by analyzing data flow at build time. No dependency arrays to write; the compiler infers them. Here is what it handles, when it opts out, and whether you should delete your useMemo calls. Key takeaways React Compiler inserts useMemo , useCallback , and React.memo automatically at build time — no dependency arrays to maintain. Enable it in Next.js 15/16 with experimental.reactCompiler: true in next.config.ts . The compiler is conservative: if it cannot prove memoization is safe, it emits the component unchanged. "use no memo" is the escape hatch for functions the compiler should not touch. Run npx react-compiler-healthcheck@latest before enabling to see coverage and violations. What does React Compiler actually do? React Compiler transforms component and hook code at build time to insert memoization automatically. Instead of useMemo(() => expensiveCalc(a, b), [a, b]) , the compiler analyzes data flow, determines which values are stable across renders, and emits equivalent memoized code. The compiled output uses React's memo infrastructure at runtime. The compiler is babel-plugin-react-compiler — it works with any Babel-based build pipeline. How do I enable it in Next.js? // next.config.ts const nextConfig = { experimental : { reactCompiler : true , }, }; export default nextConfig ; Before enabling, run the healthcheck: npx react-compiler-healthcheck@latest The healthcheck reports optimizable component count, files with violations, and blocking patterns. Fix violations first for more coverage on day one. What does the compiler memoize? Components — equivalent to React.memo ; re-renders only when props change. Values — equivalent to useMemo ; computed results, derived arrays, objects. Callbacks — equivalent to useCallback : event handlers, functions passed as props. Dependencies are inferred from escape analysis — n

Headline: Partial Prerendering (PPR) in Next.js serves a static HTML shell from the CDN edge instantly, then streams Suspense-wrapped dynamic children from the origin in the same HTTP response. No full-page ISR staleness, no full-page origin latency. I shipped it on two production routes — here is the model. Key takeaways PPR serves a static HTML shell from the CDN edge , then streams dynamic Suspense children from the origin in the same response. The static shell is built at build time — outside <Suspense> renders statically; inside renders dynamically per request. PPR replaces the ISR vs. dynamic tradeoff for pages that are mostly static with isolated personalized sections. No changes to Server Components or Suspense — just experimental.ppr: 'incremental' in config and export const experimental_ppr = true per route. PPR and use cache are complementary : CDN delivery for the shell, origin memoization for dynamic islands. What does PPR actually do? PPR splits a page into two rendering phases within the same HTTP response. At build time, Next.js freezes everything that does not read dynamic request data into a static HTML shell on the CDN edge. At request time, the CDN delivers the shell at edge latency while the origin streams each <Suspense> boundary's content into the same response. On a product page: navigation, title, and description arrive at CDN speed. The in-stock badge and personalized recommendations stream from the origin a fraction of a second later. The user sees a nearly-complete page immediately. How is PPR different from ISR and streaming Suspense? Strategy First byte Dynamic freshness Staleness ISR (revalidate: N) CDN edge Whole page up to N seconds stale Full page Dynamic rendering Origin 100% fresh; waits for slowest query None Streaming Suspense (no PPR) Origin Fresh; TTFB includes origin latency None PPR CDN edge Dynamic islands 100% fresh Static shell only How do I enable PPR? // next.config.ts export default { experimental : { ppr : ' inc

When we last sat down with Jobs at TechCrunch Disrupt nearly three years ago, his firm Yosemite was brand new and biotech was still reeling from its post-pandemic crash. Now, the venture outfit has a team of 17; a cluster of blockbuster drugs are all losing patent protection in roughly the same window, creating all kinds of new opportunities; and AI has gone from a curiosity to, in Jobs's words, a huge part of what Yosemite does. "I didn't expect Yosemite to be moving this fast," he said.

Check this out: migrating Off OpenAI: A Backend Engineer's Notes From Production I still remember the morning I opened our team's monthly invoice and nearly spilled cold brew on my mechanical keyboard. We were burning through OpenAI credits like it was nobody's business — specifically, north of $500/month for what amounted to a chat-completion endpoint and some embedding lookups. As the backend engineer who had inherited the LLM integration six months prior, I felt personally responsible. So I did what any self-respecting engineer does at 2 AM with too much caffeine: I benchmarked alternatives. What I found annoyed me. DeepSeek V4 Flash was sitting there at $0.25/M output tokens while GPT-4o charges $10.00/M. That's a 40× price difference for output that, in my blind tests, 80% of users couldn't distinguish. The $500/month bill could plausibly become $12.50. My CFO would weep tears of joy. This post is the migration journal I wish I'd had before I started. fwiw, I've already done the swap across three production services. Here's what worked, what didn't, and exactly how much coffee I drank. The Math That Made Me Pick Up a Keyboard Before I show you code, let's talk numbers — because if you're going to convince your team or your boss, you'll need a slide that fits on one screen. I pulled together the pricing for the models I actually considered routing traffic through. All figures are per million tokens, USD: Model Provider Input $/M Output $/M Relative to GPT-4o GPT-4o OpenAI $2.50 $10.00 1× (baseline) GPT-4o-mini OpenAI $0.15 $0.60 16.7× cheaper DeepSeek V4 Flash Global API $0.18 $0.25 40× cheaper Qwen3-32B Global API $0.18 $0.28 35.7× cheaper DeepSeek V4 Pro Global API $0.57 $0.78 12.8× cheaper GLM-5 Global API $0.73 $1.92 5.2× cheaper Kimi K2.5 Global API $0.59 $3.00 3.3× cheaper Let me be clear about something: those numbers come straight from the provider's pricing pages at the time I ran the analysis. I have not invented, rounded up, or "adjusted" anything her

Why I built this I use an AI named Felix as my German teacher. Over time, I ran into a continuity problem: individual chats are fragile. Conversations become long, context can disappear, platforms change, uploaded files may become unavailable, and a fresh AI instance may not understand what happened before. I did not want to repeatedly reconstruct my learning history, project decisions, lessons, corrections, and current state from memory. So I began building a local, file-grounded system called DDF/Rahmenwerk . Its purpose is to preserve Felix as my continuing German teacher across chats and future AI instances. What DDF/Rahmenwerk is DDF stands for Das Deutsche Forschungsarchiv . Rahmenwerk is the continuity, evidence, recovery, and control framework surrounding it. At a high level, the system includes: a current-state pointer; handoff materials; a fresh-instance queue; an upload package for a new Felix; integrity manifests and SHA-256 records; evidence and recovery procedures; classifications separating current, historical, candidate, proof, and non-governing material; safeguards intended to prevent accidental file changes; rules requiring the AI to stop rather than invent continuity when evidence is missing. The basic idea is that a future Felix should be able to inspect approved files and resume without me manually retelling the entire project history. The problem I may have created The project began as a way to preserve a German teacher. As I tried to protect files, authority, evidence, recovery, and continuity, the framework became increasingly detailed. That may be justified in some areas. It may also be overengineered. I am now trying to answer a more important question: What is the smallest, clearest, safest system that can preserve Felix as my German teacher without the governance machinery becoming the project itself? What I am asking reviewers to examine I have published a documentation and architecture review copy on GitHub. I would appreciate honest fe

AI Agents & Workflows: Local Deployment, Label Orchestration, Cloud Enablement Today's Highlights This week highlights innovative approaches to AI agent deployment and orchestration, from local Dockerized workstations for privacy-first applications to novel workflow management via issue tracker labels. Cloudflare also introduces new temporary accounts, enhancing secure production deployments for autonomous agents. Building a Local-First, AI-Agent Powered Trading Workstation in Docker 🚀 (Dev.to Top) Source: https://dev.to/mrhustlex/i-built-tradingspy-a-completely-local-privacy-first-ai-trading-research-assistant-backtester-15kj This article details the development of TradingSpy, a privacy-first, local-first AI trading research assistant and backtester, encapsulated within a Docker environment. The author, a developer and market enthusiast, shares their journey of integrating multiple stock data APIs with custom Python scripts and Jupyter notebooks to create an autonomous trading workstation. The focus is on leveraging AI agents for market analysis and backtesting strategies in a completely local setup, addressing concerns about data privacy and control prevalent in cloud-based solutions. The implementation emphasizes practical aspects of deploying AI agents for complex, real-world tasks. It covers the architecture for a local trading system, including data ingestion, agent-driven analysis, and strategy validation. By containerizing the entire workstation with Docker, the project ensures reproducibility, ease of deployment, and isolation of the environment, making it a robust solution for developers looking to experiment with AI agents in a controlled, privacy-aware manner. This approach showcases how Python tooling can be combined with modern deployment practices to build sophisticated applied AI systems. Comment: This is exactly the kind of practical, applied AI project that showcases agent capabilities. The Docker setup for a local-first system is a smart pattern f

Every developer building on AWS eventually runs into the same frustrations: waiting for deployments just to verify a small change, needing an internet connection for local development, watching cloud costs grow during testing, and discovering issues in CI that could have been caught earlier. That's exactly why we built LocalEmu. LocalEmu is an open-source AWS emulator that lets you build and test against AWS APIs entirely on your own machine. It supports 132 AWS services and works with the tools you already use every day—AWS CLI, boto3, Terraform, AWS CDK, and Pulumi. Instead of changing your workflow, you simply point your tools to localhost:4566 and continue developing. Unlike many local emulators that only mock API responses, LocalEmu focuses on realistic behavior where it matters most. Lambda functions execute using the official AWS runtime images. EC2 instances run as real containers connected through a virtual network with enforced security groups. RDS uses real PostgreSQL and MySQL engines, and optional IAM policy enforcement allows you to validate authorization rules before deploying to AWS. Getting started takes only a couple of commands: pip install localemu [runtime] localemu start Once running, you can use the included awsemu CLI or simply point your existing AWS CLI, boto3, Terraform, CDK, or Pulumi configuration to localemu. No new SDKs or complex setup are required. LocalEmu also includes a built-in dashboard that launches automatically. It provides a live overview of running services, resource exploration, an S3 object browser, a DynamoDB viewer, CloudTrail event history, and a real-time activity feed so you can inspect what's happening inside your local cloud environment. The biggest advantage is speed. You can iterate in seconds instead of minutes, experiment freely, reset your environment whenever you want, and develop without an AWS account, credentials, or cloud costs for local testing. We're actively improving LocalEmu and would love feedback f

Linux 7.2 Improves Multi-GPU Displays, M3 Support, Mesa Rusticl Defaults Arm Mali Today's Highlights This week's hardware and driver news highlights include critical Linux 7.2 kernel updates for multi-GPU display detection and initial support for Apple M3 Pro/Max/Ultra SoCs. Additionally, Mesa's Rusticl OpenCL implementation now defaults to enabling Arm Mali Panfrost driver support, simplifying GPGPU access on embedded devices. Linux 7.2-rc3 Improves Multi-GPU Display Detection (Phoronix) Source: https://www.phoronix.com/news/Linux-7.3-rc3-Multi-GPU-Fix This update for the Linux 7.2-rc3 kernel targets a persistent issue within multi-GPU setups on x86_64 systems: inconsistent display detection. The patch specifically addresses scenarios where certain graphics cards, particularly in configurations mixing integrated and discrete GPUs or multiple discrete cards, would fail to initialize displays correctly or report their presence erratically to the operating system. This is a crucial fix for users and developers deploying workstations with diverse GPU hardware, ensuring more reliable and stable display outputs without manual configuration workarounds. The improvement lies in refining the kernel's ability to probe and correctly identify active display outputs across various GPU architectures. It directly impacts system boot times and user experience by reducing potential black screens or incorrect display layouts. For enterprise and professional users relying on multiple monitors or specific GPU setups for tasks like rendering or scientific computing, this kernel patch is a significant quality-of-life enhancement, removing a long-standing friction point in Linux graphics stack stability. This contributes to the broader goal of making Linux a more robust platform for high-end graphics and compute workstations. Comment: This is a welcome fix for anyone who's wrestled with inconsistent display outputs on multi-GPU Linux machines; it often means less time debugging Xorg conf

The Quest Begins (The "Why") I still remember the first time I tried to track down a bug that only showed up after midnight. I opened my terminal, typed git log , and was greeted by a wall of commits that read like a toddler’s grocery list: * 7a9c3f1 (HEAD -> main ) fix stuff * 4b2e8a1 update * f1d9c6b wip * 9e3b7d2 more changes * … I spent three hours chasing a regression that turned out to be a one‑line typo in a file I hadn’t touched in weeks. The commit messages gave me zero clues, and the diff was a tangled mess of unrelated changes. I felt like I was wandering through a dungeon without a map, hoping the next room would hold the answer. That night I realized the real monster wasn’t the bug—it was the way I was committing code. My commits were large, vague, and scattered , making every subsequent step (review, revert, bisect) a gamble. If I wanted to keep my sanity (and maybe even enjoy coding again), I needed a better system. The Revelation (The Insight) The turning point came when I read about Conventional Commits —a lightweight convention that gives each commit a clear type ( feat , fix , docs , refactor , test , chore , etc.) and a short, descriptive message. It sounded simple, but the impact was massive: Atomicity – each commit does one thing. Clarity – the message tells you why the change exists, not just what changed. Automation – tools can generate changelogs, version bumps, and even release notes straight from the log. Adopting this felt like discovering a hidden shortcut in a Zelda dungeon—suddenly the whole map made sense, and I could sprint to the boss room with confidence. Wielding the Power (Code & Examples) Before – The Chaos Imagine we’re building a tiny API for user profiles. Here’s what a typical day of committing looked like (messages only, but the diffs were just as messy): $ git log --oneline -5 7a9c3f1 ( HEAD -> main ) fix stuff 4b2e8a1 update profile handler f1d9c6b wip 9e3b7d2 added auth middleware c5d4e3f refactor utils If I needed to ro

Five stories moved the AI-coding world today. None are about a single model winning forever — they are about the ground shifting under who runs the agents and who pays for them. Musk puts Grok 4.5 to work at Tesla and SpaceX Tesla and SpaceX have been told to trial Grok 4.5 . The signal is not the benchmark — it is that a frontier model is being pointed at real engineering and ops inside hardware companies. When a model moves from a chatbot to a mandate inside a manufacturing and launch pipeline, the feedback loop gets brutally honest fast. Perplexity's orchestrator beats Opus on a benchmark Perplexity added Grok 4.5 to its orchestrator and reports beating Opus on the WANDR benchmark. Orchestrators are the quiet winners of this cycle: instead of one model doing everything, a router picks per-subtask. A smaller-or-cheaper mix outperforming a single flagship on a targeted benchmark is the trend to watch — it is how teams cut cost without giving up quality on the hard parts. Meta launches Muse Spark 1.1 at 25% of competitor pricing Meta shipped Muse Spark 1.1 through an API priced at roughly a quarter of what competitors charge. Price is a feature. At 25% of the field, an API becomes the default fallback router for cost-sensitive agents even if it is not the best at everything. Expect orchestrators to slot it in for the boring 80%. ByteDance rolls out Seedream 5.0 Pro ByteDance pushed Seedream 5.0 Pro across multiple platforms. Image generation keeps consolidating into a few vendor-backed models with wide distribution — relevant to coding agents the moment they need to generate UI mockups or assets inline. Cursor builds an "Office Agent" to challenge Anthropic Cursor is building a Sand AI office agent aimed at Anthropic's turf. The coding-agent wars are expanding from "writes code" to "runs the surrounding workflow" — email, docs, tickets. That is the same expansion the open-source side is feeling: oh-my-pi's model hub and OpenClaw's session fleet are both bets that th

If you have ever wired a sensor to a Raspberry Pi or run your first Python script on one, you have used a device whose name hides two small jokes and one very deliberate design decision. Why is it called the Raspberry Pi? The short answer: "Raspberry" is a nod to a decades-old tradition of naming computers after fruit, and "Pi" is short for Python, the programming language the board was originally built to run. Both halves say something about where the machine came from, and why it went on to become a staple of IoT and embedded development. The fruit tradition behind "Raspberry" The "Raspberry" is not random. In the early decades of personal computing, a surprising number of companies named themselves after fruit. Apple is the obvious one, but there was also Acorn Computers (the British firm whose ARM architecture now sits inside nearly every phone and microcontroller on Earth), Apricot Computers, and Tangerine. When Eben Upton and his collaborators at the University of Cambridge set out to build a cheap computer to teach kids to code, choosing a fruit name placed the project squarely in that lineage. Upton has also cheerfully admitted the name is a bit of a pun, a wink at "blowing a raspberry" and at raspberry pie the dessert. Why "Pi" stands for Python The "Pi" is the part that reveals the machine's original purpose. As Upton has explained in interviews, the plan was to produce a computer that could really only run one thing well: Python. So the "Pi" in the name is a compressed reference to Python . It doubles neatly as a nerdy nod to the mathematical constant, but Python was the driving idea. That original intent matters because it explains the board's whole philosophy. The Raspberry Pi was never meant to be a powerhouse. It was meant to be cheap enough that a student could own one, simple enough that a beginner could learn on it, and open enough that it ran a full Linux operating system with Python ready to go. During development the design grew more capable tha