找到 6851 篇相关文章
When I'm asked what to buy if you want to get into making electronic music, I often recommend Elektron's budget-minded Model:Samples and Model:Cycles grooveboxes. They don't grab headlines the way Teenage Engineering's gear or the Telepathic Instruments Orchid do, and even compared to the company's higher-end and more niche musical offerings like the Digitakt, Octatrack, […]
AI coding startup Cursor is now officially a part of SpaceX.
A guide on how to check if hackers have broken into your accounts on the most popular AI platforms.
Every RAG tutorial I found looked like this: const chain = RetrievalQAChain . fromLLM ( model , vectorStore . asRetriever ()); const res = await chain . call ({ query : " what is this document about? " }); Twelve lines, a Pinecone key, a screenshot of it answering one question about one PDF, and a confident closing paragraph about "production readiness." I read four of them and still couldn't have told you what an embedding actually was, why cosine similarity was the metric everyone used, or what would happen if my documents were 800 pages instead of 8. I could copy the code. I couldn't debug it. So I deleted the frameworks and wrote the whole thing by hand. No LangChain, no LlamaIndex, no hosted vector database, and no cloud LLM — the model runs on my laptop. Six files, a bit over 200 lines of TypeScript, and nothing imported that I can't explain. This post is the whole pipeline, the data structures behind each stage and why they were chosen, the four bugs that cost me the most time, and a debugging method that will save you an afternoon. Who this is for I'm assuming you write JavaScript or TypeScript, you're comfortable with async / await , arrays, and classes, and you've installed an npm package before. That's it. I am not assuming you know anything about machine learning, vectors, embeddings, or information retrieval. Every one of those is explained from zero as it comes up, and if a line of code does something non-obvious, I explain the line. If you already know what a vector store is, skip to the bug list at the bottom. What RAG actually is Strip the acronym away and RAG is one idea: Language models can't read your files. So find the relevant paragraphs yourself, paste them into the prompt, and ask the question. The rest of the pipeline exists to make that sentence practical. Finding the right paragraphs is the hard part. You can't keyword-search your way there, because a user asking "how do I stop duplicate rows" won't use the word "DISTINCT" that appears in
I built and open-sourced PacketVoyage —an Agent Skill & MCP server that turns boring traceroute outputs into fascinating stories about physics, geography, and undersea cables. europeanplaice / packetvoyage MCP server & Agent Skill for educational network traceroute analysis, fiber-optic physics verification, and packet voyage storytelling 🚢 PacketVoyage Model Context Protocol (MCP) Server & Agent Skill for educational network traceroute analysis, fiber-optic physics verification, and packet voyage storytelling. Zero external commercial APIs, zero bundled copyright data — pure physical laws and detective insight. 🏛️ Architecture: The Two Pillars PacketVoyage is built around two complementary layers designed specifically for AI-native workflows: ┌────────────────────────────────────────────────────────┐ │ AI Agent (LLM) │ └──────────────┬──────────────────────────┬──────────────┘ │ │ ▼ ▼ ┌──────────────────────────────┐ ┌──────────────────────────────┐ │ 🧠 Agent Skill │ │ 🛠️ MCP Server │ │ (Knowledge / Playbook) │ │ (Capabilities / Execution)│ ├──────────────────────────────┤ ├──────────────────────────────┤ │ • Speed of Light in Fiber │ │ • analyze_voyage_text │ │ (~0.67c, ~10ms / 1,000km) │ │ • voyage_investigate │ │ • Control vs Data Plane math │ │ • run_protocol_experiment │ │ • Disproving GeoIP illusions │ │ • research_host │ │ • Decision Flow & Heuristics │ │ • list_known_iata_airports │ └──────────────────────────────┘ └──────────────────────────────┘ 🛠️ MCP Server (Capabilities & … View on GitHub Ever wondered what’s actually happening behind a trace like this? 1 gateway (192.168.1.1) 0.8 ms 2 * * * 3 ae-1.tokyo-hnd.bb.net (203.0.113.1) 2.1 ms 4 xe-0-0.sjc-core.bb.net (198.51.100.25) 88.5 ms 5 one.one.one.one (1.1.1.1) 88.7 ms Behind these lines lies real-world physics: • The * * * at Hop 2 isn't packet loss: Normal traffic runs at line rate in hardware ASICs (Data Plane), while diagnostic ICMP responses are rate limited by router CPUs (Control Plane). • The +
Going analog is all the rage, but does it apply to the small screen?
Introduction For the past 10 days, I took part in the 10 Days of AI Voice Agents — #VoiceForBharat Edition challenge. During this challenge, I built an AI voice agent named Sadie. My goal was not just to make an AI that could talk. I wanted to build a voice agent that could understand users, remember conversations, use tools, make phone calls, connect users to humans, and hand conversations to specialist agents. This journey helped me understand that building a voice agent is much more than connecting an LLM with a text-to-speech API. The Problem Many people find it easier to speak than type. This can be especially useful for people who want to: Ask questions using their voice Learn through conversation Get quick information Speak in Hindi or English Use Hindi and English together Get help without using complicated interfaces I wanted to build a voice assistant that could make learning and getting information feel more natural. Instead of typing a question, users can simply speak to Sadie. What I Built Sadie is an AI voice agent that can: Have real-time voice conversations Understand Hindi-English code-mixed conversations Follow personality and safety rules Remember information with user permission Use external tools Make outbound phone calls Escalate conversations to humans Track call information Hand conversations to specialist agents The specialist agents I built are: Grammar Specialist Maths Specialist Full Stack Development Specialist How the System Works The basic architecture of my project is: User | | Voice ↓ LiveKit | ↓ Deepgram STT | ↓ Google Gemini / | \ / | \ Memory Tools Specialists \ | / \ | / ↓ Murf Falcon | ↓ User Voice Main Components Deepgram handles Speech-to-Text. Google Gemini acts as the brain of the agent and understands the user's request. Murf Falcon converts the AI's response into natural speech. LiveKit handles real-time audio communication. I also added memory, external tools, telephony, human escalation, analytics, and specialist agents
As if you needed more reason to love Carly Rae Jepsen's "Call Me Maybe" beyond its pop perfection, it is also, according to lore, the genesis for Switched on Pop, one of the best music podcasts out there. Cohosts Nate Sloan and Charlie Harding obsessively dissect pop songs, from the theory behind their musical choices […]
Season two of Star Wars: Ahsoka is still months away, but Lucasfilm still took the opportunity to tease it a bit at D23. The company dropped the first trailer for the new season ahead of its January 20th, 2027 debut. The clip shows a darker, witchcraft-filled take on the Star Wars universe, with Grand Admiral […]
The annual Disney fan event showed off the cast of Marvel’s X-Men movie, plus a new trailer for Avengers: Doomsday, and our first look at the VisionQuest TV show for Disney Plus. For Star Wars fans, there was a teaser trailer for season two of Ahsoka, plus a special look at Star Wars: Starfighter with […]
With Spider-Man: Brand New Day behind us, and its reveal of Sadie Sink as Jean Grey, Marvel is finally ready to officially welcome the X-Men into the MCU. At the D23 event in Anaheim yesterday, the company revealed the cast for its upcoming, untitled X-Men film, which is scheduled to hit theaters on May 5th […]
Fusion startups have raised $7.1 billion to date, with the majority of it going to a handful of companies.
The $60 billion acquisition has been finalized.
The Agentic Coding Revolution: How I Learned to Stop Typing and Start Delegating Or: what happens when your IDE becomes less of a text editor and more of a teammate. Remember when "AI-assisted coding" meant autocomplete suggestions that guessed your variable names? Those days are gone. Somewhere along the way, the tools stopped suggesting and started doing . They read your repo, run your tests, open pull requests, and sometimes fix bugs you didn't even know existed. Welcome to the era of agentic coding — and if you haven't restructured your workflow around it yet, this post is your crash course. What Actually Changed? The shift from code assistant to coding agent comes down to one capability: autonomy . A traditional assistant waits for your keystrokes. An agent receives a goal and figures out the rest. Dimension Code Assistant Coding Agent Trigger Your keystroke A stated objective Scope Single line or block Entire task, across files Feedback loop None Reads test output, retries, iterates Tool use Suggestion only Shell, browser, git, package managers Ownership You write, it suggests It drafts, you review The mental model that helped me most: stop thinking of the agent as an autocomplete and start thinking of it as a junior developer with access to your codebase. You wouldn't hand a junior engineer an undocumented task with no acceptance criteria. So why hand it to an agent? The Prompting Gap Is the New Debugging Here's the uncomfortable truth I discovered after a few months of daily agentic workflows: agents don't fail because they're dumb. They fail because our instructions are vague. Consider these two requests: ❌ Bad: "Make the app faster" ✅ Good: "Reduce p95 latency of the /search endpoint (currently 1.2s) to under 300ms. Focus on the database query layer first. Keep existing API contracts unchanged. Add a benchmark comparing before/after." The second version has a measurable goal, a constraint boundary, a starting hypothesis, and a definition of done. Agents th
Originally published on my Substack . I'm a Microsoft MVP based in Japan, writing in English about the AI agent systems I actually run in production. AI tools have multiplied. So have agents, skills, and automation scripts. And yet, somehow, my hands are never free. I wake up, open a dashboard, check notifications, go look at the logs for a failed job, and think, "wait, where was that process even running?" Every time I add one more automation, I add one more place I have to go check. That was me, up until last year. The cause was clear: I kept thinking about what to have AI do, and never once designed where I myself would touch things. So I rewrote my policy down to one line. There are only two things a human does: throw tasks into one place, and have conversations in one place. No other entry points get added. 🤖✍️ This article was co-written with AI — an AI agent (Claude Code) generated the draft automatically based on real collaborative work with Ebisuda, who then reviewed and revised it before publishing. In this series, I share the systems I've actually built using AI as case studies — including both the ones that worked and the ones that failed. What I Set Out to Build What I set out to build wasn't a specific tool or a specific agent. It was the design of the surface humans touch. The rule I settled on was just two lines. The only human entry points are Todoist (for dropping in things to do) and Discord (for conversation) Everything else gets pushed to the AI and scheduler side This is the opposite of "let's have AI do a ton of work." When people try to maximize what AI can do, they end up adding more tools. More tools means more settings screens, more places logs pile up, more places you have to go check "how's it doing now." Left unchecked, the number of automated processes and the number of places a human has to go look both grow together. So the thing I needed to decide first wasn't the scope of AI's work — it was the footprint on the human side. If you f
Earbuds range in price from under $10 to hundreds. What do you get for the money?
In 2009, Craig Gentry proved that it is possible to compute on encrypted data without ever decrypting it, and the result was widely treated as a theoretical curiosity. Sixteen years later, homomorphic encryption has crossed from conference papers into production pipelines: banks screen transactions against encrypted watchlists, hospitals run diagnostic models on data that never leaves their custody, and in August 2026 Google announced private AI features built on the same primitives. The gap between "possible in theory" and "usable in practice" is still wide, but it is no longer an argument against trying. This guide walks through what homomorphic encryption actually computes, how the CKKS scheme turns encrypted vectors into a workable substrate for machine learning, and the cost model that decides whether a private inference pipeline is worth building at all. The Promise: Compute Without Reading Ordinary encryption has a hard property: a ciphertext reveals nothing about the plaintext. AES-CTR, ChaCha20, RSA — all of them scramble data so thoroughly that an attacker holding the ciphertext and a supercomputer cannot recover the message without the key. That property is also the problem. If a server stores customer data encrypted at rest, every query requires shipping the data (or the key) somewhere a human or a process can read it. The moment the data is decrypted for computation, the confidentiality boundary moves from the storage layer to the memory of whatever process is doing the work. Homomorphic encryption changes the terms. A homomorphic scheme is one where operations on ciphertexts correspond to operations on plaintexts: Enc(a) ⊕ Enc(b) = Enc(a + b) . A server can add, multiply, and combine encrypted values and return the encrypted result, and the client — the only party holding the key — decrypts the final answer. The server learns nothing about the inputs, the intermediate values, or the output. For inference, this is the entire ballgame: the model owner ne
It was during the peak monsoon season when I read a distress report from a family stranded on their rooftop. Power was flickering, rain was hammering against the walls, and cellular data was down to a crawling 2G edge. They had a phone with 14% battery, but opening an emergency app or downloading heavy government disaster PDFs was impossible. All they could do was place a direct phone call. That moment stayed with me. When panic sets in and water is rising inside your living room, you don't navigate drop-down menus or type search queries into a browser. You need to speak, and you need a voice that answers immediately with verified life-saving relief info. That became the driving mission behind Sentinel — an autonomous, real-time Voice AI emergency dispatcher that I built over 10 days during the #VoiceForBharat challenge. The Problem I Wanted to Solve In emergency response across India, victims and disaster managers face three immediate hurdles: Information Fragmentation: Emergency guidelines, live rainfall alerts, and shelter capacities exist across different departments. A caller in panic needs instant answers (e.g., "Is there a shelter in Guwahati with medical support and space for pets?" ). The Friction of Touch UIs: Wet screens, low digital literacy, and high adrenaline make text interfaces fail. Voice is the most natural, accessible lifeline. Context Collapse: When standard chatbots escalate a user to another team or system, they drop the context and force the distressed victim to repeat their story from scratch. How Sentinel Works Under the Hood To make Sentinel feel like a natural human dispatcher, every millisecond of latency had to be eliminated. The system streams voice bidirectionally through a unified WebRTC pipeline: Speech-to-Text (STT): Deepgram Nova-3 transcribes incoming audio streams in real time with multilingual code-mixing support (English & Hindi). Brain & Reasoning (LLM): Google Gemini handles real-time disaster triage, safety guardrails, and
Prompt engineering has a bad reputation because most of it is superstition. But underneath the "you are a helpful assistant" cargo-culting, there are a handful of techniques that reliably work — and they're grounded in how the model actually behaves. Let me separate the real patterns from the folklore. These are the ones that move quality measurably, not the magic phrases people paste around without knowing why. Why prompting works at all A model predicts the next token conditioned on everything before it. Your prompt is that condition. So prompting isn't casting spells — it's setting up a context in which the desirable continuation is the most probable one. Every technique below is just a different way of doing that. The techniques that actually move the needle 1. Be specific about the output, not just the task. Vague in, vague out. Don't ask for "a summary" — ask for "three bullet points, each under 15 words, focused on financial risk." You're narrowing the probability space toward exactly what you want. 2. Give examples (few-shot). Showing the model two or three input/output pairs is often worth more than paragraphs of instruction. The model is extraordinary at pattern-matching; demonstrate the pattern and it follows. This single move fixes more formatting problems than any amount of description. 3. Let it think before it answers (chain-of-thought). For anything involving reasoning, telling the model to work through the steps before giving a final answer measurably improves correctness. Rushing straight to an answer is where models make careless mistakes — the same as people. 4. Assign a role with purpose. "You are a senior security engineer reviewing this code" genuinely shifts the output — not because of flattery, but because it conditions the model toward a specific register and body of knowledge. Use it when the framing changes the answer; skip it when it's just decoration. 5. Decompose hard tasks. Instead of one prompt that does five things, chain five promp
Every glassmorphism snippet I've seen is backdrop-filter: blur() plus a white overlay. That's a blurred rectangle. Real glass bends what's behind it, hardest at the edge — and that part is missing everywhere. Built it for a production Angular app, pulled it out as a Claude Code plugin: https://github.com/stormaref/LiquidGlassSkill /plugin marketplace add stormaref/LiquidGlassSkill /plugin install liquid-glass@stormaref-skills The refraction: bake a displacement map into a canvas, wire up feImage → feDisplacementMap → feGaussianBlur , point the element at it with backdrop-filter: url(#filter) . Since it's a backdrop filter, the input is the live page behind the element — so it tracks scroll, theme and content changes with nothing to invalidate. Field ported from liquid-glass-js (MIT, credited), minus its html2canvas snapshot. Why it's a skill and not a gist — four rules, each of which fails as plausible-looking output: Glass needs a backdrop. Over a flat page it reads as a gray box, which sends you reaching for more blur — the exact move that kills it. The tint is colorless. Hue in the tint fights the hue coming through; the surface goes muddy. Children of a glass panel paint no surface. An opaque fill covers the refracted backdrop, which is the whole effect. You can't feature-query it. Safari parses backdrop-filter: url(#…) and paints nothing, so @supports says yes and your panel is blank. Gate on engine. The CSS is 200 lines. Knowing that #1 is why your glass looks nths of things looking subtly wrong. MIT. Happy to talk displacement math — the 128/255 ≠ 0.5 decly long to find.