标签：#p

Voice-first AI agent that operates your Mac Discussion | Link

I keep running into (and hearing about) a specific kind of bug that never throws an error — an API you depend on quietly changes its response shape. A field disappears. A number becomes a string. Something that was always present is suddenly null. Nothing crashes immediately. It just produces wrong or missing data somewhere downstream, and you find out from a bug report, not a log. I'm curious how common this actually is outside my own experience, so — genuine question, not a pitch: Has this happened to you, with a third-party API or even an internal one your own team owns? How did you find out it happened — a user report, a stack trace somewhere unrelated, manual debugging? Do you currently do anything to catch this kind of thing before it bites you (contract tests, monitoring, or just... hoping)? If you don't do anything about it today, is that because it's not painful enough to bother, or because you just haven't found a lightweight way to? Not selling anything here, just trying to understand how real and how painful this actually is for people building on top of APIs day to day. Would genuinely appreciate hearing your experience, even a one-line "yeah this happened to me once, wasn't a big deal" is useful data.

I started building Kudzu while making static websites with AI. AI coding tools have become very good at producing React-shaped TSX, and I have become used to reviewing code in that form. Function components, props, JSX, and event handlers are often easier for me to understand and verify than scattered DOM queries and imperative JavaScript mutations. But I was still building static pages. I wanted to keep TSX as the authoring and code-review format without automatically shipping React, a virtual DOM, hydration, or a browser-side component tree. Kudzu grew from that idea: Write familiar TSX, execute components during the build, and ship ordinary HTML with only the JavaScript each route actually needs. Kudzu is an experimental, HTML-first TSX framework. Website: kudzujs.cloud GitHub: github.com/kudzujs/kudzu The problem I wanted to solve Consider a blog, documentation site, newsletter, or product landing page. Most of the page is already known during the build: headings; navigation; articles; images; metadata; product descriptions; documentation content. TSX is a convenient way to author and review that structure. function PostCard ({ title , description , href }: { title : string description : string href : string }) { return ( < article > < h2 >< a href = { href } > { title } </ a ></ h2 > < p > { description } </ p > </ article > ) } The component model is useful for authoring, but that does not necessarily mean the browser needs a component runtime. For a static page, I wanted the output to remain ordinary HTML. <article> <h2><a href= "/posts/hello" > Hello </a></h2> <p> My first article. </p> </article> I also wanted interactive pages to receive only the JavaScript required for their actual behavior. Kudzu's model Kudzu treats components as build-time authoring units. React-shaped TSX ↓ Kudzu compiler ↓ Static HTML + CSS + capability-specific ESM Function components execute during the build. The browser does not receive: the component functions; React; a virtual D

Subscription Goldmine: SaaS Models and Startup Cash Flow Here's the brutal truth: nothing brings a tech solopreneur closer to existential dread than staring down a dried-up cash runway in the office at midnight. This concern is universal for founders, whether you're nestled in a cozy Davao home office or grinding away in a bustling city. The rise of subscription-based Software as a Service (SaaS) models is shifting this narrative, offering both solutions and new challenges. The stakes are high, but so are the potential rewards. The Core Problem & Why This Matters Startups live and die by their cash flow. Managing liquidity is crucial for keeping the lights on and securing future growth. Traditional software sales were typically characterized by large, one-time purchases. This model, while sometimes lucrative, posed significant challenges for startups that needed a steady influx of cash. The subscription model flips this on its head by transforming how revenue is recognized, providing a more predictable income stream. The consistent monthly inflows from subscriptions give startups the cushion they need to weather the ups and downs of growth periods. But here's the catch: converting users into paying subscribers isn’t a cakewalk. It requires upfront investments in product development, marketing, and customer support. Yet, this model becomes a vital lifeline, especially when venture capital isn't an option. Subscription models necessitate long-term engagement strategies, but they offer a recurring revenue stream that can stabilize an otherwise volatile cash flow. The Systems Engineering Approach Developing a subscription-based SaaS model requires a meticulous systems approach. The first step involves designing a seamless user experience . Every touchpoint must be optimized to retain users and convert trial customers into paid subscribers. From initial sign-up to daily usage, every feature should scream value. Next, focus on robust backend systems. These systems are the

Friendly hobby machine or serious production tool? Here’s how to know which one is for you.

Researchers say TikTok, X, and Meta aren't providing data they're legally required to.

I packed these Leatherology totes with laptops, chargers, and everything else my workday demands. Months later, they’re still the bags I keep reaching for.

Safe AI chat for kids Discussion | Link

I Run Bare-Metal Kubernetes on $200 of Scrap Hardware (And Why I Burned 3 SD Cards...

Tokenization → embeddings → causal Transformer → LM head → softmax → loss → backpropagation. No TensorFlow, no PyTorch, and no hidden autograd. Repository: tiny-language-model-neuro-js . Most explanations of language models present correct formulas but hide the path between them inside a framework. I wanted the opposite: one small scenario where every scalar is visible and where the terminal clearly shows incorrect answers before learning and correct answers after it. The project now has one command: node src/train.js --generalize --adaptive-teach It requires Node.js 18.19+ and has no dependencies. The result first The model is queried immediately after random initialization: BEFORE TRAINING — random, usually wrong answers > can human read ? model: ? <unk> ... expected: human can read. [WRONG] > can fish swim ? model: ? <unk> ... expected: fish can swim. [WRONG] > can cat read ? model: ? <unk> ... expected: cat cannot read. [WRONG] After pre-training, SFT, and adaptive SFT, the same model produces: FINAL ANSWERS AFTER ADAPTIVE SFT > can human read ? model: human can read. [CORRECT] > can fish swim ? model: fish can swim. [CORRECT] > can bird fly ? model: bird can fly. [CORRECT] > can cat read ? model: cat cannot read. [CORRECT] Rehearsal controls preserved: 14/14. Stable criterion reached 11 times in a row. The initial text varies because initialization is random. The final acceptance criterion does not: all answers must be correct, every target token must have at least 95% probability, and the complete check must pass more than ten times consecutively. What remains after removing the extra modes The code previously contained several debug and training modes. They were useful while experimenting but obscured the main idea. The final version keeps one educational pipeline: text → word tokenization → token IDs → token + position embeddings → two causal Transformer blocks → multi-head self-attention → two-hidden-layer FFN → LM head → softmax → next-token probabilities

GoPro’s New Mission 1 cameras bring action cameras to a higher level with a larger sensor and more cinematic footage.

Most journaling and mental wellness apps require syncing sensitive personal thoughts to cloud servers where they risk being mined or exposed. I wanted a space where user data never leaves the browser. So I built Sanctuary — a lightweight, local-first reflection vault. 🛠️ Technical Highlights 100% Local-First: All entries and app states stay strictly inside browser local storage. Zero tracking scripts or analytics. Resonance Diagnostics: Dynamic, client-side SVG visualizations mapping baseline mood trends over time. Therapy PDF Export: Uses native CSS print styling ( @media print ) to generate clean offline summary reports for check-ins without sharing app access. Zero Overhead: Blazing fast load times with no database or cloud sync latency. Check out the live app: sanctuaryb.lovable.app I'd love feedback from the dev community on the local storage architecture, baseline algorithms, or visual UI!

If you're writing Playwright API tests manually from an OpenAPI/Swagger spec, you're doing work that should be automated. Every endpoint in your spec already tells you: What the request looks like (path, method, parameters, body schema) What responses to expect (200, 401, 404, 422...) What fields are required What security is needed That's not documentation — it's a test plan. You're just not running it yet. What I built I got tired of the boilerplate loop: read spec → write happy path → add 401 test → add missing-field test → repeat for 40 endpoints. So I built a tool that does it for you. swagger-to-playwright.vercel.app takes your OpenAPI 3.x spec (YAML or JSON) and generates a ready-to-run Playwright .spec.ts file. For each endpoint, it produces four tests: 1. Happy path — calls the endpoint with valid data, asserts 2xx response and key fields in the body. 2. Auth check — if your spec declares a security scheme, it calls without a token and asserts 401. Only generated when the spec actually says authentication is required — no false positives. 3. Input validation — sends a request with missing required fields (or wrong types, invalid enums) and asserts 422. Reads directly from your schema's required array and field types. 4. Contract validation — if there's a path parameter, it calls with an invalid value and asserts 404. What the output looks like Here's what you get for a POST /users endpoint with email and password required: import { test , expect } from ' @playwright/test ' ; test . describe ( ' POST /users ' , () => { test ( ' happy path — creates user successfully ' , async ({ request }) => { const res = await request . post ( ' /users ' , { data : { email : ' test@example.com ' , password : ' password123 ' } }); expect ( res . status ()). toBe ( 201 ); const body = await res . json (); expect ( body ). toHaveProperty ( ' id ' ); }); test ( ' auth — 401 without token ' , async ({ request }) => { const res = await request . post ( ' /users ' , { headers : {

Disclosure: This post includes affiliate links; I may receive compensation if you purchase products or services from the different links provided in this article. Credit: codemia.io Hello Devs, if you're preparing for software engineering interviews, particularly in MAANG, you already know that Data Structures & Algorithms (DSA) and System Design are two key areas where you will be rigorously tested. While LeetCode is the go-to platform for DSA, system design has always been a challenge. While there are many websites and platforms to prepare for System Design Interviews like ByteByteGo , DesignGurus.io , Exponent , Educative , and Udemy , there is nothing like LeetCode. These are great resources to learn fundamentals, go through case studies, and understand the theory part of system design, but LeetCode-style practice is one thing that is missing - until now. I recently found Codemia.io , and I must say, it feels like the LeetCode for System Design. If you've struggled with structuring your system design answers, getting real feedback, or knowing whether your approach is correct, Codemia.io is a game-changer. They not only have the biggest collection of System Design and OOP Design problems for practice, but they also have a free System Design course called Tackling System Design Interview Problems , which is a great free resource to learn essential System Design concepts. It's a short course with 2 hours of content, but it's powerful and also has quizzes to test your skills. Here are all the key System Design topics you can learn on this free course: Now, let's check out how Codemia.io can help you to prepare better for your System design and OOP Design interview, and why I think it's like Leetcode for System design. Most system design resources today are long, text-heavy articles or expensive courses. The problem? No hands-on practice - Reading about system design isn't enough; you need to actively design solutions. No structured progression --- Unlike DSA, where

Before you can truly understand how AI systems think, learn, and generate responses, you need to understand the math that powers them. This guide covers the essential mathematical concepts that form the backbone of modern Artificial Intelligence and Large Language Models (LLMs). Why does this matter? Every aspect of AI — from how text is encoded, to how a model predicts the next word, to how it improves itself during training — is driven by mathematics. Skipping this foundation means you will only ever use AI as a black box, without understanding why it works. 🔄 How an LLM Actually Works — The Complete Pipeline Before diving into each math concept individually, here's the big picture of how text flows through a Large Language Model from input to output. Every section in this guide maps to a step in this pipeline: ┌─────────────────────┐ │ Your Prompt │ "What is gravity?" └──────────┬──────────┘ ↓ ┌─────────────────────┐ │ Tokenizer │ Splits text into chunks (BPE algorithm) └──────────┬──────────┘ → Section 1: Number Systems & Encoding ↓ ┌─────────────────────┐ │ Token IDs │ Each token → a number (e.g., "gravity" → 17942) └──────────┬──────────┘ → Section 1: Number Systems & Encoding ↓ ┌─────────────────────┐ │ Embedding Model │ Each token ID → a dense vector of numbers └──────────┬──────────┘ → Section 3: Vectors & Embeddings ↓ ┌─────────────────────┐ │ Vectors │ [0.12, -0.87, 0.45, ...] per token │ + Positional Info │ → Section 3 & 6: Embeddings & Linear Algebra └──────────┬──────────┘ ↓ ┌─────────────────────┐ │ Transformer │ Multi-Head Attention + Feed-Forward layers │ (×N layers) │ repeated 32-96+ times └──────────┬──────────┘ → Section 4, 6: Algebra & Linear Algebra ↓ ┌─────────────────────┐ │ Probability │ Softmax converts final output to │ Distribution │ probabilities over entire vocabulary └──────────┬──────────┘ → Section 2 & 6: Probability & Softmax ↓ ┌─────────────────────┐ │ Next Token │ Sampling picks one token │ (Sampling) │ (using Temperature, Top-K,

Hash the password, hand out a token, and make absolutely sure no one can read someone else's expenses. So Phase 2 gave my app a mouth. It could finally talk — create, read, update, and delete expenses over real HTTP endpoints, all clicking together through /docs . But there was a giant, deliberately-ignored problem sitting in the middle of it: the door had no lock. Anyone who could reach the server could read, edit, or delete anything. And every expense I created was quietly stamped with the same hardcoded owner — a "dev user" whose id I'd nailed into the code with a # TEMP note and a promise to fix it "in Phase 3." Well. It's Phase 3. Time to pay that debt. This is where the app grows a bouncer. The buzzword is auth , which actually hides two jobs that sound the same and aren't: authentication ["who are you?"] and authorization ["okay, but are you allowed to touch this ?"]. I went in thinking auth was "add a login form" and came out having learned about one-way hashing, signed tokens, a security bug with the excellent name IDOR , and why the same password can produce two different hashes. Let me dump what I learned [and the parts that tripped me up, because — as usual — there were several]. Auth is the one phase where you have to stop thinking like a builder and start thinking like the person trying to rob you. So every step below is really "here's a way an attacker wins, and here's the gap I closed to stop them." The structure. Let's call it PHASE 3 — The Lock: Give the User table somewhere to store a password [a hashed one, never the real thing] Password hashing helpers — turn a password into something safe to store POST /auth/register — sign up with a hashed password Understand what a JWT actually is [it's just a signed string, and it's readable] POST /auth/login — check the password, hand back a token get_current_user — the gatekeeper that turns a token back into a user Lock every expense endpoint and scope it to the logged-in owner Retire the hardcoded DEV_USE

In 2024, everyone and their manager launched an AI wrapper. A thin layer over GPT-4, a nice UI, a subscription fee, and boom: you were an AI company. Product Hunt had hundreds of these launches. Investors poured money into them. And by 2026, most of them are dead. Not all of them though. A handful survived and crossed real revenue milestones. Their stories reveal something important about where the AI market is actually going. The wrappers died but the value moved somewhere real. What Actually Killed the Wrappers The math never worked. An AI wrapper is a startup whose core product is a prompt sent to someone else's model. You pay OpenAI (or Anthropic or Google) for tokens. You charge your users a markup. And you hope the difference covers your hosting, your team, and your coffee. Three things broke that math. First, the model providers kept getting cheaper. OpenAI cut prices multiple times through 2024 and 2025. As TechCrunch reported , each price drop squeezed the wrapper margin another notch. If you were marking up tokens 3x and the base price dropped 50%, your margin went from 200% to 50% overnight. Second, the big models got good enough at general tasks that users stopped needing the specialized UI. Why pay $20/month for a writing assistant that wraps ChatGPT when you can just use ChatGPT directly? The OpenAI GPT Store made this worse: custom GPTs replaced a huge chunk of wrapper functionality for free. Third, users wised up. The initial AI hype in 2023 convinced people to pay for anything with "AI" in the name. By 2025, that was over. G2's research showed that enterprises stopped buying standalone AI tools and started demanding AI features built into their existing software stacks. The result was predictable. Hundreds of wrapper startups shut down, got acquired for pennies, or pivoted to something completely different. What Actually Works Now The survivors fall into three categories. Each one solves the problem the wrappers ignored: building defensible value on

A HIPAA-compliant AI voice agent for healthcare typically costs $40,000-$150,000 to build, depending on call complexity and EHR integration, plus $2,000-$15,000/month to operate. The build cost isn't dominated by the speech model — it's dominated by the compliance and data-retention layer wrapped around it. Most cost estimates for "AI voice agents" quietly assume a sales or support use case, where a wrong transcription costs you an annoyed customer. In healthcare, a wrong transcription in a medication name or a dropped consent statement is a liability. That difference reshapes the budget. Where the money actually goes 1. Speech recognition (10-20% of build cost) This is the smallest line item, despite being the part founders worry about most. You have three options: Managed API with a BAA (e.g., enterprise-tier Deepgram, Azure Speech, Google Healthcare API) — fastest to ship, but you're paying per-minute and locked into the vendor's accuracy on medical terminology. Fine-tuned open-weight model — better accuracy on clinical vocabulary and accents, but adds MLOps overhead. Self-hosted model — highest control over data residency, needed if your contracts or state law prohibit sending PHI to a third party. If your patient population speaks Gulf Arabic or another dialect underserved by mainstream ASR, budget separately for this — see our breakdown on Arabic speech recognition costs for how accent and dialect coverage move accuracy and price independently of the base model choice. 2. Compliance infrastructure (30-40% of build cost) This is where healthcare voice AI diverges hardest from a generic voice bot: Business Associate Agreements with every vendor in the call path (ASR, LLM, telephony, storage) Encryption at rest and in transit, with key management you can audit Role-based access control on transcripts and recordings Immutable audit logs of who accessed what patient data and when The U.S. Department of Health and Human Services publishes the actual HIPAA Security R

Introdução Integrar Apache Airflow com .NET 10 não significa portar o orquestrador, reescrever DAGs em C# ou executar o runtime Python dentro da aplicação. A solução correta é manter o Airflow responsável por criar, agendar e monitorar workflows e fazer o serviço .NET consumir sua API REST pública. O serviço autentica, dispara um DAG Run com parâmetros, guarda o identificador retornado e consulta o estado até receber success , failed ou canceled . Essa separação preserva o papel de cada tecnologia e cria um contrato claro entre a aplicação transacional e a plataforma de dados. Neste guia, eu vou implementar esse fluxo de ponta a ponta usando .NET 10 , HttpClient , autenticação JWT e a API /api/v2 do Apache Airflow 3.3 . O exemplo não se limita a um POST : ele gera um dag_run_id rastreável, serializa conf corretamente, reutiliza o token até perto da expiração, renova a credencial após uma resposta 401 , aplica timeout ao monitoramento e propaga cancelamento. Também vou expor a integração por uma Minimal API, para que outro sistema possa iniciar o processo sem conhecer os detalhes do Airflow. O nome atual da plataforma da Microsoft é .NET 10 , e não “.NET Core 10”. A marca “.NET Core” foi usada até a versão 3.1; desde o .NET 5, o produto unificado passou a se chamar apenas .NET. Essa diferença não altera o código, mas evita confusão ao procurar documentação, imagens de container e pacotes compatíveis. O cenário prático será um serviço de pedidos que solicita a execução do DAG etl_vendas . A configuração enviada contém a data de referência e um identificador de correlação. O Airflow continua executando tarefas Python, SQL, containers ou jobs distribuídos; o C# apenas controla o ciclo de vida da execução pela fronteira HTTP. ℹ️ Informação: no Airflow 3, os endpoints públicos estáveis ficam sob /api/v2 . Rotas internas de UI não são um contrato de integração e podem mudar conforme o frontend. Pré-requisitos Para acompanhar o exemplo, você precisa do .NET 10 SDK , do Dock

Ship localised Apps faster Discussion | Link