标签：#os

The MacBook Neo is Apple's cheapest laptop, its most colorful, and its easiest to repair in years. That means owners can buy replacement parts in all four of its available colors and swap them in on their own. So that got us thinking: What if we bought a Neo just to see how funky we […]

Indie Hacking the App Store: Navigating Apple's Guidelines for Niche Catholic AI Applications The era of building generic software-as-a-service (SaaS) platforms is shifting. For independent developers and indie hackers, the real opportunity now lies in underserved, highly specific markets. One of the most fascinating and complex niches emerging today is the intersection of artificial intelligence and religious utility. Building a catholic ai application presents a unique set of technical, ethical, and regulatory hurdles. Developers must create highly accurate systems while navigating strict platform guidelines. Unlike general-purpose chatbots, religious applications require absolute precision. A single theological error can ruin user trust. Furthermore, platforms like the Apple App Store have strict rules regarding user safety, privacy, and functionality. This article explores the technical architecture, prompt engineering strategies, and platform compliance steps required to build and launch a successful catholic ai app . Whether you are using Flutter, Swift, or Kotlin, these insights will help you build a robust, secure, and helpful application. Designing a Catholic AI: Aligning with the Catholic Church Stance on AI Before writing a single line of code, developers must understand the domain. Building tools for this community requires respect for established doctrines and traditions. Fortunately, the Vatican has provided clear guidance on this technology. The Catholic Church Stance on AI The Vatican has taken a proactive and surprisingly technical approach to modern computing. Under the leadership of Pope Francis, the Church has introduced the concept of "algorethics"—the ethical development and deployment of algorithms. The catholic church stance on ai emphasizes that technology must always serve human dignity, protect personal privacy, and promote truth. For developers, this means your application must prioritize: Truthfulness: Minimizing errors in theological ou

I recently rebuilt my homelab from scratch. The goal was simple: one machine, everything containerised, zero exposed ports, GPU-accelerated local AI, and a fully automated backup setup. No cloud subscriptions for the tools I use every day. This is the full technical breakdown — what I'm running, how it's wired together, and the hard-won fixes that cost me hours so you don't have to repeat them. What I'm Running Eight services, 26 containers, one machine: Service Purpose Portainer Docker management UI Uptime Kuma Service monitoring (7 monitors) NocoDB Self-hosted Airtable — CRM & leads n8n Workflow automation Open WebUI Local AI chat interface Ollama Local LLM inference (GPU) AFF!NE Collaborative docs & whiteboards Plane Project management (roadmaps, sprints) Duplicati Encrypted daily backups Cloudflare Tunnel Zero Trust secure access — no open router ports All external-facing services sit behind Cloudflare Zero Trust with email OTP. No passwords to manage, no VPN clients — Cloudflare handles authentication at the edge. Architecture ┌──────────────────────────────────┐ │ Cloudflare Edge (Zero Trust) │ │ *.yourdomain.com — email OTP │ └──────────────┬───────────────────┘ │ HTTPS ┌──────────────▼───────────────────┐ │ Ubuntu Machine │ │ │ │ cloudflared (outbound tunnel) │ │ │ │ │ ┌─────▼────────────────────┐ │ │ │ homelab-net (bridge) │ │ │ │ │ │ │ │ portainer uptime-kuma │ │ │ │ nocodb n8n │ │ │ │ open-webui affine │ │ │ │ plane-* duplicati │ │ │ │ ollama (GPU passthrough) │ │ │ └───────────────────────────┘ │ └───────────────────────────────────┘ Everything runs on a shared Docker bridge network ( homelab-net ). The cloudflared container maintains an outbound-only encrypted tunnel — no inbound ports open on the router at all. Ollama runs in Docker with NVIDIA GPU passthrough. The AI model inference happens on the GPU, leaving CPU headroom for all other services. Prerequisites Ubuntu 24.04 LTS Docker Engine + Compose v2 NVIDIA GPU with driver 535+ NVIDIA Container Too

APScheduler's Advisory Lock Failure: My Solo VM's Scheduler Died Permanently It started with a user report: "Content engine auto-publishing should put 3 posts on dev.to, but only 2 appeared, and then nothing worked." This is the kind of subtle bug that can fester, but the reality was far more systemic. My entire APScheduler setup had died. Not just for dev.to, but for *all* my scheduled tasks: content engine sweeps, daily top 3 analysis, profile analysis, model health checks, weekly reports – everything. The cron logs showed nothing for three days straight. This wasn't just a hiccup; it was a full-blown scheduler apocalypse on my single small VM. The immediate symptom was a lack of new posts on dev.to, but the root cause was a complete, permanent scheduler failure. The Wrong Turn: Relying on PostgreSQL Advisory Locks for Leader Election My approach to ensuring only one instance of my worker process ran scheduled jobs involved using PostgreSQL's pg_try_advisory_lock . The idea was that each worker would try to acquire this advisory lock. The one that succeeded would be the leader, responsible for running the jobs. Other workers would see the lock is held and stand down. However, in my specific environment – direct PostgreSQL connection (localhost:5432) without a connection pooler like pgbouncer, using asyncpg for dedicated connections – this mechanism proved fatally flawed. The lock was acquired, but immediately released. The worker thought it held the lock ( active=True ), but a check of pg_locks showed zero holders. This meant the singleton pattern was broken. Worse, the self-healing mechanism relied on the same flawed lock acquisition, meaning it couldn't recover. The situation was so unstable that I even observed a period where both my blue and green services (running on ports 8000 and 8001 respectively) thought they were the leader, resulting in a double execution of jobs. This was a clear sign the leader election was fundamentally broken. The Root Cause: Sessio

I used to think the best AI food logging flow would be simple: Take a photo, let the model identify the meal, confirm it, done. That works surprisingly well for a lot of meals. But while building MetricSync, I learned the awkward product truth: the best input method changes depending on what is in front of the user. A photo is great for a plate. A barcode is better for packaged food. Text is better when the user already knows what they ate or wants to fix one detail quickly. The mistake is treating one input mode like the whole product. Photos feel magical until the meal gets messy Photo logging is the most impressive demo because it removes the blank search box problem. The user does not need to know the exact database name for “rice bowl with chicken and avocado.” They can just show the app what they ate. But meals are messy. A photo might miss the sauce. It might not know if the drink is diet or regular. It might confuse a small serving with a large one. It might identify the food category correctly but still need a portion correction. That does not make photo logging bad. It just means the UX cannot end at “AI guessed something.” The real product is the correction loop. Can the user fix the meal without starting over? Barcode scanning is boring in the best way Barcode scanning is not as exciting as AI, but it is often the right tool. If someone is logging a protein bar, yogurt, cereal, or a packaged drink, asking an image model to infer the nutrition facts is silly. The barcode is more direct. That changed how I thought about the app. AI should not be the star of every interaction. Sometimes AI should get out of the way. The goal is not “use AI everywhere.” The goal is “make logging the thing in front of me take the least effort.” For packaged foods, that means barcode first. For mixed plates, that means photo first. For quick edits, that means text. Text still matters The more AI features you add, the easier it is to forget text input. But text is still the fas

NousResearch Agent, Open-Source Notebook LM, & Local Multimodal OCR for Consumer GPUs Today's Highlights Today's highlights feature new open-source tools empowering local AI inference and deployment, including an adaptive agent from NousResearch, a self-hostable AI-powered notebook, and a lightweight multimodal OCR solution. These practical GitHub trending projects enable developers to build and run advanced AI applications directly on consumer hardware. NousResearch Unveils Hermes Agent for Adaptive Local AI (GitHub Trending) Source: https://github.com/NousResearch/hermes-agent NousResearch, a prominent contributor to the open-weight LLM ecosystem with models like the Hermes series, has unveiled hermes-agent , a new GitHub trending project described as "The agent that grows with you." This initiative represents a significant step towards practical, adaptive AI agents designed for local execution. While specific architectural details are awaiting a deeper dive into the repository, the "grows with you" philosophy strongly implies advanced capabilities for personalized learning, continuous adaptation, and long-term memory integration—features crucial for self-hosted AI applications. Such an agent is highly relevant for developers focused on local inference, as it provides an open-source framework to build sophisticated agentic workflows, potentially integrating seamlessly with local LLM runtimes such as llama.cpp or vLLM . This allows users to leverage powerful open-weight models directly on their consumer GPUs, enhancing privacy and reducing reliance on cloud services. The project's emergence from NousResearch solidifies its potential as a robust foundation for next-generation local AI applications. Comment: A NousResearch agent is exciting; it implies strong open-source model compatibility and local deployment. I'm keen to see its learning mechanisms and integration potential with local LLM runtimes. PaddlePaddle's Lightweight OCR Toolkit Bridges Images to Local LLM

I can't remember the last time Microsoft kicked off a Build keynote with Windows front and center, but that's exactly what CEO Satya Nadella did this week. Nadella didn't address the issues Microsoft is trying to fix in Windows 11 but chose to woo the audience with Microsoft's slick Surface RTX Spark Dev Kit instead, […]

Create a storage account and configure high availability. Create a storage account for the internal private company documents. In the portal, search for and select Storage accounts . Select + Create . Select the Resource group created in the previous lab. Set the Storage account name to private . Add an identifier to the name to ensure the name is unique. Select Review , and then Create the storage account. Wait for the storage account to deploy, and then select Go to resource . This storage requires high availability if there’s a regional outage. Read access in the secondary region is not required. Configure the appropriate level of redundancy . Explanation A storage account is like a digital locker in the cloud. Resource group is a folder that organizes related services. High availability means your files stay safe even if one region (data center area) has problems Configure Redundancy In the storage account, in the Data management section, select the Redundancy blade . Ensure Geo-redundant storage (GRS) is selected. **Refresh **the page. Review the primary and secondary location information. Save your changes. Explanation : Redundancy means keeping copies of your files in multiple places. GRS ensures your files are copied to another region for safety. Create a storage container, upload a file, and restrict access to the file. Create a private storage container for the corporate data. In the storage account, in the Data storage section, select the Containers blade. Select + Container . Ensure the Name of the container is private . Ensure the Public access level is Private (no anonymous access). As you have time, review the Advanced settings, but take the defaults. It means: don’t change anything in the Advanced settings unless the lab specifically tells you to. Azure already chooses safe, recommended defaults for you. Select Create . Explanation : A container is like a folder inside your storage account. Setting Public access level to Private means nobody can see

Introduction: The Controversial Rise of AI in Software Development The software development industry is at a crossroads. On one side, the rapid advancement of AI tools promises to revolutionize coding, automate repetitive tasks, and accelerate project timelines. On the other, a growing chorus of experts, led by figures like George Hotz , warns that the integration of AI agents into software development could become "one of the most costly mistakes in the field’s history." This bold prediction isn’t just hyperbole—it’s a call to scrutinize the mechanisms by which AI adoption could deform the very foundation of software engineering. At the heart of this debate are three critical failure points: over-reliance on AI without human oversight , insufficient real-world testing , and misalignment between AI capabilities and software development demands . Each of these factors acts as a stressor on the system, threatening to heat up development costs, expand systemic vulnerabilities, and ultimately break the delicate balance between innovation and reliability. Consider the causal chain: over-reliance on AI leads to a degradation of human expertise , as developers become less engaged in problem-solving. This, in turn, creates a feedback loop where AI-generated code, lacking nuanced understanding, introduces errors that go unnoticed. Without proper oversight , these errors propagate through systems, causing observable effects like reduced software quality and increased maintenance costs. Similarly, insufficient testing of AI agents in real-world scenarios means their failure modes remain unknown until they’re deployed at scale, risking systemic collapse in critical applications. The stakes are high. If unchecked, AI integration could lead to a loss of institutional knowledge , escalating development costs , and vulnerabilities in critical systems . The question isn’t whether AI has a role in software development—it’s how to implement it without deforming the field’s core princi

Dumpert is a Dutch video site I've watched for years, but there's never been an Apple TV app, so I built one. DumpertTV is an unofficial, open-source tvOS client. Here's how it's put together and a few things that were more interesting than I expected. Disclaimer up front: this project is not affiliated with Dumpert or DPG Media B.V. It's an independent app that uses the public Dumpert API. The stack Swift 6 with strict concurrency ( complete mode) across every target SwiftUI for all UI, tvOS 18+ XcodeGen so the .xcodeproj is generated from a project.yml and never committed CloudKit , GroupActivities (SharePlay), Vision , AVKit , Swift Testing One actor for the network, one source of truth for the UI The whole networking layer is an actor . That makes per-request state like ETags and retry bookkeeping thread-safe without a single lock: actor DumpertAPIClient { private var etags : [ URL : String ] = [:] func fetch < T : Decodable > ( _ endpoint : APIEndpoint ) async throws -> T { // Exponential backoff on 5xx + network errors; honours 304 Not Modified. try await fetchWithRetry ( endpoint , attempt : 0 ) } } The UI reads from a single @Observable @MainActor repository injected through the SwiftUI environment — no Combine, no view models competing over the same state: @Observable @MainActor final class VideoRepository { private(set) var hotshiz : [ MediaItem ] = [] let apiClient : APIClientProtocol // protocol-backed for testing } ContentView () . environment ( videoRepository ) Views just read repository.hotshiz ; updates flow automatically. With Swift 6's strict concurrency on, the compiler kept me honest about every actor hop. Things that were trickier than expected tvOS focus + a top tab bar. Getting a Netflix-style hero carousel to behave with the focus engine took real care. It also made automating screenshots interesting — scripted remote input doesn't reliably drive the simulator, so I added #if DEBUG launch-argument hooks to jump straight to any tab/category f

Some quantum computing companies we've covered have done recent progress updates.

Just in case you were wondering, Nvidia's RTX Spark isn't supposed to be a one-off. The company is not just flirting with becoming the fifth high-profile vendor of consumer laptop chips to see if people bite. At Computex 2026 in Taipei, Nvidia CEO Jensen Huang confirmed at least two additional generations of RTX Spark are […]

At Microsoft's annual Build conference on Tuesday, the company announced a slew of new or expanded AI initiatives, including a super app, in-house reasoning models, a cybersecurity tool, and OpenClaw-esque AI agents. All this news added up to a clear message: Microsoft is positioned to be one of the biggest players in AI, and it's […]

Microsoft has two new Surface devices arriving later this year, both powered by Nvidia's RTX Spark chips. I got a chance to take a closer look at both the Surface Laptop Ultra and Surface RTX Spark Dev Box at Microsoft's Build conference this week, and while both have the same chip inside, they're utilizing Nvidia's […]

Every detection vendor ships a MITRE ATT&CK heatmap, and every one of them is mostly green. Broad coverage, techniques lit up across the board, a reassuring wall of color in the sales deck and the board slide. It's the universal flex. We cover the matrix. Then you parse the actual rules – the real YAML in the public repo, not the marketing layer on top of it – and the green collapses into three tactics. Everyone covers execution and persistence. Almost nobody covers discovery, lateral movement, or collection. The heatmap wasn't measuring coverage. It was counting rules, and counting them in a way designed to look complete. What a green cell actually means A green cell in a Navigator layer means one thing: at least one rule somewhere references that technique tag. That's it. Not "we detect this reliably." Not "this fires on real attacks and stays quiet otherwise." Not "this survives an attacker who knows the rule exists." One rule that names the technique in its metadata turns the cell green, and forty rules turn it the same shade. Unless the layer is scored by rule count – and most published heatmaps aren't – one and forty are indistinguishable. I've written before that an untested detection isn't a detection, it's a query that runs on a schedule. The heatmap is the same lie one level up. A green matrix isn't coverage. It's a wall of queries that run, rendered in a color that means "present," dressed up as a color that means "protected." The vendor knows the difference. The buyer staring at the green doesn't. You can measure the real shape yourself Here's the part the heatmap marketing depends on you not doing: the rules are public, and you can count them. SigmaHQ, Elastic's detection-rules, Splunk ESCU, Panther, Sublime – all on GitHub, all tagged with attack.TXXXX technique IDs and tactic tags in the rule metadata. The method is boring on purpose. Walk the rule directories. Pull the ATT&CK tags out of each rule. Aggregate by technique, roll the technique counts up

Microsoft launched seven new in-house AI models at Build 2026 on June 2, 2026, marking the company's most significant push yet to build its own frontier AI stack independent of OpenAI. The centerpiece is MAI-Thinking-1, Microsoft's first large-scale reasoning model, built from scratch on clean commercially licensed data using a sparse Mixture of Experts architecture. Alongside it: MAI-Code-1-Flash, a 5-billion-parameter coding model that outperforms Claude Haiku 4.5 by 16 percentage points on SWE-Bench Pro while using 60% fewer tokens on complex tasks. This is the complete developer guide to all seven MAI models, their specs, benchmarks, deployment paths, and what they mean for the AI development ecosystem. Why Seven Models at Once? The strategic context matters. For three years, Microsoft's AI product surface — GitHub Copilot, Azure AI, Bing Chat, Microsoft 365 Copilot — ran almost entirely on OpenAI models. The Build 2026 announcement is Microsoft's public declaration that it is building a parallel, proprietary model stack. Every new MAI model is trained from scratch using "clean and appropriately licensed data, without distillation from third-party models" — language that directly addresses the intellectual property concerns that have accompanied third-party model licensing. The distribution strategy is equally deliberate. Microsoft is not routing MAI models exclusively through Azure. MAI-Thinking-1 and MAI-Code-1-Flash are available via Fireworks AI, Baseten, and OpenRouter — three infrastructure providers that collectively reach developers who explicitly do not want cloud vendor lock-in. This signals a platform-first posture: Microsoft wants MAI to become a model ecosystem, not just an Azure feature. MAI-Thinking-1: The Reasoning Flagship MAI-Thinking-1 is Microsoft's answer to Claude Opus 4.x and GPT-5.5 on the reasoning side of the model spectrum. The architecture is a 35-billion-parameter active / approximately 1-trillion-parameter total sparse Mixture of Ex

A user picks a video from Photos. The app turns that video into a file the server can accept. Then it uploads the file. On the surface, this sounds like a simple upload flow. In practice, iOS makes you answer a much more specific question: How do you reliably turn a video from the user's Photo Library into an uploadable MP4 file? At first, I used AVAssetExportPresetPassthrough . It looked like the right default. It preserves the original media as much as possible, avoids unnecessary re-encoding, and is fast when it works. No quality loss, less CPU usage, less battery cost. But some videos failed during export. The error was usually in the AVFoundationErrorDomain Code=-11838 family. Apple describes this error as operationNotSupportedForAsset : an operation was attempted that is not supported for the asset. At first, I suspected an iCloud download issue, a Photos permission edge case, or something retryable inside PHImageManager . That was not the real problem. The actual problem was more fundamental: I was trying to write an iPhone MOV asset into an MP4 file using a passthrough export. The Original Flow The original code was roughly shaped like this: PHImageManager . default () . requestExportSession ( forVideo : asset , options : options , exportPreset : AVAssetExportPresetPassthrough ) { exportSession , info in exportSession ? . outputURL = outputURL exportSession ? . outputFileType = . mp4 exportSession ? . exportAsynchronously { // upload } } The intention was reasonable: Ask Photos for an export session for the PHAsset . Use AVAssetExportPresetPassthrough to preserve the original quality. Write the result as an .mp4 file for upload. Many videos exported successfully this way. That is what made the bug confusing. Some videos worked. Some did not. The hidden assumption was: Any iPhone video can become an MP4 file through a passthrough export. That assumption is not always true. iPhone Videos Are Usually MOV Files To a user, it is just "a video." Internally, an iPh

One hardware announcement and several software highlights from Microsoft Build.

Privacy-First Personal Finance for iOS Your finances. On your phone. Nowhere else. A privacy-first personal finance app that connects your banks, brokerage, and investment accounts into one unified dashboard — entirely on-device, no backend, no account required, no subscription. View on GitHub At a Glance 🏦 Multi-source 🔒 100% On-device 📊 Full picture Banks, Revolut, Trading 212 and more No server. No account. Your data stays in your Keychain. Net worth, spending, investments — all in one place Screenshots Log Insights Budget Transaction Entry Settings About Escudo Built out of two frustrations: every decent finance app costs a monthly subscription, and none of them support Trading 212. Escudo connects your banks, brokerage, and investment accounts and gives you a single view of your net worth, spending, and investments — without your data ever leaving your phone. Key Features Net worth dashboard — aggregated balance across all accounts and investment portfolio P&L Unified transaction log — every account in one feed, auto-categorised Spending insights — breakdown by category and trends over time Budget tracking — per-category budgets with visual progress dials Multi-currency — EUR, GBP, USD with stored exchange rates Recurring transactions — template-based recurring transaction engine Shortcuts support — deep linking via escudo:// URL scheme Integrations Source Method Trading 212 REST API — portfolio, orders, dividends Revolut Enable Banking OAuth 2.0 Bankinter PT Enable Banking OAuth 2.0 SIBS SIBS Open Banking (PT market) CSV import Revolut & Bankinter statements All credentials live in the iOS Keychain — never in UserDefaults, never in iCloud, never on a server. Known Limitations Enable Banking does not expose credit card accounts — only bank accounts and transactions are available through the PSD2 API; credit card balances and transactions are not accessible No token auto-refresh for Enable Banking — manual re-auth when tokens expire Categorisation rules are hard

The LedgerSync pipeline was inserting 1.5 million rows into PostgreSQL using pandas.to_sql() . It took four minutes per run. I switched to psycopg2's COPY command and it dropped to 18 seconds. Same data, same schema, same machine. That is not an optimization tip. It is the difference between a pipeline that fits in an Airflow schedule and one that does not. This article is about patterns like that: the ones that matter when you are building pipelines that run on a schedule, not when you are writing ad-hoc queries. Loading Data: to_sql vs execute_values vs COPY There are three ways to write rows from Python into PostgreSQL, and the performance gap between them is significant. pandas to_sql issues one INSERT statement per row by default, or a multi-row INSERT with method="multi" . It is the easiest to write and the slowest for any serious volume. psycopg2 execute_values batches many rows into a single multi-row INSERT VALUES statement. About 5x faster than to_sql for medium-sized loads. psycopg2 COPY streams rows directly to PostgreSQL using its native bulk-load protocol. No statement parsing, no row-by-row overhead. For LedgerSync at 1.5M rows, this was the one that mattered. import psycopg2 import io import pandas as pd conn = psycopg2 . connect ( " host=localhost dbname=proj_db user=proj_user password=proj_pass " ) def bulk_copy ( df : pd . DataFrame , table : str , columns : list [ str ]): buf = io . StringIO () df [ columns ]. to_csv ( buf , index = False , header = False ) buf . seek ( 0 ) with conn . cursor () as cur : cur . copy_from ( buf , table , sep = " , " , columns = columns ) conn . commit () print ( f " Loaded { len ( df ) } rows into { table } " ) Use COPY for initial loads and large backfills. For incremental daily writes of a few thousand rows, execute_values is fine and gives you more control over conflict handling: from psycopg2.extras import execute_values def bulk_insert ( rows : list [ dict ], table : str ): if not rows : return columns = list