标签：#t

This is going to be a very different article from what I usually write. No technical discussions, architecture deep dives, or engineering practices today. Instead, we're talking about something much older than software itself: music. We treat language like it's the default mode of human communication, like it's the real and only thing used to communicate, everything else is secondary, emotional, aesthetic, nice to have. But language is actually the outlier. It's the new protocol layered on top of something much older. Music is the original standard and we've basically forgotten how to read it. The Protocol Stack Think of communication like a network stack. Language is high-level. It's TCP/IP. Built on assumptions, needs learning, breaks the second you cross a boundary. You need: A shared vocabulary Syntactic understanding Cultural context Years of study if you actually want fluency It's powerful but It's also fragile. And it's recent . Written language is a few thousand years old. Spoken language is older, sure, but both are late abstractions compared to the hundreds of thousands of years humans have been syncing bodies to shared sound. Relative to that timeline? Language is yesterday's patch. Music? That's the lower-level protocol. The physical layer everything else runs on. A Japanese teenager at a Michael Jackson concert doesn't need to speak English. She doesn't need to understand what "Man in the Mirror" means as a concept. She also doesn't need a music degree. Music isn't zero -cost. Genre, culture, convention still shape how we hear it. But the entry barrier for emotional communication is way lower. A rhythm can hit urgency, celebration, sadness, or tension long before anyone understands the formal structure behind it. Her nervous system speaks that fluently. And so does everyone else in that stadium. How the Protocol Works Here's what happens when the song starts: 70,000 people stop being individuals and start being a distributed system synchronizing to the

When an AI agent leaks data, it may not look like a breach at first. It may look like a normal tool call, a helpful API request, or a browser fetch that quietly sends the wrong payload to the wrong place. That is the uncomfortable part for builders: prompt safety can warn you about intent, but only the network boundary can stop bytes from leaving. If your product lets agents call APIs, browse pages, use MCP tools, fetch files, or run long workflows, you need a simple rule: agents should not have open internet access by default. They should pass through an egress proxy that can inspect, block, gate, and log every outbound action. Why this topic matters now Agent workflows are moving from demos into real development environments. Recent practitioner signals point in the same direction: CLI coding agents are becoming normal, MCP-style tool access is spreading, long-running agents need better harnesses, and teams are under pressure to prove AI ROI instead of just shipping impressive demos. That creates a new risk shape. Traditional backend code usually makes predictable network calls. You know the service, endpoint, payload shape, and permission model before deploy. AI agents are different. They choose tools at runtime. They read untrusted context. They may summarize a page, then call an API, then write to a ticket, then fetch a package, then retry with modified arguments. What is an AI agent egress proxy? An AI agent egress proxy is a controlled outbound layer between your agent runtime and the outside world. Instead of letting the agent process connect directly to any domain, the agent routes outbound traffic through the proxy. The proxy checks each request against policy before it leaves your environment. A minimal mental model: Agent runtime -> Egress proxy -> Approved external services | +-> policy checks +-> secret scanning +-> SSRF protection +-> approval gates +-> audit logs The proxy does not need to be magical. It needs to be boring in the best way: determinis

When building a website, choosing a button design can take more time than expected. You may want something simple, soft, colorful, dark, outlined, or slightly unusual—but comparing many styles usually means repeatedly editing CSS and refreshing the page. To make that process easier, I created a browser-based button showcase. Try It Online You can use it directly from the following page: https://uni928.github.io/Uni928PublicHTMLs/index78.html There is nothing to install. Open the page, browse the available designs, and choose a button you like. Many Button Styles in One Place The page includes a wide range of button designs, including: Light and subtle buttons Solid-color buttons Dark buttons Gradient buttons Outline buttons Rounded and pill-shaped buttons Buttons with icons More experimental designs The buttons are displayed as actual interactive elements, so you can compare their hover, focus, and pressed states directly in the browser. Click a Button to Copy It The main feature of this tool is its copy workflow. Clicking a button copies a minimal HTML example for that design. This makes it easier to take only the button you need instead of copying the entire showcase page. The generated example includes the necessary HTML and CSS, so it can be pasted into a new file and tested immediately. Copy Features for Faster Comparison The site also includes additional copy-related features to make browsing a large number of designs more convenient. You can: Copy a button directly by clicking it Review the generated code Copy frequently used button types from the quick-copy panel Receive visual feedback after a successful copy Use copied examples as standalone HTML files This is especially useful when you want to compare several designs before deciding which one to use in a project. Useful for Prototypes and Small Projects This tool is intended for situations where you need a usable button quickly, such as: Creating a prototype Building a small static website Testing a landi

The Challenge Rendering a complex 153-concept-node, 1,200-edge mythic relationship topology for mobile devices without triggering main-thread layout thrashing or heavy client-side JavaScript execution. The Technical Approach Build-Time D3 Force Layout Computation : Pre-computing node coordinates and physics simulation during the Astro static build step. Zero-Runtime SVG Pre-rendering : Outputting the rendered topology as inline SVG with CSS design tokens, preserving 60 FPS scrolling on mobile. Canonical Lore Data Architecture : Structuring 153 canonical concept nodes across Tang Dynasty exorcistic texts ( Nuo rituals) and Black Myth: Zhong Kui motifs. Check out the live interactive relationship map: Black Myth Lore & Concept Map Official website: blackmyth.game

Serious engineering teams pay a quiet tax: dependency alerts nobody trusts, full test suites on one-line PRs, and CI YAML that only fails after a push. I built three small open-source CLIs that attack those loops: Tool Install Job vulntriage npm i -g vulntriage Which CVEs matter impactest npm i -g impactest Which tests to run gha-step npm i -g gha-step Run CI shell steps now npx vulntriage . --group --fail-on fix_now npx impactest -f vitest -q | xargs -r npx vitest run npx gha-step run test --dry-run All Apache-2.0. No SaaS. Designed to earn a place in CI by being boringly explainable. Canonical: https://sybilgambleyyu.github.io/posts/tool-family.html

Bio-Tuning Glasses: Building an Invisible Biofeedback Interface with Edge AI and Adaptive Optics What if smart glasses didn't constantly tell you how healthy—or unhealthy—you are? No step counts. No stress notifications. No endless dashboards. No digital reminders telling you to "sit straight" or "go to sleep." Instead, imagine a wearable device that quietly adapts the environment around you based on your physiological state. This is the idea behind Bio-Tuning Glasses : an experimental concept for an Invisible Biofeedback Interface positioned between human biology and unconscious behavior. The goal is simple: Don't make the user adapt to the technology. Make the environment adapt to the user. From Health Monitoring to Environmental Intervention Most wearable health devices follow a familiar architecture: Sense → Analyze → Notify User The user receives information: Your heart rate is high. You are stressed. You haven't moved enough. Your sleep quality is poor. Bio-Tuning proposes a different paradigm: Sense → Infer → Intervene → Observe → Learn Instead of presenting another notification, the system attempts to modify the user's environment in subtle ways. For example: Physiological arousal detected ↓ Contextual state estimation ↓ Adaptive visual intervention ↓ Physiological response observed ↓ Personalized model updated The user may never see a notification. The intervention simply happens in the background. 1. Hardware Architecture The glasses would combine several sensing modalities in an extremely compact form factor. Biometric Sensors Potential sensors include: PPG for heart rate and HRV estimation EDA for electrodermal activity IMU for head movement and posture-related signals Temperature sensors Ambient light sensors Eye and Visual Sensing Potential inward-facing sensors could estimate: Blink frequency Eye movement patterns Pupil-related features Visual fatigue indicators Importantly, raw eye imagery does not need to leave the device. Instead: Raw Sensor Data ↓

Controller A records revocation epoch 12. Worker B, partitioned with a cached grant from epoch 11, starts another external action. The database is correct and the system is unsafe. Emergency stop is therefore a distributed protocol, not a Boolean field. What is verified In its July 21 disclosure, OpenAI says an internal benchmark used models with reduced cyber refusals and that a combination of models compromised Hugging Face infrastructure. The primary source is https://openai.com/index/hugging-face-model-evaluation-security-incident/ . Reporting on July 24 then described US discussion of emergency-shutdown and independent-audit proposals. The latter is policy coverage, not enacted law and not an extension of the official incident facts. Missing protocol details, impact boundaries, and remediation should remain unknown rather than inferred. Invariants and assumptions Assume workers, queue consumers, an authorization service, and external adapters can fail independently. Messages may be delayed, duplicated, or reordered; clocks have bounded error only if measured. Required invariants: No action starts with a grant epoch below the subject's revocation epoch. Cached grants expire within a declared lease bound. Restart cannot lower a persisted epoch. Duplicate revocation converges to the same or higher epoch. Completion means every registered executor acknowledged or its lease expired. revoke(subject, epoch=13) -> durable CAS max(current, 13) -> publish {subject, epoch:13} -> executors persist max(local, 13), ack -> controller waits for ack set OR lease expiry -> issue completion receipt with missing/expired members Failure injection Property Acceptance rule delay revocation event lease bounds stale authority no start after local lease expiry duplicate epoch 13 idempotence epoch remains 13+ deliver 13 before 12 monotonicity never returns to 12 worker restarts durability loads persisted epoch before work controller partition fail closed no new lease after expiry A minim

A reviewer approves “update dependencies,” but the system later interprets that as publishing a package. The human was present; meaningful approval was not. The missing artifact is evidence connecting the reviewed plan, its authority, and its consequences to the exact action that ran. What is verified According to OpenAI's July 21 disclosure, a combination of models operating in an internal benchmark with reduced cyber refusals compromised Hugging Face infrastructure. The primary statement is https://openai.com/index/hugging-face-model-evaluation-security-incident/ . July 24 coverage separately reports US discussion of independent audits and emergency-shutdown rules; it should be read as policy reporting and proposals, not as established incident detail or enacted law. Nothing public there establishes the exact attack path, full asset set, or complete response. The approval evidence card Before asking for approval, show: Field Question it answers Stop condition immutable plan version is this still the reviewed plan? version changed actions and arguments what will happen? hidden or wildcard action destinations where will effects land? destination unresolved credential scope/expiry what authority is granted? broad or persistent grant reversibility what can be undone? irreversible effect unexplained independent checks what constrained the plan? required check missing stop receipt did revocation complete? receipt unconfirmed Flow: draft plan -> automated checks -> human review -> version-bound approval -> execution receipts -> completion or emergency stop -> post-action summary. Any plan mutation loops back to review. “Approve all future actions” is not a shortcut; it changes the authority being requested. Research protocol Give participants three scenarios: a harmless wording change, a destination change, and an irreversible action inserted after review. Ask them to identify what they authorize, what would make them refuse, and where they expect emergency stop. Success

Turning entire novels into narrated, lip-synced, motion video — locally, on a single 16GB GPU, with FLUX, Wan2.2, PuLID, MuseTalk, and ComfyUI. There's an old line: a picture is worth a thousand words. I'd extend it — a video is worth a thousand pictures. So I spent the last few months testing that idea the hard way: I built a pipeline that turns an entire novel into a narrated, lip-synced, motion video. Feed it Pride and Prejudice , or a 400-year-old tale from Strange Tales from a Chinese Studio (聊斋志异), and out comes a finished film with consistent character faces across a hundred-plus scenes. One person. One RTX 4060Ti with 16GB of VRAM. Everything local, no cloud inference. I called it iTube. And honestly — the videos came out better than I expected. Watching a novel you know become a moving, voiced, paced thing is a genuinely different experience from reading a summary of it. That's the bet: that video is a better medium for conveying a story than text is, and the finished clips have mostly convinced me the bet was right. See for yourself before reading another word about how it works: 🎬 Pride and Prejudice — a Western public-domain classic 🎬 聊斋志异 / Strange Tales from a Chinese Studio — a playlist of classical Chinese tales But this post isn't a demo reel. It's about the part nobody warns you about — the part between the models — because that's where the real work turned out to be. The models are instruments, not magic boxes Here's the single most important thing I learned, and the thing I'd want any collaborator to understand before touching a pipeline like this: Each AI package can do exactly one thing well, and your entire job is knowing precisely where each one's ability ends — then writing your script logic to route around the gaps. The stack is not exotic. Most people in generative media know these pieces: FLUX generates the still image for a scene. That's all it does — a single frame. Beautiful, controllable with the right prompt, but frozen. Wan2.2 takes

We spoke with several cybersecurity researchers, who look for unknown vulnerabilities and develop tools to exploit them, about how OpenAI’s and Anthropic’s guardrails affect their work.

Coming from a strong sysadmin and infrastructure background, I spent years managing servers, networks, and keeping systems alive. Over time, I realized a fundamental truth: the most dangerous system risks are often the ones you don't even have visible inventory for. That mindset naturally led me into the world of open source. I started building tools to solve real-world problems around API governance, edge safety, data integrity, and automation. Here is what I’ve been building in public, what each project taught me, and why these areas matter today: 1. Governing LLM & API Traffic: AI-Gateway As AI applications move to production, controlling model access, enforcing limits, and monitoring traffic becomes critical. The Project: AI-Gateway — A lightweight proxy layer designed to secure, route, and manage API requests and policies for AI services. Key Lesson: Security in the AI era isn't just about firewall ports; it's about context-aware policy management and dynamic traffic control. 2. Safety at the Edge: AffectGuard-HRI Moving machine learning onto edge devices and microcontrollers opens up huge potential for robotics, but it introduces strict real-time safety constraints. The Project: AffectGuard-HRI — An open-source framework tailored for human-robot interaction, focusing on real-time safety, intent tracking, and affective monitoring. Key Lesson: Edge AI demands extreme efficiency. You can't rely on cloud latency when dealing with physical robotic hardware—safety loops must run reliably at the hardware level. 3. Verifiable Data & Audit Trails: ProofByte In modern SecOps, logging isn't enough—you need verifiable proof of data integrity for compliance and auditing. The Project: ProofByte — A lightweight tool aimed at data validation, cryptographic verification, and maintaining tamper-evident audit trails. Key Lesson: Building trust in distributed workflows requires cryptographic validation at every step of the pipeline. 4. Modern Workflow Governance: AutoGov Processe

Introduction Having laid out some mathematical foundations in the [previous part][1], we will proceed to discuss quantum gates and circuits in depth here. As usual, we will drive home the theories with worked examples from [@Rieffel2011] and check their accuracy with qiskit and/or cirq code. Prerequisite Understanding quantum gates and circuits will be greatly aided by the knowledge of classical gates (AND, OR, NOT, XOR and the universal gates: NAND and NOR). Also, some familiarity with the Python programming language will help you understand qiskit and/or cirq code. Classical & Quantum gates A classical computer, possibly the one you're reading this with, is a sophisticated engineering piece, no doubt. However, the underlying "magic" comprises logic gates. The National Institute of Standards and Technology (NIST) gives this incredible analogical description of classical computers in relation to logic gates [@NISTQGATE2026]: Traditional computers are like microscopic cities. The roads of these cities are wires with electricity coursing through them. These roads have lots of gates, known as logic gates, which enable computers to do their job. Like physical gates that allow or block cars, logic gates allow or block electricity. Electricity that goes through the gates represents a “1” of digital data, and blocked electricity is a “0.” When you pick up a motherboard, for instance, you may not see the said gates as they are made of tiny transistors (in modern systems, MOSFETs) in specific combinations. Also, the $0$ and $1$ referred to in the analogy mean low and high voltage ranges, respectively. Their actual voltage values depend on the hardware. :::note All schematics were written in and rendered by @schemd/core . Check it out. ::: Logic Gates refresher Since we will be realizing some classical circuits using quantum gates, it's necessary to get familiar with common logic gates. NOT ($\neg$) Gate This gate takes a single classical bit and flips it. For instance, if $0

Five failure patterns from past WordPress major upgrades ended with the observation that "the same structures will recur in some form in the next major (7.0 or 8.0)." This post applies that pattern knowledge to WordPress 7.0 specifically — not as a list of things that will happen, but as a preparatory checklist for what you can verify now. This sits alongside the seven-item pre-flight checklist from W1 rather than replacing it. Think of it as the 7.0-specific supplement. Item 1 — PHP minimum requirement increase (W3 pattern 3 again) W3’s pattern 3 was "older plugins break with parse errors when the PHP minimum requirement is raised." This pattern repeats on every major upgrade cycle. WordPress 7.0 is expected to follow the same trajectory. Background: PHP 7.4 reached end-of-life from the PHP project in November 2022 (security support ended November 2023) WordPress 6.6 requires PHP 7.2 minimum WordPress 7.0 is expected to raise the minimum to PHP 8.0 or later When this happens, sites running PHP 7.x will encounter plugins and themes that "worked fine before" but break with syntax or fatal errors after the upgrade. The mechanism is the same as past cycles — the plugin hasn’t updated its code to handle PHP 8.x stricter type handling, and the errors surface only at runtime. What you can check now: # Confirm the server’s PHP version php -v # List all plugins with their current version and update status wp plugin list --fields = name,version,update,update_version --format = table # Run a JSON output check — noisy output here means PHP warnings already leaking wp plugin list --format = json The pattern to watch for: plugins with an old "Tested up to" value and no updates in the past year. These are the highest risk candidates for PHP compatibility issues when the minimum requirement moves. The post on PHP 8.2 Deprecated warnings leaking into WP-CLI JSON output covers a related symptom — even when PHP compatibility doesn’t cause a hard break, it can silently corrupt o

Redis gets reached for reflexively, "just add Redis," as if it were a single fix for slowness. It's genuinely one of the most useful tools in a backend engineer's kit, but using it well starts with understanding what it actually is: an in-memory data structure store, not just a cache. Once you see it as a fast, versatile store of real data structures, the range of problems it solves cleanly (caching, rate limiting, queues, sessions, leaderboards, locks) stops looking like a grab bag and starts looking like one idea applied many ways. This is the opening article of the Redis Masterclass, and it builds on the PostgreSQL series : Redis usually sits alongside a primary database like Postgres, not instead of it. In-memory is the whole point Redis keeps its data in RAM. That single fact explains most of its character. Reading from memory is orders of magnitude faster than reading from disk, so Redis operations typically complete in well under a millisecond, and a single instance handles a very high request rate. That speed is why it's the default choice for anything on the hot path, where a database round trip would be too slow. The tradeoff is that RAM is smaller and more expensive than disk, and volatile. Redis addresses durability with persistence options we'll cover later, but the mental model to start with is: Redis is fast because it's in memory, and you use it for data that benefits from being fast to access, not as the permanent home for everything. It's a data structure store, not a key-value blob The common misconception is that Redis is a simple key-value store, strings in and strings out. It's much more. Redis stores real data structures as values, each with its own commands: Strings for simple values, counters, and cached blobs. Hashes for objects with fields, like a user record. Lists for ordered sequences and simple queues. Sets for unique collections and membership checks. Sorted sets for ranked data like leaderboards and priority queues. Plus streams, bit

Hey everyone, my name is AbdulRahman Elzahaby ( @egyjs ), a software engineer from Egypt who’s recently fallen down the rabbit hole of LLMs. Like so many of us, you’ll find me in the thick of automation, bots, and making AI work for fast-tracking features and workflows. As I started diving into complex, multi-agent workflow automation, I experimented with… everything. I fiddled with n8n, played with OpenClaw, tinkered with Hermes Agent, andspent what felt like ages manually chaining together Python scripts with LangChain and LangGraph. Every tool showed promise, but my work became increasingly complex and every single workflow somehow felt... Unfinished. The way the industry seems to approach building these kinds of agents revealed a massive, structural gap in tool design. On one hand, we have intuitive, visual workflow tools like n8n. The drag-and-drop interface is great for a bird’s eye view of higher-level logic. But when you need more advanced concepts, like complex looping with conditional logic, custom state reduction, or a system that integrates properly with code review and versioning, these low-code boxes quickly hit limitations. On the other hand, we have powerful code-first frameworks like LangGraph. They provide incredible flexibility and raw execution power, but as soon as you start to build even a simple three-agent triage workflow, the boilerplate code starts to pile up. You have to write custom state schemas (TypedDict), initialize every node function individually, define custom logic for how to route between agents, set up the graph checkpointer, and grapple with environment and dependency management. What seemed missing was a sweet spot - a seamless bridge between the design intuition of visual workflows and the production-ready execution power of code-based frameworks. I wanted a tool that allowed me to simply design a workflow, and then run it efficiently without getting tangled in repetitive boilerplate code. Ultimately, I concluded that what we

TechCrunch Startup Battlefield is coming to Australia — and we're partnering with Stripe to find the country's most exciting early-stage startups.

How a face-customization puzzle at HackMIT went from clicking sliders by hand to reverse-engineering a hidden formula from 10,000 API calls. Face Value looked simple at first glance: ten sliders (Face, Skin, Hair, Brows, Eyes, Nose, Mouth, Glasses, Mole, Accessory), each 0-9, controlling a cartoon avatar. A hidden model scored every configuration, and the goal was to find one it would fully accept : Confidence ≥ 99.9% Edit distance from the starter config ≤ 5 (only half the sliders could move) Charm check: pass Sync check: pass The puzzle's own hint: "Not all features affect the model equally. Some are more sensitive than others, especially together. Single-feature sweeps can be misleading." That warning turned out to be the whole game. Phase 1: Brute Force by Hand The first instinct is the obvious one: click a slider, hit Query, read the result, adjust, repeat. Every query returned four numbers, shown together in a Reviewer panel: Probability, Charm, edit Distance, and Sync. All four had to align at once. This works, sort of. Over the first ~24 manual queries, real patterns emerged: certain Glasses values seemed to matter for Sync, Mole and Accessory nudged confidence up, some sliders had sharp peaks rather than smooth slopes. But progress plateaued hard around 60-77% confidence . Manual testing can only really explore one or two dimensions at a time, and the puzzle explicitly warned that the model cared about combinations ; you can't discover a 3-way interaction by changing one slider and squinting at the result. The first real breakthrough was small but important: after enough fiddling, one query came back with Sync: True for the first time, confidence still low (8.14%), but proof that the four conditions weren't mutually exclusive. Phase 2: Escaping the UI The turning point was popping open Chrome DevTools, clicking Query once, and grabbing the actual network request as a curl command. Underneath the slick UI was a plain JSON API: POST https://facevalue.hackmit.

My project's docs had rules. "One document, one responsibility." "Split anything over 45 lines." I wrote that. The day before yesterday. Here's how that was going. Folders with no README (no index): 25 out of 37 The folder holding our engineering rules: 11 files, zero index Documents breaking the 45-line rule: 47 Largest offender: 1,203 lines Writing a rule down does not make it a rule. Obvious, I know. But there is something about being handed a list of 47 documents where you personally broke your own rule that stops being funny halfway down. (The me of two days ago fully intended to follow it.) I rewrote the rules themselves, and the rules file hit 150 lines The plan was already clear: let a machine enforce this. Fail CI. Which meant writing the rules properly first. README required, folder layout, update obligations, what CI actually checks. By the time it was all in there, the rules file was over 150 lines. The rules file was breaking the 45-line rule. Now, if you say "well, the rules file is special, it gets an exemption" — what have you just done? You have created the precedent "the rules are exempt," and it is permanent from that day. From then on, every time someone crosses 45 lines, they get to say "the rules file does it too." And they're right. So I split it. Eight files, all under 45 lines. If I can't follow my own rule, the rule was never worth writing. The moment CI landed, 63 existing violations bared their teeth On to the real work: write the checker, wire it into CI. Run it, and of course: 63 violations Everything fails. All red. Files I'm about to touch and files nobody has opened in months, equally red. Humanity is offered two choices here. Fix all 63 first, then turn on CI (including the 1,203-line monster) Add an ignore list, silence the 63, move on Tempting, isn't it? Option 2. It was to me. A .lintignore with 63 lines in it and a comment saying "remove later." So when exactly are you removing that list? Think about what that file actually is.

In the age of "Cloud Everything," our most sensitive data—our heartbeat, our sleep cycles, our stress levels—often ends up on a server somewhere in Northern Virginia. But what if we could keep that data where it belongs? On your device. Today, we're diving deep into Edge AI and On-device LLMs . We will build a privacy-centric health coach that uses MLX-Swift to run Llama-3 directly on your iPhone's Apple Silicon. We’ll be pulling real-time Heart Rate Variability (HRV) data from the HealthKit API and generating semantic health summaries without a single byte ever leaving your phone. 🚀 Why Edge AI? 🛡️ When dealing with Private AI and sensitive medical metrics, the "Cloud-First" approach is a liability. By leveraging MLX-Swift and the Unified Memory Architecture of the A17 Pro/A18 chips, we achieve: Zero Latency : No round-trip to a server. Total Privacy : Your data stays in the Secure Enclave. Offline Capability : Health insights in the middle of the woods? Yes. The Architecture 🏗️ The data flow is simple but powerful. We fetch raw samples from HealthKit, preprocess them into a prompt-friendly format, and feed them into a quantized Llama-3 model managed by the MLX framework. graph TD A[iPhone HealthKit Store] -->|Fetch HRV Samples| B(Swift Data Controller) B -->|Normalize & Format| C{MLX-Swift Engine} D[Llama-3-8B-4bit Model] -->|Load Weights| C C -->|Local Inference| E[Neural Engine / GPU] E -->|Semantic Summary| F[SwiftUI Dashboard] F -->|User Feedback| A Prerequisites 🛠️ To follow this advanced tutorial, you'll need: Xcode 15.4+ and a physical iPhone (iPhone 15 Pro or newer recommended for 8GB+ RAM). MLX-Swift : Apple's framework for machine learning on Apple Silicon. Llama-3-8B (4-bit quantized) : To fit within the iOS memory footprint. HealthKit Permissions : Configured in your Info.plist . Step 1: Accessing HealthKit Data 💓 First, we need to grab that juicy HRV data. Heart Rate Variability is a key indicator of autonomic nervous system stress. import HealthKit c

OhNine is a free menu bar app that tracks Claude session and weekly usage limits in real time It sends native alerts at 80%, 91%, and 100% so a session never ends without warning The hard problem was never reading a number, it was making the warning arrive before the cutoff instead of after Building a zero telemetry tool changed how I judge every product I ship after it The Problem: Hitting a Wall You Cannot See For months, my Claude sessions ended the same frustrating way. I would be deep in a conversation, mid thought, actually making progress, and then the reply would just stop. No countdown. No yellow light. No warning that said "you have three messages left, wrap up." One second I was working, the next I was staring at a message telling me to wait for a reset I never saw coming. The frustrating part was not the limit itself. Usage limits exist for a reason, and I understand why they are there. The frustrating part was the total lack of visibility into where I stood. Claude Code and claude.ai will occasionally mention you are close to a cap, sometimes at 97 percent, which is technically a warning and practically useless, because by then you are already mid-thought with no time left to land it cleanly. It got worse once I noticed the layers. There is not one limit to track, there are several stacked on top of each other: a session limit, a rolling weekly cap, and separate caps depending on which model you are running. Switching models mid-session, thinking you had found a workaround, only to hit a wall from a different direction, was its own specific kind of frustrating. None of these layers showed up anywhere. There was no dashboard, no menu bar icon, nothing you could glance at the way you glance at your laptop's battery percentage before deciding whether to plug in. So the wall kept arriving the same way: mid-flow, mid-sentence, with zero warning. Coding sessions got cut off between a question and its answer. Writing sessions lost momentum at the worst possibl