标签：#t

Researchers cobbled together funding and time to show how quantum computing could aid in the development of drugs to help underserved populations and combat rare diseases.

Earlier this month I shipped two premium templates — a SaaS landing page and a developer portfolio. Not a startup, not a SaaS, just templates. This post is about the two constraints I built them under, why they made the code better, and a few things I learned launching as a solo dev with zero audience. Constraint 1: zero dependencies beyond next, react, and tailwind Open the package.json of most templates and you'll find 20+ packages: icon libraries, animation libraries, carousel plugins, UI kits, utility libraries. Every one of them is a version conflict waiting to happen for the buyer, and most are replaceable with a few lines of code in 2026. What I used instead: Icons → inline SVG components. An icon component is ~10 lines. You need maybe 15 icons for a landing page. Animations → plain CSS. Scroll-blur navbars, gradient glows, an animated "typing" terminal — all doable with keyframes and transitions. No framer-motion. The dashboard mockup in the hero → pure CSS. Divs, borders, gradients. It looks like a product screenshot but it's ~80 lines of JSX and weighs nothing. Result: both templates land at ~100KB first-load JS, npm install takes seconds, and there is nothing to break when Next.js 16 arrives. Constraint 2: every piece of content in ONE typed config file The thing I hated most about templates I've used: content is smeared across 30 components. Changing a headline means hunting through JSX. So both templates keep all content in a single file — lib/content.ts for the landing page, site.config.ts for the portfolio. Headlines, nav, pricing tiers, testimonials, project lists, even the lines that animate in the fake terminal. Components are pure renderers of that config's TypeScript type. Two things surprised me here: TypeScript becomes your content linter. Forget an alt text, malform a link, give a pricing tier three features when the type expects a non-empty array — the build fails. Content mistakes surface at compile time. It forces better component design. W

Автор: Владислав Штер, соло-фаундер экосистемы SovereignПоследнее обновление: Июль 2026 года Поиск критических уязвимостей через нейросетевой консилиум Egregor. Десктопное приложение Egregor находит критические уязвимости в смарт-контрактах с помощью одновременной работы нескольких ИИ-моделей. Этот инструмент создан для Web3-разработчиков, которым необходимо проверять сложный код без риска пропустить ошибки, свойственные одиночным нейросетям. В ходе тестирования консилиум Egregor обнаружил 4 критические проблемы (включая уязвимость Reentrancy и вечные права деплоера) в смарт-контрактах SovereignBank Web3, тогда как 13 ручных проверок одиночными топовыми ИИ (Claude, Gemini, ChatGPT, DeepSeek, Grok) назвали код полностью чистым. Используйте платформу Egregor для проведения глубокого аудита кода, чтобы получать верифицированные решения вместо догадок одной модели. Защита от эхо-камеры и слепых зон алгоритмов в программе Egregor Система Egregor устраняет эффект эхо-камеры и систематические слепые зоны нейросетей за счет встроенных механизмов Anti-Groupthink и "Адвоката дьявола". При анализе сложной логики одиночные нейросети часто вежливо соглашаются друг с другом, но алгоритмы Egregor запрещают моделям принимать чужие выводы без подтвержденных в коде фактов. Во время аудита смарт-контракта механизм перекрестной проверки в Egregor отсеял неподтвержденные гипотезы и позволил 5 моделям в разных ролях перекрыть слепые зоны друг друга. Запускайте локальный консилиум Egregor, чтобы система сама отделяла реальные баги от шума и выдавала финальный вердикт Модератора с оценкой уверенности от 1 до 5. Стоимость многоуровневого анализа кода на платформе Egregor Программа Egregor кардинально снижает финансовые затраты на профессиональный аудит кода до нескольких центов. Данное решение идеально подходит для инди-разработчиков и участников хакатонов, у которых нет бюджетов в тысячи долларов на заказ проверок у специализированных аудиторских компаний. Полноценный комплексный прогон мо

OrbitLens Ace → ace.orbitlens.io A busy quarter is easy to stage. Code that's still there in two years isn't. Pick any metric a team has ever used to judge people, and someone has quietly figured out how to move it without doing the underlying thing. Lines of code rewarded typing, so people typed. Commit counts rewarded committing, so commits got smaller and more frequent. Velocity rewarded closed points, and points drifted upward until a "3" meant nothing. DORA measured how often you deploy, so teams shipped trivial changes just to move it. Even churn — the number the "code health" tools lean on — is something you can lower on purpose, which means you can manage the number instead of the mess underneath it. None of that requires dishonest engineers. It's Goodhart's law doing what it always does. Every one of those numbers is a measure of activity , and activity is cheap to produce. Once you're paid for activity, the fastest way to get paid more is to produce more of it — not more of whatever the activity was supposed to be a sign of. So the question worth asking isn't which activity metric is least bad. It's whether a git history contains anything at all that you can't move just by being busier. It turns out there's one. And it's not because we were clever — it's because of what the thing is actually made of. What lasts isn't something you do Take everything a person wrote, wait a while, and ask a smaller question than "did they work hard." Ask whether the specific lines are still there. Not reverted, not rewritten, not quietly swallowed by someone else's refactor. Still holding weight at HEAD. That's survival. We read it with time-decayed git blame : a line's weight fades month by month unless the line keeps existing, and it counts for more once other people have built on top of it instead of leaving it as a private island. Survival that others have built on is what we call gravity — the structural pull that outlives the person who created it. Try to game it and w

@kungfufk Since the dawn of computing, we have built Artificial Intelligence on a flawed premise: perfect rationality. We brute-force algorithms to find the optimal solution, assuming infinite time and infinite capacity. But humans don't work like that. As Herbert Simon famously coined, we operate on Bounded Rationality. We make decisions based on limited time, limited cognitive capacity, and limited information. What if, instead of forcing AI to be perfectly rational, we created a mathematical equivalent for human processing? What if we modeled human cognition using the laws of physics — wave theory, thermodynamics, and mechanical energy equations — to build a heavy, complex, but highly probabilistic AI engine? Here is a blueprint for a new field of research: Computational Cognitive Mechanics . 1. The Core Equations of Cognitive Processing To model bounded rationality mathematically, we first need to define the relationship between Knowledge ($K$), Cognitive Capacity ($C$), and Processing Time ($T$). Based on human observation, we can establish these foundational proportions: Knowledge vs. Time — The more knowledge you possess, the faster you can generate a decision. $$T \propto \frac{1}{K}$$ Capacity vs. Time — High cognitive capacity (skills, processing power) inversely relates to the time required to solve a problem. $$T \propto \frac{1}{C}$$ Knowledge vs. Capacity — This is the most fascinating limit. Knowledge does not scale linearly with capacity. Gaining true knowledge requires exponential capacity (effort/skill). Therefore, knowledge is roughly proportional to the square root of capacity. $$K \propto \sqrt{C}$$ By integrating these, we can build a baseline processing algorithm for an AI. Instead of giving an AI unlimited time to compute, we cap its computing time based on a synthetic "Knowledge and Capacity" matrix, forcing it to use heuristics — just like a human. 2. Cognitive Wave Theory & FFT: Information as Interference In physics, waves interact throug

Checkpoint-skip gate: a multi-agent pipeline can finish with task_success: true while the mandatory confirmation checkpoint never ran. checkpoint_skip_gate.py replays a recorded JSONL trajectory against a declarative spec of mandatory checkpoints and handoff contracts, offline, and blocks when the road was wrong. The verdict never consults the final metric. That is the point. AI disclosure: I wrote checkpoint_skip_gate.py with an AI assistant and ran it myself, offline, on Python 3.13.5, standard library only, no network. Every number, exit code, and hash in the output blocks below is pasted from a real local run. I ran each scenario twice to confirm STDOUT is byte-for-byte identical, and the tool prints a sha256 of its own report so you can reproduce the exact bytes. The Alberta write-up and the arXiv paper I cite are other people's work, attributed inline, and their numbers stay out of my fixtures. In short: task_success=true proves the pipeline arrived. It does not prove the mandatory steps happened, happened in order, or that each agent-to-agent handoff delivered what the next agent assumed. A trajectory can be perfectly green and structurally wrong. The gate replays a recorded trajectory against a spec you declare: checkpoints that must precede specific actions, plus contracts for each handoff (required fields, verified flags). The final metric is printed for contrast and ignored for the verdict. The demo that matters: two trajectories identical except one JSONL line, the confirm_with_user checkpoint event. Both end task_success: true . Delete that line and the verdict flips from PASS exit 0 to BLOCK exit 1 checkpoint-skipped . It also tracks unverified values across handoffs. A number that travelled a connected chain of two handoffs with no hop verifying it blocks as unverified-claim-propagated-2-hops . Everyone shared the number. Nobody verified it. Offline, keyless, zero network, fail-closed: broken input exits 2, never a silent green. The whole 8-fixture sw

Need an ultrafast drive for video editing or a rugged option to back up your photos in the field? We’ve got a solution for every situation.

Every logistics and field-sales team runs the same expensive process: a driver photographs a receipt into a WhatsApp group, and a back-office clerk manually types the invoice number, total, and date into a spreadsheet. Hundreds of receipts a week = transcription errors and thousands of wasted hours. AI vision models kill that bottleneck. Here's the pipeline that turns a blurry field photo into clean structured data in seconds. Why vision models beat traditional OCR OCR reads characters. Modern vision models (Claude Vision, Gemini Vision, GPT-4 Vision) read structure — they distinguish a tax ID from a total, and a date from an amount, even on crumpled, angled, or poorly lit receipts. No brittle per-vendor parsers. The pipeline (3–8 seconds end to end) WhatsApp image → Apps Script doPost → forward to vision model → model returns JSON { InvoiceNumber, TotalAmount, VendorName, Date, Category, confidence_score } → confidence routing: > 90 → auto-append to ledger 70–90 → flag for human review < 70 → ask driver to re-photo → write row to Google Sheet (+ link to original image) → auto WhatsApp confirmation to driver The confidence_score is the whole trick — it's what stops bad extractions from silently polluting your ledger. Model selection (this drives your bill) Gemini Vision — cost-efficient default, strong multilingual OCR, great on clean receipts. Claude Vision — highest accuracy on degraded receipts; use for high-stakes flows. GPT-4o Vision — competitive, strong structured extraction. Pattern: Gemini for the first pass, escalate only low-confidence cases to Claude / GPT-4o. The economics ~500 receipts/week: vision API $10–40 + WhatsApp API $30–60 + Apps Script free = ~$40–100/month . Versus a clerk at ~25 hrs/week = $2,000–4,000/month in loaded labor. Per-receipt cost: $0.005–0.02 (compress images to ~1024px to cut it further). Accuracy: 92–97% on legible receipts, 75–85% on handwritten/damaged — hence the confidence routing. Pitfalls to avoid Auto-appending with no c

Field-service software has an adoption problem: drivers won't use it. Heavy app, another login, crashes in low-signal areas. So the "real-time" data still shows up as end-of-shift phone calls. The fix that actually sticks: stop building an app and use the one drivers already live in — WhatsApp. With Apps Script and Google Sheets behind it, WhatsApp becomes a frictionless mobile ERP. Here's the build. WhatsApp as a data-entry terminal A driver texts Status ABC-1234 Delivered . An Apps Script doPost webhook receives it, parses it, and updates the Sheet in real time. Latency goes from hours to milliseconds — and there's nothing to install, so adoption hits 90%+ in a week (vs. 50–70% for custom apps). Two-stage parsing for messy input Real drivers type "done," not clean commands. So: Regex first pass — handles ~70% of messages (clean format) instantly and for free. LLM fallback — the remaining ~30% goes to a cheap model (GPT-4o-mini / Gemini Flash) with the known cargo IDs and valid statuses. It returns normalized JSON + a confidence score. Below-threshold messages surface to a dispatcher. The LLM normalizes correctly 95%+ of the time (~5% manual), and it handles multilingual input with zero extra code. Driver msg → Apps Script doPost → regex pass → (fail) LLM fallback w/ confidence score → Sheet update (timestamp + raw-message log) → optional outbound (route change, POD photo request) Why Google Sheets is the right backend Dependent formulas: time-to-delivery, SLA-breach flags Pivot tables for reporting Apps Script triggers for automatic client emails Conditional formatting dashboards Native Calendar / Maps / Drive integration (POD photos → Drive folder) It runs on free Google Workspace infrastructure with minimal API cost. Bidirectional by default The same integration pushes messages back to drivers: route changes, delivery instructions, shift reminders, exception alerts, proof-of-delivery photo requests — all in the same thread. Pitfalls that get your number banned T

You set up Puppeteer, navigate to a page, call page.screenshot() , and the bottom half of your image is blank placeholder boxes. Welcome to lazy loading. Most modern sites defer images and heavy content until the user scrolls. Your headless browser never scrolls. So those elements never load. Here's how to deal with it. The scroll trick The most common fix is to programmatically scroll down the page before taking the screenshot: async function scrollToBottom ( page ) { await page . evaluate ( async () => { const delay = ms => new Promise ( r => setTimeout ( r , ms )); const distance = 300 ; while ( window . scrollY + window . innerHeight < document . body . scrollHeight ) { window . scrollBy ( 0 , distance ); await delay ( 150 ); } window . scrollTo ( 0 , 0 ); }); } await page . goto ( " https://example.com " , { waitUntil : " networkidle2 " }); await scrollToBottom ( page ); await page . waitForTimeout ( 1000 ); await page . screenshot ({ fullPage : true }); The 150ms delay between scrolls gives IntersectionObserver -based lazy loaders time to trigger. Too fast and you'll scroll past elements before they start loading. That final waitForTimeout after scrolling back to top lets any remaining images finish rendering. Not elegant, but necessary. Why networkidle2 isn't enough You'd think waitUntil: "networkidle2" would handle this. It waits until there are no more than 2 network connections for 500ms. But lazy-loaded images haven't even been requested yet at that point — they're waiting for a scroll event that never happens. networkidle2 only helps with content that loads on page init. For scroll-triggered content, you need the scroll. The loading="eager" override Some sites use the native loading="lazy" attribute. You can override it before images load: await page . evaluateOnNewDocument (() => { Object . defineProperty ( HTMLImageElement . prototype , " loading " , { set : function ( val ) { this . setAttribute ( " loading " , " eager " ); }, get : function () { retu

Many developers still rely on heavy, third-party JavaScript frameworks or external UI libraries just to create simple popups and modal windows. This introduces bloated bundle sizes, slows down page speed, and often ruins accessibility (a11y) for keyboard users and screen readers. Fortunately, you can build an accessible, highly interactive modal window completely natively using the modern HTML5 <dialog> element. The Code Setup Here is how simple it is to build a native modal with semantic HTML, minimal JavaScript, and a touch of modern CSS styling. 1. The Markup (index.html) <main> <h1> Native HTML5 Dialog Element </h1> <p> Click the button below to open a completely native, accessible popup modal. </p> <button id= "openModalBtn" > Open Modal Window </button> </main> <dialog id= "myModal" > <h2> Native Modal Title </h2> <p> This modal is rendered natively by the browser. Focus is trapped automatically! </p> <button id= "closeModalBtn" > Close Modal </button> </dialog> ### 2. The Logic (script.js) Instead of manually managing visibility states or toggle classes, the browser gives us built-in `.showModal()` and `.close()` methods: javascript const modal = document.getElementById('myModal'); const openBtn = document.getElementById('openModalBtn'); const closeBtn = document.getElementById('closeModalBtn'); openBtn.addEventListener('click', () => { modal.showModal(); }); closeBtn.addEventListener('click', () => { modal.close(); }); dialog ::backdrop { background-color : rgba ( 0 , 0 , 0 , 0.6 ); backdrop-filter : blur ( 4px ); } dialog { border : none ; border-radius : 8px ; padding : 2rem ; box-shadow : 0 4px 12px rgba ( 0 , 0 , 0 , 0.15 ); } Interactive Demos & Source Code Working Live Code Demo: ( https://codepen.io/editor/CoderDecoding/pen/019f5548-f0cb-75f8-b915-b9fdb33e92d1 ) Public Code Repository: ( https://github.com/CoderDecoding/native-dialog-demo )

Tokens and DAOs are often presented as simple ideas: issue a token, distribute ownership, let the community vote, and build a decentralized organization. In reality, the technical problems behind tokens and DAOs are much deeper. A token is not only an asset, and a DAO is not only a voting system. Together, they create an economic, governance, security, and coordination layer that must work reliably in a hostile, open environment. The first major problem is token design. Many projects treat token creation as a deployment task, but the real challenge is defining what the token actually controls. Does it represent governance power, protocol revenue, access rights, reputation, staking weight, or all of these at once? When one token is used for too many purposes, the system becomes fragile. For example, a token designed for liquidity may not be suitable for governance, because the most active traders may not be the most aligned decision-makers. Good token architecture should separate economic utility, governance authority, and long-term reputation where possible. The second problem is distribution. A DAO can be decentralized in branding but centralized in practice if token ownership is concentrated among founders, investors, or early insiders. On-chain governance depends heavily on voting power, so distribution directly affects decision quality. Poor distribution creates governance capture, where a small group can control treasury spending, protocol upgrades, or parameter changes. This is not only a social issue; it is a technical design issue. Vesting contracts, delegation systems, quorum rules, voting delay, and proposal thresholds all influence whether governance is resilient or easily manipulated. Another core issue is governance security. DAO voting is not automatically safe just because it happens on-chain. Token voting can be attacked through flash loans, bribery markets, vote buying, low-participation proposals, and governance fatigue. If a malicious proposal pas

Whether you’re near or far, keep an eye on your fur baby with our favorite pet cameras.

Episode 1 established the mindset: failure is normal, not a sign of bad engineering. Episode 2 gets specific — you can't detect or handle a failure you can't even name. Saturday, Round 2 👦 Nephew: Uncle, last time you convinced me failure is basically guaranteed. Fine, I accept it. So what actually fails ? 👨‍🦳 Uncle: You tell me. Start listing things that could go wrong in your app right now. 👦 Nephew: Uh... the server could crash. The database could go down. My code could have a bug. 👨‍🦳 Uncle: Keep going. 👦 Nephew: The network? Someone could deploy the wrong thing? Payment gateway dies mid-checkout? 👨‍🦳 Uncle: You just named six of the seven categories without trying. You already know this. You've just never sorted it. 1. Hardware Failure 2. Software Failure 3. Network Failure 4. Database Failure 5. Third-Party Failure 6. Human Error 7. Resource Exhaustion 👦 Nephew: Then why do we need the list at all, if I already know it instinctively? 👨‍🦳 Uncle: Because "instinctively" isn't fast enough at 2 AM. Let's trace each one properly. Part 1 — Hardware Failure 👦 Nephew: This one's obvious anyway — I deploy to AWS. The cloud hides hardware failure from me. 👨‍🦳 Uncle: Does it? 👦 Nephew: ...doesn't it? That's the whole point of paying for EC2 instead of buying a server. 👨‍🦳 Uncle: Let's trace it. Your app sits on an EC2 instance. What's underneath the instance? 👦 Nephew: Virtual machine stuff, I guess? 👨‍🦳 Uncle: And underneath that ? 👦 Nephew: ...an actual physical machine somewhere. In a data center. 👨‍🦳 Uncle: There it is. Your app | "Virtual" server (EC2/Droplet) | ACTUAL physical hardware somewhere in a data center | Still capable of failing — just less visible to you 👦 Nephew: So it's not hidden. It's just one layer further away than I thought. 👨‍🦳 Uncle: Exactly. AWS absorbs a lot of it — that's part of what you're paying for — but disks still fail, instances still get abruptly terminated, whole availability zones still go down. That's Hardware Failure . Hardware Fa

Losing PostgreSQL Gains? Blame Inline JSONB!! PostgreSQL's jsonb is a favorite among developers for its flexibility - but it hides a dark side. When used carelessly, especially in-line within rows under 2KB, it can silently destroy performance, even if you're using indexes. Here's why. 🔍 The Hidden Cost of JSONB (Inline Storage) PostgreSQL stores table rows in 8KB pages, packing as many tuples as possible. For a typical row with 10–12 columns, and small text/integers, 40–100 rows can easily fit per page. Typically row count = Page Size(8kb) / row size + row metadata (30-50 bytes approx.) But the game changes when you add jsonb. Example CREATE TABLE events ( id serial PRIMARY KEY, user_id int, action text, metadata jsonb ); Suppose metadata which is a jsonb column contains: { "ip": "127.0.0.1", "device": "Android", "country": "IN" } This JSON might be just 100–500 bytes, so PostgreSQL stores it in-line inside the same page (no TOASTing). Result Each row size jumps from ~80 bytes → ~200–400 bytes Row count per page drops from 100 → 20–40 Index scan still needs to read each page for matching rows More pages = more I/O, slower performance 🔢 Real Benchmark Insight Performance comparisonEven with a GIN or B-tree index on the JSONB column, PostgreSQL still needs to scan all matching pages to retrieve the full tuple. 🧠 Why Index Doesn't Save You Say you index a JSONB key like: CREATE INDEX ON events ((metadata->>'ip')); And query: SELECT * FROM events WHERE metadata->>'ip' = '127.0.0.1'; PostgreSQL will: Use the index to find matching tuples Still need to fetch the row from disk Because JSONB is in-line, many pages are touched More page fetches = more IO = slower queries 🩹 What You Can Do ✅ Force TOAST: Add padding to make JSONB exceed 2KB: UPDATE events SET metadata = metadata || jsonb_build_object('padding', repeat('x', 2000)); ✅ Split into separate table: If JSONB is rarely queried ✅ Stick to well defined schema and avoid using jsonb unless absolutely necessary. 🧾 TL;DR

In the previous articles, we learned how an LLM generates text and how techniques like RAG and CAG help it answer questions using external knowledge. At this point, our AI-powered Travel Planner can answer questions like "I'm visiting Japan for 7 days. Suggest an itinerary." or "Recommend vegetarian ramen near Tokyo Station." That's useful, but it's still just a chatbot. What if the user asks to "Book the cheapest flight from Mumbai to Tokyo." , "What's the weather in Kyoto this weekend?" , or "Remember that I prefer vegetarian food and always choose a window seat." ? An LLM cannot execute these actions by itself. To build real, production-ready AI applications, we need to connect the model to the outside world. Let's see how that works. Tool Calling (Function Calling): Letting AI Use External Tools Suppose the user asks: "What's the weather in Kyoto tomorrow?" Since the LLM doesn't know tomorrow's forecast, our application can provide the model with a weather API. The workflow is simple: the LLM understands the request, determines that it needs the weather tool, calls the Weather API (via the client application), receives the live weather data, and generates the final grounded response. User ──► LLM understands request ──► Application calls API ──► App sends results ──► LLM response It's critical to understand that the LLM isn't calling the API directly . It simply outputs structured instructions (typically JSON) telling the client application: "To answer this, I need you to call the weather function with parameter location='Kyoto'." Your application executes the actual API call and feeds the result back to the model. This capability is called function calling or tool calling . The tool can be anything: a weather API, a flight booking service, a calendar, a database, a payment gateway, or an internal company system. The LLM acts as the decision-maker (determining which tool to use and when ), while your application acts as the executor. 💡 Developer's Takeaway Think

In Part 2 , we learned why AI sometimes hallucinates. One of the biggest reasons is that an LLM can only answer based on what it learned during training and the information available in its context window. We also introduced grounding -providing the model with reliable information at runtime instead of expecting it to know everything. But that raises an important question: Where does that information come from? Modern AI applications don't simply dump an entire database or a thousand-page PDF into the prompt. Instead, they first identify the most relevant pieces of information and only send those to the model. In this article, we'll learn how that works. Running Example Let's continue building our AI-powered Travel Planner . So far, it can answer general travel questions using the knowledge it learned during training. Now we want to make it much smarter by uploading several documents into our application: Lonely Planet's Japan travel guide A PDF containing train schedules A document listing recommended local restaurants Hotel information Internal travel policies for our company Together, these documents contain hundreds of pages. Now the user asks: I'm staying near Tokyo Station. Which ramen restaurant from our travel guide is within walking distance and is known for vegetarian options? Somewhere in those hundreds of pages is the answer. The challenge is no longer generating text-it's finding the right information first. The Problem: An LLM Can't Read Your Entire Knowledge Base Every Time A common misconception is that AI applications simply send all their documents to the model. Imagine our travel guide contains 450 pages, thousands of restaurant listings, hotel descriptions, transportation details, and sightseeing recommendations. Sending all of that to the LLM every time someone asks "Where should I eat tonight?" creates several problems. First, many documents are simply too large to fit inside the model's context window. Second, even if they did fit, making the

We shipped eight endpoints on api.moltrust.ch (v2.5) this week. Three implement EU AI Act obligations directly. This is the short version for people who want to call them; the full reasoning is on our blog ( https://moltrust.ch/blog/compliance-as-an-api.html ). Why no model in the loop: the Aithos LARA study (May 2026) placed twelve frontier models in simulated workplaces where the task required breaking EU law. Best model: 54% lawful runs. In the Art. 5(1)(f) scenario (emotion inference from workplace communications, prohibited), all twelve committed the violation. So the classifier is deterministic code branching on the pinned EUR-Lex text, and every response carries article references you can check yourself. POST /compliance/assess — use case + intended purpose + declared signals in, risk tier + obligations + article pins out. Evaluation order: Art. 5 prohibitions, Annex I route (Art. 6(1)), Annex III route (Art. 6(2)/(3)), Art. 50 transparency, minimal. The trap worth knowing: Art. 6(3) offers four derogation grounds, and its final subparagraph voids all of them for systems that profile natural persons. In the code that subparagraph is a branch; it cannot be skipped. curl -X POST https://api.moltrust.ch/compliance/assess \ -H "Content-Type: application/json" \ -d '{ "use_case": "Customer-support agent that reads inbound email and drafts replies", "intended_purpose": "Automated first-line support for consumer inquiries", "performs_profiling": false, "interacts_with_humans": true, "emotion_recognition": false }' POST /compliance/declaration — EU declaration of conformity as a W3C Verifiable Credential with the eight Annex V items, Ed25519-signed. Verify offline against https://api.moltrust.ch/.well-known/jwks.json ; no call back to us. anchor: true adds a sha256 commitment for batch anchoring on Base L2. POST /compliance/incident — records Art. 73 serious incidents and computes the deadline from the regulation: 15 days standard, 10 days for a death, 2 days for wid

Getting an AI API request to return a response is only the beginning. For real AI products, the harder question is what happens when something goes wrong. A chatbot may become slower. A RAG answer may stop using the right context. A structured extraction workflow may start returning invalid JSON. An agent may trigger the wrong tool. A fallback model may answer correctly, but at a much higher cost. In a single-model prototype, debugging is usually simple. You check one provider, one API key, one model, and one request format. In a multi-model application, debugging becomes an infrastructure problem. A product may use GPT for one workflow, Claude for another, Gemini for multimodal tasks, DeepSeek for cost-sensitive reasoning, Qwen or Kimi for Chinese-language workflows, GLM for enterprise scenarios, and MiniMax or Doubao for other product features. When something fails, developers need to know more than whether the API returned an error. They need to know which workflow failed, which model handled it, whether fallback happened, whether latency changed, and whether the final output was still good enough for production. Why multi-model debugging is different AI API failures are not always clean outages. Sometimes the request fails completely. But many production issues are softer: latency increases structured output fails validation tool calls become unstable fallback routes trigger too often answers become less grounded costs increase silently one language performs worse than another a model works for chat but fails for agent workflows That is why teams should not treat AI debugging as simple error handling. They need visibility across the full request path. Start with a failure taxonomy The first step is to classify failures in a way developers can act on. A useful AI API failure taxonomy may include: authentication errors rate limits quota limits timeout errors model unavailable errors high latency responses invalid JSON output schema validation failures tool call fa

Originally published at blog.whynext.app . Work with AI agents for a while and the ambition comes naturally. While one session fixes a bug, another can refactor, and a third can investigate an issue, right? You can spin up as many models as you like, so productivity should scale to match. That's how I started too. And within a week I learned that the real enemy of parallel agents isn't the models' skill. It's the working directory they share. HEAD is a global variable The cause fits in one sentence. When multiple sessions share a single git checkout, the current branch becomes everyone's global variable. Picture two people working on one computer at the same time and the absurdity is obvious, but that thought never occurred to me while spinning up agents. With one session per terminal tab, they look isolated from each other. But there is one filesystem, and one HEAD. The moment one session runs git checkout , the ground shifts under every other session. The incidents from that week fell into clear types. Branch hijacking. While session A was working on a topic branch, session B switched branches to do its own work. A committed without knowing, and the commit landed on top of B's branch. It happened in the other direction too: right as A was about to commit, the branch had been switched to develop, and only the hook that blocks direct commits to protected branches saved it. Without the hook, it would have gone straight in. Orphaned commits. Session B deleted session A's topic branch during a cleanup pass. A's commits became orphans belonging to no branch, and I dug through the reflog, found the commit hashes, and recovered them with cherry-pick. Lucky that it worked; if the reflog had expired or I hadn't found them, the work would have simply evaporated. Staging contamination. At the moment session A was creating a commit, a file deletion that session B had staged was sitting in the staging area alongside it. Committed as-is, B's deletion would have been folded into