AI 资讯

📓 Stop Memorizing English — I Built an AI App That Actually Works ⚡ The Hook You try to learn English. You memorize words. And then… you forget them. 🧠 The Real Problem Most people learn English the wrong way: memorizing random word lists switching between apps and dictionaries learning without context That’s why nothing sticks. 🚀 The Idea What if learning English felt like this: 👉 You read something interesting 👉 You click a word you don’t know 👉 You instantly understand it No interruptions. No friction. ✨ Introducing: English Notebook A modern AI-powered app where you learn English by interacting with real content . generate stories click unknown words build vocabulary automatically 🤖 Generate Stories Based on Your Level This is one of the most powerful features. You choose your level: A1 → Beginner A2 B1 B2 C1 C2 → Advanced And the app generates a custom story just for you . 🖼️ Story Generator 📖 Learn by Clicking Words No more: copy-pasting opening dictionary tabs losing focus Just click any word: definition translation (your language 🌍) example sentences 🖼️ Word Interaction 📚 Smart Vocabulary Notebook Every word you click: 👉 automatically saved 👉 turned into a flashcard You can: review anytime mark as mastered ✅ 🖼️ Vocabulary Notebook 📊 Track Your Progress (Game Changer) This is where things get serious. You don’t just learn — you measure your growth . Dashboard shows: total words learned active vs mastered words daily streak 14-day activity trend 🖼️ Dashboard What gets measured gets improved. 🕘 Nothing Gets Lost (History System) Every story you generate is saved. You can: revisit old stories continue reading anytime track your learning journey 🖼️ History 🔊 Learn with Audio listen to stories follow highlighted words improve pronunciation naturally 🌍 Multi-Language Support You can choose your translation language: Persian 🇮🇷 Arabic Spanish Hindi and more 🎯 Why This App Is Different Most apps: ❌ force memorization ❌ feel like school ❌ break your focus English Note

A follow-up to Part 1: the self-recall thesis — the series runs through Part 6 . Code: RE-call — everything below is measured and reproducible ( make eval ), full study in docs/ENTAILMENT_SUPERSESSION_STUDY.md . I published a thesis post about agent memory and got five comments that were better than the post. Two of them didn't just critique the design — they described, precisely, why it would fail and what would fix it. So I did the only reasonable thing: I turned both into experiments, ran them on the same eval harness the series is built on, and shipped what survived. That's RE-call v0.3 , and this post is the receipt. I want to be explicit about why I'm writing it this way. The point of publishing this series was never broadcast — it was error-correction . A design you keep in a drawer accumulates conviction; a design you publish accumulates objections , and objections are the cheapest high-quality signal you will ever get. The comment section of Part 1 did more for this codebase than any week of solo iteration. This post exists to pay that back with the thing commenters almost never receive: evidence that someone listened, measured, and changed the code. Comment 1: "A similarity score is not a confidence score" Vinicius Pereira put it in one line I've been quoting since: Proximity is a candidate; entailment is the evidence. His argument: the near-misses that hurt most are high-similarity and wrong — memos semantically adjacent to the query that don't answer it. A threshold-based gap_warning (Part 3, Part 5) waves them straight through by construction , because their similarity clears any threshold you could calibrate. The abstention signal cannot be the retriever's own score. You need a separate check that the retrieved memo actually entails an answer. He was right, and measurably so. I built a held-out challenge set of 10 near-miss queries — each names a strongly on-topic memo that does not contain the asked-for fact ("how much did the cache reduce memory usag

Part 6 (finale) of Retrieval-Augmented Self-Recall. Code: RE-call . Part 5: the gap threshold that didn't transfer . I fine-tuned the embedder on my own domain expecting a win. I measured it properly, on held-out queries. The improvement was exactly zero. Δ+0.00 MRR. Δ+0.00 nDCG@10. Not "small". Not "within noise". Zero. It's also the result I wanted, which takes some explaining. That's the first half of this post. The second half is how the whole engine ships, so an agent can actually use it. The fine-tune that did nothing After Part 5, the natural next question: if calibrating the threshold helps, would a better embedding help more? So I fine-tuned one on my domain. The setup: all-MiniLM-L6-v2 , OnlineContrastiveLoss on query/gold-chunk pairs, trained on the 14-document corpus. The result: Model Test MRR Test nDCG@10 Base 1.00 1.00 + Fine-tuned 1.00 1.00 Δ +0.00 +0.00 Zero lift. And that is the correct outcome, not a failed experiment. Here's the reasoning, because it's the whole point. The base model already scores a perfect MRR and nDCG@10 on this corpus. There is no headroom left to recover. The only ways to manufacture a "gain" from here would be dishonest ones: evaluate on the training set (and measure memorization, not retrieval), or artificially cripple the baseline so fine-tuning has something to fix. Reporting +0.00 is the honest read, and the honest read is that off-the-shelf embeddings already saturate this corpus. But the full result is more nuanced, and more useful. On a harder , opaque-jargon corpus — one where the base model genuinely struggles to map queries to the right chunks — the same fine-tuning gave +0.24 MRR . So the real conclusion isn't "fine-tuning doesn't work." It's: Fine-tuning helps when the base model doesn't already cover your vocabulary. When it does, you get nothing. Know which regime you're in before you spend the GPU hours. That's the value of a null result. "+0.00" told me my corpus was already well-covered by a general-purpose

I wrote a cleanup routine that matched processes by command line with a wildcard pattern. It reported success on every run. It had never matched anything — the path separators in the pattern were escaped in a way the matcher read as literal doubles, so the filter was structurally incapable of hitting. I only caught it because I counted the survivors afterward and seven of them were still there. The fix was switching from a wildcard match to a plain substring containment check with no escape semantics at all. A filter that cannot fail loudly will lie to you politely forever. Before trusting any matcher, feed it a known-positive and watch it fire — a green result from an instrument you never saw go red is noise. What's the equivalent lesson your worst bug taught you?

It's been a good few weeks for games on rails. Nintendo's Star Fox remake wisely kept the tightly scripted, action-packed levels from Star Fox 64 largely the same, and they're still fun to fly through nearly 20 years later. Denshattack!, a new game from Undercoders, similarly features levels packed with carefully orchestrated sequences to great […]

Enjoy our weekend guide to the best indie games worth checking out.

The government is piloting a program that uses AI for insurance-coverage decisions.

OpenAI will send a notification to parents with linked teen accounts if their children have violated its policies around violence.

Plus: Russian cyberspies turn to infrastructure hacking, DHS repeatedly fails to realize it’d been hacked, a breach exposes an AI music generator’s scraping ways, and more.

Why some records should be created by your system, not your users, and how to do it safely in .NET. A support ticket lands on your desk: "The Teams page is empty. I added a member, but no team shows up." You check the API. It's behaving exactly as written: { "items" : [], "totalCount" : 0 } Nothing is broken. And that's the problem. The system is faithfully returning nothing, because the row that the page reads from was never created. Somewhere in your design, you assumed a human would create it first. This article is about a small, recurring design decision that quietly causes empty dashboards, confused users, and "is this a bug?" tickets: who is responsible for creating derived records the user, or the system? and how to let the system do it without introducing duplicate rows or race conditions. The problem Let's use a fictional product: a collaboration tool called Loop . In Loop, the important entities are: An Organization (a paying customer). A Member (a person invited into an organization under a plan). A Team a grouping that members belong to, keyed by (OrganizationId, PlanCode) . The admin dashboard lists Teams . Each team card shows a member count. Here's the catch in the original design: creating a Member wrote a member row. Creating a Team was a separate, manual step an admin was expected to do first. If an admin invited members without first creating the matching team, the dashboard showed nothing even though the members clearly existed. From the user's point of view, they did everything right. From the system's point of view, a required row simply didn't exist. Why it matters The Team record isn't independent information. It is fully derivable from the first member invited under a plan. When one entity's existence is implied by another, forcing a human to create it manually is a design smell. It leads to: Empty states that look like outages. Users can't tell "no data" from "misconfigured." Support load. Every skipped step becomes a ticket. Silent data dr

The Architectural Shift: Client-Side vs Server-Side For years, the standard for building modern React applications was the Single Page Application (SPA). Vite revolutionized this space by providing an incredibly fast developer experience (DX) and an optimized build process. However, as applications grow, many teams find themselves hitting the performance ceiling of client-side rendering. When we talk about migrating from a Vite-based SPA to Next.js, we aren't just changing build tools; we are moving from a model where the browser does all the work to a model where the server shares the load. In this article, we'll look at the benchmarks of a mid-sized e-commerce dashboard before and after migration. Understanding the Core Metrics To measure the impact truly, we focus on three Core Web Vitals: LCP (Largest Contentful Paint): How quickly the main content is visible. FID (First Input Delay): How responsive the page is to the first interaction. CLS (Cumulative Layout Shift): How stable the visual elements are during loading. Vite SPA Performance (The Baseline) In a Vite SPA, the initial HTML request returns a nearly empty <body> tag with a <script> bundle. The browser must: Download the HTML. Download the JavaScript bundle. Parse and execute the React code. Fetch data from an API. Finally, render the UI. Benchmark Results: LCP: 2.4s (on 4G connection) FID: 45ms TBT (Total Blocking Time): 320ms While the DX is lightning fast, the user experience suffers from the "white screen of death" during the initial bundle download. Next.js SSR/ISR Performance (The Post-Migration Result) Next.js changes this via Server-Side Rendering (SSR) or Incremental Static Regeneration (ISR). The server fetches data and pre-renders the HTML. The browser receives a fully formed UI immediately. Benchmark Results: LCP: 0.8s (on 4G connection) FID: 55ms TBT: 180ms There is a slight increase in FID because the browser's main thread is busy "hydrating" the static HTML into an interactive React app, b

Now that Google has changed how its usage quotas are tallied, you might not get as many AI responses as you did before.

🇮🇩 Originally written in Indonesian. This English version was AI-assisted and adapted for a more natural reading experience. It is not a literal translation. _open Introduction Lately, I've been having quite a few discussions with frontend developers about the frameworks they use. My question is actually pretty simple. "When you're building a web frontend, what framework do you usually use?" Almost everyone gave more or less the same answer. "It depends on the project." And honestly, I agree. There's no framework that's always the best choice for every situation. However, as the conversation went on, they started sharing their own experiences and preferences. Well... That's when I started noticing an interesting pattern. Among the developers I talked to, quite a few of them mentioned that they usually use Next.js / React for work, while Vue.js is what they often choose for personal projects. The interesting part is... I never actually asked, "What do you use at work?" or "What do you use for personal projects?" That explanation came up naturally as they explained why they preferred certain frameworks. At first, I thought it was just a coincidence. But after hearing the same pattern from several different people... I got curious. Why do so many developers who are comfortable with both frameworks end up separating how they use them? (・_・;) Disclaimer This isn't based on an official survey or research. It's simply an interesting pattern I noticed after talking with several frontend developers. Discussion Vue.js Looking at today's frontend ecosystem, Vue.js is clearly not a small framework. Its community is large. Its documentation is great. Its ecosystem is also quite mature. That said, compared to React and Next.js, its community is still smaller. Then another question comes to mind. If that's the case... Why do so many developers still choose Vue.js for personal projects? From the answers I heard, the main reason wasn't performance. And it wasn't because other framew

Before a young Athenian took his full place in the city, he spent two years in the ephebeia. Training happened in the gymnasion, organized by tribe, the same tribes that would later send him to represent them in the Boule itself. Nobody handed him full standing first and hoped the judgment would follow. This should have been post seven. It’s showing up as sixteen because the gap only became visible once the room was real enough to test against. The Agora described what a Spec Session does. It never asked whether everyone walking into that room shares an accurate picture of what the agent can actually do. Most rooms don’t. Someone watched a demo and thinks the agent can do anything. Someone else got burned by a bad output three weeks ago and doesn’t trust it with anything real. Nobody’s intuition has been tested against the same tasks, and the spec that comes out of that room ends up too ambitious or too conservative depending on whose untested belief happened to speak first. That gap has a name in Athens. The gymnasion existed because nobody was handed a place in the city first and expected to develop judgment on the job. The ephebeia ran two years, training built around a specific fact. Physical readiness and civic judgment weren’t taught in separate places. They happened in the same space, under the same supervisors, organized by the same tribal groupings that would later structure how the city actually governed itself. The same word, gymnasion, ended up naming both the training ground for eighteen-year-olds and the buildings where Plato and Aristotle did their most serious thinking. Academy and Lyceum were gymnasia first. Nobody separated the trial from the reflection. The trial was how the reflection got earned. That’s the part worth taking seriously. Testing a tool and understanding a tool were never two different activities. The testing is how the understanding gets built. A team that reads documentation about what an agent can do has a description. A team tha

Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is...

Why We Built This As developers and builders at Smart Tech Devs , we love analyzing data trends. But when it comes to trading charts—whether it's crypto, stocks, or forex—reading technical signals manually requires hours of screen time. Beginners struggle with complex patterns, and experienced traders often want a quick sanity check on their thesis. We asked ourselves: Can we leverage Vision LLMs to turn static chart screenshots into professional-grade technical analysis reports in seconds? That question led us to build and launch Realtime Chart Analyzer (ChartAI Pro) , now live on the Google Play Store! ⚡ Key Architectural Features We designed ChartAI Pro to act as a seamless, secure second pair of eyes for market charting. Here is a breakdown of what the application delivers right out of the box: 🧠 1. Multi-Modal AI Chart Analysis Instant Processing: Upload or snap a screenshot from platforms like TradingView, Binance, Zerodha, Groww, Upstox, or MT4/MT5. Signal Detection: The core engine evaluates market structures to return clear Bullish or Bearish indicators alongside an AI confidence score. Plain-English Summaries: No overly dense academic jargon—you receive an intelligible breakdown of current market conditions. 🎯 2. Automated Key Price Levels & Patterns Support & Resistance: The system instantly flags primary macro price horizons. Risk Mitigation: Calculates approximate entry zones, mathematical target price targets, and clear Risk/Reward ratios. Geometric Processing: Detects complex shapes including Head & Shoulders, Double Tops/Bottoms, Triangles, Wedges, Flags, and specialized candlesticks (Doji, Engulfing lines). 📊 3. Native Live Market Infrastructure Live Scanners: Includes a built-in terminal tracking real-time crypto, forex, and stock prices (NSE & BSE). Interactive Tooling: Features built-in interactive TradingView frames directly in the layout, allowing you to scan Top Gainers and Losers without hopping between apps. 🔒 Privacy & Security First When d

Github currently doesn’t let you unstar repositories in bulk. To resolve that let me introduce Workaround : a web app where users can not only unstar GitHub repos in bulk but also use AI filters and discover and star repos with AI. https://github.com/Ayush0054/workaround