标签：#c

The Sony Bravia 9 II is the most anticipated new TV in years. It's an amazing RGB LED TV. I watched Dungeons & Dragons: Honor Among Thieves on the new Bravia with my son, who has been getting into the roleplaying game but had never seen the movie. The landscapes of Faerûn looked natural and […]

This is a submission for DEV's Summer Bug Smash: Clear the Lineup . Project Overview Typst is the Rust-based markup typesetting system that's been quietly eating LaTeX's lunch for the last couple of years — you write plain-text markup, Typst compiles it to PDF (or HTML) with a real incremental compiler underneath instead of a multi-pass macro soup. Part of what makes it pleasant is that it exposes its own evaluator to itself: a document can call #eval("some typst code") and get back whatever that code produces, at runtime, inside the document being compiled. It's a small feature, but it opens up a surprisingly deep rabbit hole, which is exactly where this bug was hiding. Bug Fix or Performance Improvement The problem: typst/typst#8632 reports that Typst crashes instead of erroring when #eval is used to recursively re-import the file it's running in. The repro is one line. Save this as overflow.typ : #eval("import \"overflow.typ\"") Then: $ ./target/debug/typst compile overflow.typ overflow.pdf thread 'main' (750833) has overflowed its stack fatal runtime error: stack overflow, aborting No PDF, no diagnostic, no exit code you can act on — just a native stack overflow and a SIGABRT. Typst has had cyclic-import detection since forever; a normal top-level import "overflow.typ" inside itself gets caught cleanly with an error: cyclic import message. Something about routing the import through #eval specifically was bypassing that check. The hunt I'll be upfront about how this investigation actually went: I worked through it with Claude (Anthropic's coding agent) rather than solo. The triage pass it did before I sat down with the code had already narrowed the search to one function — eval_string in crates/typst-eval/src/lib.rs — and named the suspect line. That's a big head start, but a named suspect isn't a confirmed root cause, so the actual work was reading that function next to its sibling, the file-level eval() a few lines above it, and checking the claim against the s

As a developer, I got a bit scared and fed-up of blindly merging massive pull requests and losing context on my own codebase, so I built FluencyLoop . https://github.com/baokhang83/fluencyloop It is an open-source, local-first workflow plugin for Claude Code and Codex that ensures your code and your codebase fluency are produced together. Instead of letting an agent dump raw code, it tracks your technical familiarity locally and pauses to explain complex architectural choices or rejected alternatives only on topics you do not know yet. It also produces documentation and tracks the decisions it makes along the way. Try it out ! It feels really good to get the AI caring for my understanding 🤣

The problem with "just add another tool" When you're building one image tool, performance is easy. When you're building 71 of them in the same app — resize, compress, crop, PDF merge, format converters, exam-photo presets, social media templates — the naive approach (import everything, bundle it all together) turns your app into a multi-megabyte JavaScript payload before a user has even picked a tool. This is the actual engineering problem behind ResizeHub , which now has 71+ tools across 11 categories, all running client-side with zero server uploads. Here's how the architecture holds up at that scale. Stack, and why each piece earns its place React + TypeScript — type safety matters more, not less, as tool count grows. A shared ImageProcessor interface that every tool implements catches integration bugs at compile time instead of in production. Vite — its native ES modules dev server and Rollup-based production build made code-splitting dramatically easier to reason about than older bundlers, which matters a lot once you have dozens of independent tool routes. HTML5 Canvas API — the actual compression/resize/crop engine, shared across tools rather than reimplemented per-tool. Cropper.js — for interactive cropping UI specifically (aspect-ratio locking, circular crop for signatures) rather than rebuilding drag-handle math from scratch. Pica — for high-quality image downscaling; the browser's native canvas scaling can introduce visible aliasing on large downscales, and Pica's algorithm handles this noticeably better. Cloudflare Pages — static hosting with edge caching, which matters since 100% of the actual processing work happens in the user's browser, not on any server at all. Lesson 1: Route-level code splitting isn't optional past a handful of tools With React Router and dynamic import() , each tool becomes its own chunk: const PhotoResizer = lazy (() => import ( ' ./tools/PhotoResizer ' )); const PdfCompressor = lazy (() => import ( ' ./tools/PdfCompressor ' ));

A closer look at why companies like EvenUp are difficult to compete with, and what this means for the future of AI-powered legal technology. Introduction A few weeks ago, I went down a rabbit hole trying to understand how EvenUp built one of the most successful AI products in personal injury law. Like many people, I assumed the competitive advantage would come from a proprietary large language model, sophisticated prompt engineering, or some secret AI architecture hidden behind the scenes. Instead, I found something much less glamorous—but far more valuable. There is no magical prompt. There is no proprietary model that nobody else can build. The real competitive advantage is data. Hundreds of thousands of real personal injury cases. Millions of medical records. Actual settlement outcomes connected to real case facts. Years of attorney corrections, paralegal feedback, negotiations, settlements, and litigation outcomes—all continuously improving the system. Once you realize this, you begin to see the same pattern across almost every successful vertical AI company. The model is rarely the moat. The data is. Why "AI for X" is mostly noise right now Today, almost every industry has dozens of startups claiming to build: AI for law firms AI for healthcare AI for accounting AI for insurance AI for real estate Scratch beneath the surface, however, and many of these companies are built on the same foundation: GPT Claude Gemini Llama The underlying model changes every few months. The interface changes. The branding changes. The product positioning changes. But underneath, many products are simply orchestration layers around publicly available foundation models. That isn't inherently bad. Good user experience matters. Workflow automation matters. Tool integrations matter. But none of those create a durable competitive advantage. Anyone with API access, a competent engineering team, and enough time can recreate that layer. What they cannot recreate overnight is years of proprie

📓 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?

Hi, friends! Welcome to Installer No. 136, your guide to the best and Verge-iest stuff in the world. (If you're new here, welcome, hope your neighborhood isn't as smoky as mine, and also you can read all the old editions at the Installer homepage.) This week, I've been recording the next season of Version History […]

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

Our remote team clocked serious hours walking, working, and sometimes jogging to find the best under-desk treadmills for home offices and small spaces.

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.