与「Frontend」相关的搜索结果

🚀 The full DeepSeek App experience, now via API Search, files, links, safety, and voice. The capabilities behind the DeepSeek App are now available through the DeepSeek API. Enable built-in features with a few parameters, or call standalone APIs such as OCR, ASR, and TTS. Build richer conversations or recreate the full DeepSeek App in your own application. Try our open-source frontend demo, with support for importing DeepSeek conversation history. 🔗 Demo: 📦 Code: 📖 Details: 1/4

🚨 Google resmen kabul etti. AI’lar frontend yazarken hâlâ 2019 seviyesinde takılı kalıyor. Sebep basit: Eğitim verileri eski miras kodlarla dolu. Çözüm olarak Chrome ekibi modern-web-guidance’ı çıkardı. • 212 modern web özelliğini modellere besliyor • Claude Code, Codex, Copilot ve Antigravity ile çalışıyor • Başarı oranı %56’dan %88’e çıkmış Kurulum tek satır: npx modern-web-guidance Sizce sıradaki “kaşıkla düzeltilmesi gereken” alan hangisi olacak?

一块榴莲千层蛋糕，保质期居然长达 9 个月？？ 这两天董宇辉新品牌“禾与春时”首发的猫山王金枕榴莲千层（16 分钟卖光 15 万单）因为“9 个月保质期”吵上热搜（#董宇辉蛋糕检测报告多达60多页## 阅读破 1490 万）。有人拿它跟山姆的冷藏千层拉了张实拍配料表对比图，还用大红圈把底下一串化学名圈了出来，质疑是不是“科技与狠活”；品牌方则直接甩出了 62 页的 SGS 检测报告。 普通吃瓜群众谁有耐心去逐字核对糊图的配料表和 62 页报告？ 正好蚂蚁百灵刚发了原生多模态模型 Ling-3.2-flash（官方称已落地灵光 2.0，总参数 560B、单步激活 25B，支持 1M 原生长上下文，主打复杂图文理解与视觉反馈自检），我直接打开 Ling Studio 网页端，把这张打满红圈的网传配料表对比图和 SGS 核心指标丢给它，让它生成一张「深色系单文件 HTML 一图流鉴定卡」，顺便看看它会不会掉进红圈的节奏里。 【测试环境与配置】 • 测试入口：Ling Studio 在线网页端（左上角确认模型为 Ling-3.2-flash）。 • 工具配置：关闭联网搜索/时间/天气插件（纯靠模型原生多模态读图与推理），开启思考模式，最大推理生成长度 262144。 【实测第一轮：它从糊图里看出了什么？】 原本我以为第一版生成的 HTML 样式多少会有点错位，结果它第一把直出的深色系鉴定卡（直接内置在 Preview 预览窗里，自动分了 01~06 六个模块，右上角甚至自己写了个“🖨️ 打印/存为 PDF”按钮）排版居然一次成型，完全没崩。更让我意外的是这两点： 1️⃣ 一眼戳破“红圈添加剂”的伪命题：网友红圈重点圈出来的那个名字吓人的「羟丙基二淀粉磷酸酯」，它直接对比左右两栏配料表指出：“两边（禾与春时与山姆）都有『羟丙基二淀粉磷酸酯』→ 不是决策差异点！红圈成分是口感稳定剂（防冷冻解冻出水），不是防腐剂。” 所以这波还真不能算翻车，它本质上是用 -18℃ 冷冻链 + 杀菌工艺 + 隔氧包装做出来的速冻甜品（果肉 ≥50%，适合冷冻囤货），而山姆是 0~4℃ 冷藏即食（果肉 33%，适合大分量尽快吃完）。 2️⃣ 极强的“反幻觉”克制：原图右边山姆那一栏被网友画的大红圈挡住了净含量和保质期，而且最底下有几行压糊的重影错字。很多模型遇到这种图会自己脑补瞎编，但 Ling-3.2-flash 直接在表格里诚实标了「图中未显示」，并在表底主动写了一行小字：“右栏底部小字分辨率不足，未采信”，同时声明无联网条件下未核验 62 页报告原文，仅按摘要呈现。 【初版版面有什么不足 → 第二轮反馈怎么改？】 虽然第一版逻辑和样式都很稳，但从直接截图分享的角度看，初版 Preview 渲染画面还有两个可以打磨的细节： • 初版版面不足：一是初版把 01~06 六个模块做成了纵向长页面布局，高度超出一屏，手机端一屏截不完（见图3）；二是焦点成分的定性结论融在文字段落里，缺少一眼就能看懂的视觉标签。 • 反馈与微调：第二轮我直接针对渲染结果让它收紧版面，它用时 63 秒把原本 6 个纵向长模块重构成了三栏紧凑布局（控制在 100vh 一屏内看完），还主动把「羟丙基二淀粉磷酸酯」的国标分类（GB 2760 / INS E1442 变性淀粉）做成了显眼的红绿胶囊标签——「质构·口感稳定剂 ✓」「防腐剂 ✗」，并加上了一句金句总结：“名字长 ≠ 防腐剂，与保质期无因果关系”（见图4）。 【真实体验判断：值不值得用？边界在哪？】 • 能打的地方：据官方介绍，Ling-3.2-flash 采用 7∶1 混合注意力架构，在 DesignArena 的 Image-to-Frontend 前端生成评测拿了 1238 分（注：官方披露在 Hopper GPU、约 30K 上下文及 DSpark 投机推理加速特定条件下解码均值达 280 tokens/s）。实测下来，这个 1238 分确实没水分——直出单页 HTML 的审美和结构完成度很高，尤其是「看不清的糊字宁可标『未采信』也不瞎编」这点非常讨喜。 • 客观边界：一方面，无联网条件下模型仅对用户提供的图文与报告摘要做结构化呈现，不能替代专业检测机构或人工对 62 页原始报告的最终复核；另一方面，官方也坦诚指出，目前模型在长程跨应用任务状态维持、复杂三维空间推理及 3D 细节保真度上仍有客观差距，在线网页端也不直接内置官方演示里的 Blender 等外部软件环境。 搞了半天，所谓“9个月保质期千层蛋糕”根本不是加了防腐剂，而是把千层做成了「-18℃ 冷冻速食」。如果是你，你会买这种能冻大半年、果肉 ≥50% 的冷冻千层，还是买冷藏 3 天内必须吃完的现做千层？👇

The Across domain is currently down while we secure it against an attack from earlier today. At ~18:45 UTC, a social engineering attack on @Namecheap (our domain registrar) gave a bad actor control of the Across domain. Within 15 minutes of this attack, we were alerted and immediately worked to shut the site down. SEAL911 marked across.(to) as a phishing site with major wallets, and Cloudflare worked with us to mark the domain as at risk, and later pulled the site’s DNS records. At the time of this post, Across.(to) is fully down, and the phishing site is no longer available. In the brief period before Cloudflare fully blocked the malware site, some users who visited across.(to) may have been affected. No third-party integrations or API users were affected. Users who believe they were affected should DM us with transaction details and revoke attacker permissions (see next tweet for details). Despite our best efforts, @Namecheap has been unresponsive, and we have not been able to properly secure the domain to bring Across’s services back up. Across’s frontend and API will remain down until we can properly secure them. We will always put user safety first. Across’s domain was fully locked down with best-in-class security practices; this unauthorized takeover should not have been possible. We will be investigating this deeply and will provide a post-mortem on how this domain takeover was possible once we have more information.

I asked Claude Fable 5.2 to create 100 HTML files Rules were simple: - look stunning - zero repetitive designs - go full creative mode What can I say? Anthropic has done it YET AGAIN. Just another mind-blowing model, nothing less. Fable 5.2 is the BEST MODEL I HAVE EVER TESTED on frontend web design‼️ The previous best result on this experiment was Opus 5.5, but Fable 5.2 is a noticeable step up. Many files include playable games, fun experiments, and just insanely high-quality HTMLs and designs. There is ONE big problem though: it costs 2x as much as Opus 5.5! This experiment includes only 76 files, because this prompt alone used ALL of my Fable usage, including a FULL RESET! Meaning it burned TWO weekly Fable usage limits! However, as expected, ZERO BROKEN FILES. There are TOO MANY INSANELY GOOD files to list them all here. YOU MUST go over EVERY SINGLE FILE. See the results for yourself (incl. prompts): All other experiments here: Some great examples: Volcán Chico Hot Sauce Koi Pond Descent - A Vector Lander Landscapes in One Pen - this is amazing. The Wheel - Throw a Pot Tangram Menagerie The Night Typist Lava Lamp, 1971 Jelly Alphabet Ariadne's Thread - just wow! Cross-Stitch Studio Pinscreen And so on... just open all the files!!!

Claude Opus 5.5 just cooked a 20-person motion studio... these are the 20 skills I actually use with Opus 5.5 for video, design, 3D, motion and gamedev. 770K+ github stars between them: VIDEO ┣ hyperframes · write HTML, get a video (81K★) ┃ ┗ ┣ openmontage · full agentic video studio, 12 pipelines (79K★) ┃ ┗ ┣ video-shotcraft · cinematic product promos (18K★) ┃ ┗ ┗ remotion skills · the official one, videos in react (6.7K★) ┗ DESIGN ┣ anthropic skills · frontend-design, canvas, algorithmic art (190K★) ┃ ┗ ┣ impeccable · /polish /bolder /critique, kills AI slop (107K★) ┃ ┗ ┣ open-design · open-source AI design workspace (107K★) ┃ ┗ ┗ hallmark · design that refuses to look AI-made (51K★) ┗ 3D ┣ blender mcp · claude drives blender, whole scenes (34K★) ┃ ┗ ┣ anatomy · any idea as a real working 3D object (26K★) ┃ ┗ ┣ unity mcp · claude runs the unity editor (16K★) ┃ ┗ ┗ blender-skills · 94 skills, blockout → export (2.3K★) ┗ MOTION ┣ gsap skills · official easing, timelines, scroll (18K★) ┃ ┗ ┣ anything2explainer · topic in, narrated explainer out (3.2K★) ┃ ┗ ┣ oil-motion · animation that follows scroll + mouse (2.9K★) ┃ ┗ ┗ herk edit kit · cut dead air, edit reels + shorts (2.7K★) ┗ GAMES ┣ universal-modder · mod any PC game you own (9.5K★) ┃ ┗ ┣ gamedev skills · 77 skills, godot to three.js (7.9K★) ┃ ┗ ┣ pixelfx · 244 pixel effects in code (6.2K★) ┃ ┗ ┗ sprite-gen · game sprites + animation atlases (3.9K★) ┗ all open source. the 3D scene on each card is mine, fully rendered in blender for that skill

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

pump/sol & pump/usd pairings, swapped some more solana into pump betting on weekly close > .0055 and .01+ shortly after already 5x off bottom from summer & leading altcoin thus far this cycle believe this breaking ATHs will raise ceilings for all new launches, still very underowned, yearlong accumulation & buybacks remain consistent with crosschain mobile app gaining traction ---- other general market thoughts zec 400 to 1600 in Q3, up from 40 in september of 2025, (500M -> 20B mcap) by far the top crypto performer of the past year, entering the double bubble turbulent area where price action becomes most volatile and blow off top ensues, i believe btc 2017 is best comp, aggressive uptrend+selloffs all year btc eth & sol holding above range highs after good move off the lows from the summer, pa has been clean, no large liq runs yet but believe most are still offsides, think higher before pullbacks hype & lit have been strong but recently sold off p aggro on robinhood perps integration news, believe this is the time period where it will make the most sense for hyperliquid & lighter to be aggressive with marketing, especially hyperliquid as i feel they have dominated but mostly exhuasted all of the liquidity of the crypto native cohort, hyperliquid has ~100k active traders? RH has 25M DAUs, want to see hyperliquid move aggressively into marketing towards more retail but also tradfi HNWI clients, am sure they are already thinking of ways to do this but is necessary step for them becoming 1T+ behemoth as Jeff envisions, partnership with Kraken on US integration is a big step this is also the area where i expect a lot of builders to capitalize, HL builder codes are designed in such a way that retail frontends can build easily on top, believe gamified hyperliquid mobile apps will be some of the most successful crypto apps this cycle, similar to trading terminals success last cycle with onchain coins, social trading has been huge sofar with onchain coins, but PNLs on perps are much larger & whoever figures out how to tap that liquidity wins huge ---- timing altcoins zec uptrend started sept 2025 hype uptrend started jan 2026 pump uptrend started july 2026 ZEHYPERPUMP still strongest 3 imo stating because i believe it will be important to be able to determine where different altcoins are in their market cycles, crypto does not trade one to one anymore, btc eth sol were all in downtrend for most of the year while hype outperformed aggressively, pump was in downtrend for a year straight while zcash pumped 20x, alt szns are an ever-rotating game, not something that happens all at the same time, being able to recognize when certain trends are beginning and others are ending is a necessary skill for compounding wins together if i had to guess in terms of timing macro trends in three parts, id say zec is in its last third, hype is in its middle third, & pump is in its first third it takes time for a base to build on assets before demand outweighs supply and uptrend begins & the opposite happens at tops when supply eventually outweighs demand go look at old coinbase & robinhood charts, same trend diff timeframe ----- anyway my point being i believe we are entering a new phase for alts doing well, onchain & cex alts, cex alts currently have extreme discounts because of how poorly they did last cycle, imo this is your opportunity for identifying gems in the piles of trash, because there are some out there and most still believe crypto is a scam there is a lot of sidelined capital looking for things to bid, VCs & smart retail alike the time to make your list of which coins to start buying is now, everything is floored ------ TLDR: Q4 bias: bullish, pullback + OI wipe in October, early bull market but late lev entries dangerous, high conviction spot positions safe highest conviction: PUMP invalidation levels: 74k, 73, .0034, 750, 95 concerns: rates/war/dxy strength

Yep. Except: 1. This was about important internal tools. The team was stuck in some architecture nightmare of their own doing (writing it in rails but headless, with graphql api, and a SPA react app, constantly needing frontend engineers for changes). I call this kind of thing 'cosplaying an enterprise production app'. All that complexity was in the way and using straight rails was perfect in that case. 2. I make calls like this all the time. Usually someone on the team asks me to. They see what needs to happen but don’t want to be the bad guy. I’m happy to just make the call if I agree with the premise. Saves enormous amounts of meetings and change management etc. Sometimes this is jokingly referred to as Founder-mode-as-a-service here. 3. For ten years I’ve also run an internal podcast called Context, where I revisit decisions like these and explain the reasoning so everyone can learn from them. This is helpful to give people all the variables that were considered and why this was the choice made given the information available at the time. I want to teach how to make such decisions effectively without needing me. Sunk cost fallacy is a problem. 4. Any notions that Shopify is succcessful despite of me doing this, instead of because of it, will have a hard time making their argument come together I think 😄 the part of 'two weeks later tobi learns about...' is nonsese and the pivot of that project up there happens one of the more successful examples of interventions. But getting the company to work effectively with great architecture and low technical debt baggage into the right direction is literally the job, so guilty as charged I suppose. But there are always cope stories floating around like this because they are more fun, than saying 'somehow we needed tobi to stop doing silly architecture astronautics'. I can totally see that.