XNickDaN

Anthropic just dropped a 31-page prompting guide. Here's everything you actually need (in 10 rules): 1. You write "review this contract" and pray. Fix: Name every output. "Review this contract. Flag risks per clause. Rate severity 1-5. Return as a table." 2: You say "summarize this" on a 40-page report. Fix: 4.7 sizes the answer to the input. Cap it: "5 bullets. Each under 15 words. Start each with an action verb." 3: You write "don't use jargon. don't be salesy." Fix: Negative instructions don't stick. Flip them: "Write in plain English a 16-year-old could read aloud." 4: You type "can you help me with the email?" Fix: Each verb ships something. For example: "Go to Gmail. Find [contact]. Write the send-ready reply. Under 90 words. Tone: confident, casual." 5: You wait for Claude to web search on its own. Fix: Claude opus 4.7 calls fewer tools than 4.6. Force it: "Use web search aggressively. Verify every claim with at least 2 sources." 6: You miss the warm tone from old Claude. Fix: Claude opus 4.7 is direct. Almost zero emojis. Paste 2-3 sentences in the voice you want. Tell Claude to match the rhythm. 7: You ask for "a landing page" & get bare minimum. Fix: Drop this one line on every creative task → "Go beyond the basics." It's from Anthropic's own doc. 8: You forget Claude 4.7 doesn't reason by default. Fix: They call it "adaptive thinking." Add this at the end: "Think before answering (maximum reasoning)." Free upgrade. Every time. 9: You rewrite the same prompt 14 times a week. Fix: A skill is a command with instructions pre-built. Write the same prompt twice? Make it a skill. 10: You assume Claude knows what you meant. Fix: Old Claude 4.6 guessed. New Claude 4.7 does exactly what you typed. Spell it out. Output. Order. Length. Tone. Format. If you don't say it, you don't get it. To go even further & download my .md files directly: Step 1. Go to how-to-ai.guide. Step 2. Subscribe for free. Don't pay anything. Step 3. Open my welcome email (most skip this). Step 4. Hit the automatic reply button inside. Step 5. Download my .md files from my Notion. Bonus. Enjoy my best copy-paste prompts, too.

@tangero To je omyl, AI nemělo na Seznamu sílu číst ne diskuse pod články, ale ty články samotné.

Seznam nezvládl provoz umělé inteligence v českém politickém prostředí 😇😁(nutno číst a uvážit co se stalo)

@tangero Pokud bude na projektu pracovat více lidí, bude v .docs za chvíli pořádný guláš. Druhák, o tom jak má vypadat CLAUDE.md, si vystačím s tím, co doporučují Andrej Karpathy nebo Boris Cherny.

Harness zní trochu jako magie. Přitom je to velmi pragmatický přístup, jak zlepšit kvalitu projekt v Claude Code (nebo třeba v CODEX). Mám pro vás 5 tipů, co udělat lépe: vibecoding.cz/articles/claud…

@Suryanshti777 Good point, but greenfield needs different flow: 1) Interview - goals, arch, constraints → CLAUDE.md 2) Lock in patterns 3) Then run claude-code-setup Without that, "analyze codebase" has nothing to work with.

Claude Code feels completely different once you install this. Anthropic quietly released an official plugin called claude-code-setup and it basically turns Claude Code from “pretty good” into an actual AI dev environment. It scans your project and recommends: → hooks → skills → MCP servers → subagents → automations Then sets everything up step-by-step for you. Most people are using Claude Code completely vanilla… which is why their experience feels messy. The real power comes from the ecosystem around it. Install: /plugin install claude-code-setup@claude-plugins-official Bookmark this before you forget it.

@OpenAIDevs Cool feature. But which regions is this actually available in? Announcing things without mentioning availability is just wasting everyone's time. For most of the world this tweet is pure FOMO marketing, not useful information.

Codex can now take on more of your browser dev work. With the new Chrome plugin in the Codex app, it can test web apps, gather context across tabs, use web DevTools efficiently in parallel, and keep results organized without taking over your browser.

@dr_cintas Is it intentional that /codex:rescue supports inline --model, but /codex:review and /codex:adversarial-review only pick the model from config.toml and can’t override it per run?

Link: github.com/openai/codex-p… And if you want to get my full free Claude course: 1. Go to simplifyingai.co 2. Subscribe free by just writing your email. 3. Open my welcome email and get the free resources.

You can use now Codex in Claude Code 🤯 OpenAI has dropped a plugin that lets you run Codex directly inside Claude Code. Code reviews, adversarial reviews, background tasks…one command to install: /plugin install codex@openai-codex

@petarivanovv9 @AntonMartyniuk Could you walk through the concrete order in which you’d add test scenarios (and which layers you mock or defer) when doing AI‑first TDD for something as simple as CreateUser in a brand‑new project?

@AntonMartyniuk I'd also experiment with adding the test scenarios before prompting the agent to write the code. Then, you know, it can't bullshit you. 😅 Looking forward to the read, Anton!

𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝘄𝗶𝗹𝗹 𝗿𝗲𝗽𝗹𝗮𝗰𝗲 𝗷𝘂𝗻𝗶𝗼𝗿 𝗮𝗻𝗱 𝗺𝗶𝗱𝗱𝗹𝗲 .𝗡𝗘𝗧 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿𝘀 Read this to survive 👇 Junior and mid-level devs often skip the fundamentals and take shortcuts on every path with AI. AI amplifies what you already know. If your fundamentals are weak, you can't tell when Claude or Copilot generates code that's subtly wrong. And it will be wrong. Often enough to matter in production. The stronger your fundamentals, the better your judgment on what to keep, what to fix, and what to throw away. Here are 5 fundamentals that will help you survive in the age of AI: 𝟭. 𝗛𝗧𝗧𝗣 → Junior: ships the AI-generated controller. → Senior: catches the missing idempotency on POST, the wrong status codes, the leaked stack trace in error responses. 𝟮. 𝗖𝗼𝗻𝗰𝘂𝗿𝗿𝗲𝗻𝗰𝘆 → Junior: ships the async method. → Senior: catches the missing CancellationToken passed through the call chain, and the .Result call that will deadlock under load. 𝟯. 𝗘𝗙 𝗖𝗼𝗿𝗲 𝗮𝗻𝗱 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀 → Junior: sees code that compiles. → Senior: catches the N+1 query, the missing AsNoTracking, the IQueryable that materializes a million rows in memory. 𝟰. 𝗔𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲 𝘁𝗿𝗮𝗱𝗲-𝗼𝗳𝗳𝘀 → Junior: accepts Microservices because Claude suggested it. → Senior: asks "why not start with a Modular Monolith and extract later if needed?" 𝟱. 𝗩𝗮𝗹𝗶𝗱𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗲𝗿𝗿𝗼𝗿 𝗵𝗮𝗻𝗱𝗹𝗶𝗻𝗴 → Junior: keeps try/catch inside the endpoint. → Senior: knows Result beats exceptions for business flow, and FluentValidation beats inline if-else. The AI didn't generate worse code in any of these cases. The senior just knew what to look for. That's the gap. And it's growing. Developers who treat AI as an assistant they guide through structured decisions will ship production software. Tomorrow, I'm sending my complete 10-step workflow to 𝟮𝟱,𝟬𝟬𝟬+ .NET developers: ✅ The CLAUDE[.]md template I use for every .NET project (the single most impactful technique) ✅ The 4 specification documents that turn AI into a Principal Developer ✅ The 3-pass code review prompt that catches N+1, missing auth, and leaked secrets ✅ The file reference trick that makes Claude follow your patterns instead of inventing new ones This is the workflow I use to ship well-architected, production-ready .NET software with AI, without sacrificing quality. And you can too. 📌 Subscribe to my weekly .NET newsletter so you don't miss the issue: ↳ antondevtips.com/?utm_source=tw… —— ♻️ Repost to help other .NET developers survive in the AI era ➕ Follow me ( @AntonMartyniuk ) to improve your .NET and Architecture Skills

@bcherny Great, will try it! Though with Opus 4.7 burn rate, I expect it to 1-shot book the outbound flight - and leave me with zero credits to book the return.

I needed to book flights for a bunch of upcoming travel. As always, I used Claude Cowork to do it. In the past, Cowork has been decent at booking flights, but with Opus 4.7, for the first time ever, it 1-shotted it!

@karpathy Love this, but worth calling out the tradeoff explicitly: richer HTML UIs = more output tokens. We’re basically paying extra per answer to buy more “visual bandwidth” into the human brain - and that’s often a great deal.

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral x.com/zan2434/status… There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.

@davidfowl Could you write a standalone article for senior devs new to AI-first: brutally practical from-scratch guide - Claude Code CLI/Desktop, CLAUDE.md, skills, plugins, MCP servers → multi-agent workflow with virtual AI collaborators across PRD → impl → test → review?

@HVokurka cukry 4,9 g; nechci. Chci něco alá Mattoni esence

Ode dneška je Vratislavická kyselka i v 25L sudech - Citron 🍋 a Pomeranč 🍊! kitl.cz/vyrobky/vratis… kitl.cz/vyrobky/vratis…

@rubenhassid Small nuance on the “negative rule”: Google’s official DESIGN.md spec has a canonical “Do’s and Don’ts” section where explicit “don’t” guardrails are expected. The real issue isn’t negatives, but negatives without a paired positive instruction.

Anthropic just dropped a 31-page guide. On how to prompt Claude 4.7. Here's what it fixes: 1. The scope rule: "Review this contract" gets you nothing. Name every output to Claude. 2. The negative rule: "Don't use jargon" doesn't work. Use positive instructions. 3. The length rule: "Summarize this" returns 8 paragraphs. Always define the cap. You upgraded to the new Claude model. But you forgot to upgrade your prompts. I spent the weekend reading Anthropic's 31-page guide on prompting 4.7 so you don't have to. I wrote a free guide with the exact 7 rules that fix it. Go to: ruben.substack.com/p/prompt-47 ___ I know I talk (a whole lot) about Claude. But I don’t care about Claude. 𝗖𝗹𝗮𝘂𝗱𝗲 𝗼𝗿 𝗔𝗻𝘁𝗵𝗿𝗼𝗽𝗶𝗰 𝗱𝗼𝗲𝘀 𝗻𝗼𝘁 𝗽𝗮𝘆 𝗺𝗲. I’m sharing, twice a week, how my work is speeding up (𝘷𝘦𝘳𝘺 𝘧𝘢𝘴𝘵) with AI. As I’m trying to keep up, I want 𝘺𝘰𝘶 to keep up. So we move just as fast. I want to be the great filter to your AI noise. And 593,000 people read this twice a week to focus on the 𝗛𝗼𝘄. Some came because of my LinkedIn. But most readers subscribed because someone they trusted sent one of my articles to them. If this article helped you, 𝗯𝗲 𝘁𝗵𝗮𝘁 𝗽𝗲𝗿𝘀𝗼𝗻 𝗳𝗼𝗿 𝘀𝗼𝗺𝗲𝗼𝗻𝗲 𝗲𝗹𝘀𝗲 (and share it):

@crowdlinker @bharatmodi2014 ...also will it be limited to 3 requests?

@XNickDaN @bharatmodi2014 Hey, we just launched the CLI. Working on MCP next.

We just shipped DesignMD. Paste any website URL → get a complete DESIGN.md file in seconds. Color palette, typography, design tokens — extracted by AI and ready for your coding agents. Free. No sign-up. → designmd.me

ZipIt 1.4 just got a massive power upgrade ⚡️ Turn any website into: 📦 Full offline bundle (React / Vue / Next ready) 🎨 Design system (colors, gradients, fonts — copy instantly) 🧩 Export Clean components + Figma-ready layers (paste directly into Figma) , Download or collect in figma 🤖 AI prompts for ChatGPT / Claude / Gemini — recreate UI precisely , copy prompt to create any ui element 🖼 Extract all assets (WebP, Lottie, SVG, JPG, MP4, audio) 🧹 Production-ready clean CSS ♿ Full WCAG audit + downloadable PDF reports All in one click. Download → Inspect → Extract → Rebuild zipit.blintix.store 🚀

I must never use AI to avoid thinking.

@bharatmodi2014 @crowdlinker Just one important question - does it respect robots.txt? Asking for a friend 😅

Build similar tool for chrome → zipit.blintix.store With ZipIt, you can instantly extract code, design tokens, fonts, colors, and media—right from your browser to your local workspace. The best part? Copy any website element and paste it directly into Figma with fully editable layers. This seriously speeds up workflows 🚀

@AntonMartyniuk .NET

👉 I just created something I wish I had 12 years ago. I've compiled 650+ hand-picked resources for mastering C#, .NET, ASP .NET Core, EF Core, and Microservices. These resources will help developers level up with targeted knowledge. I spent hours putting them together from my library. You can get these resources for free as PDF. This isn't just another PDF - it's the ultimate learning guide I always wanted when I started my developer journey. Inside, you'll find carefully selected resources: 📌 Official docs, tutorials, and guides 📌 Best blogs, videos 📌 Expert tips from my 12+ years as a .NET Technical Lead and Microsoft MVP Why trust me? Each Tuesday, 𝟮𝟱,𝟬𝟬𝟬+ developers receive my newsletter filled with practical tips on building robust, scalable .NET applications. My goal? To help developers craft better software, faster, using the right tools for each case. Want this PDF? Here's how you get it: 1️⃣ Follow me @AntonMartyniuk 2️⃣ Like and comment ".NET" below 👇 3️⃣ I'll send the PDF your way! 4️⃣ Repost to help more developers get these resources! ___ ➕ Follow me ( @AntonMartyniuk ) to improve your .NET and Architecture Skills Comment ".NET" now, and you will get the best set of resources for free, you can't find anywhere else. P.S.: Stay subscribed to my Newsletter to ensure you receive future updates

Link: styles.refero.design Follow me @dr_cintas for more AI gems like this. And if you want to actually learn AI, I send daily guides the latest resources and full tutorials here: simplifyingai.co