#PromptIn

el ingeniero que construyó Claude Code acaba de publicar un video de 28 minutos sobre cómo escribir prompts que realmente funcionan he visto cursos de 300$ que no cubren lo que él muestra en los primeros 10 minutos archivos CLAUDE.md, atajos de memoria, sesiones paralelas, patrones de prompting todo en un video y completamente gratis funciona seas desarrollador, principiante o alguien que lleva meses usando Claude

⚠️ A deeply worrying moment during Tenerife vs Andorra. In the 98th minute, Jesus de Miguel was involved in a serious collision with Owono and remained down on the pitch, prompting an immediate stoppage as medical staff rushed to provide assistance. Reports indicate he suffered a cardiac arrest and is currently receiving intensive care. Our thoughts are with Jesus and his loved ones. Wishing him strength and a full recovery. 🙏❤️

The engineer who built Claude Code from scratch just released a 28-minute video that's pure gold: how to write prompts that deliver ridiculously good results. I've seen $300 courses that don't even come close to what he explains in the first 10 minutes. CLAUDE.md files, memory shortcuts, parallel sessions, and prompting patterns that almost no one uses... All in one single video. Completely free. No fluff. Whether you're a developer, just starting, or have already been using Claude for months, this changes the game for you starting today.

Are we getting smarter with AI, or just getting better at prompting?

My friend makes $1.2 million a year as an Anthropic engineer. I asked him how he learned prompting so well. He sent me a video that was never supposed to get out. Their core team's prompting playbook. You won’t find anything better about prompting than this 30 minutes video. I watched it last night. Halfway through, I realized I've been using Claude completely wrong for two years. Watch it, then read the article below.

Are we getting smarter with AI, or just getting better at prompting?

The Internet Computer is now a connector in Claude. Search for it in Claude's connectors, connect it once, and start prompting. Set up a cloud engine for your business, launch a client portal, keep building, all from the same conversation. Build on the Internet Computer directly from @claudeai.

genuine question for people who vibe code: do you actually understand the code AI generates, or do you just keep prompting until everything works?

POTENTIAL PUMPFUN HACK 🚨 The PumpFun Website is now actively prompting users to upload PRIVATE KEYS to link email & socials 🚩 No official announcement on X 🚩 No identical requirement on mobile 🚩 Former claims of NEVER asking users for private keys Considering recent hacks on Flap & StonkFuns' frontends, you'd expect official communication on an update that requires users' PRIVATE KEYS @a1lon9 @json1444 Has PumpFun been hacked?

Andrej Karpathy’s 1-hour Stanford lecture explains AI engineering beautifully. 10% → LLM 30% → Prompt 50% → Agent 70% → Loop 100% → Graph The real power isn’t just prompting models. It’s building systems around them with context, memory, tools, and feedback loops. “Delete everything, keep Graph.” A must-watch for anyone building AI agents. 🚀

🚨 إنت ممكن تكون بتستخدم Claude غلط وعمرك ما هتعرف إلا لما تشوف الفيديو ده! مهندس في Anthropic بيكسب 1.2 مليون دولار سنويًا، بعت لصاحبه فيديو مدته 30 دقيقة عن أسرار الـ Prompting. الفيديو، بحسب روايته، بيشرح دليل كتابة الأوامر الخاص بالفريق الأساسي في Anthropic. صاحبه اتفرج عليه… واكتشف إن المشكلة مكانتش في Claude، بل في طريقة استخدامه ليه! 🤯 تخيّل إنك بتستخدم أداة قوية كل يوم، لكنك مش عارف تستخرج منها أفضل النتائج، لمجرد إنك بتطلب منها بطريقة غلط. الفيديو ده ممكن يغيّر الطريقة اللي بتتعامل بيها مع الذكاء الاصطناعي.

Change a robot’s mind mid-move 🤖 New blog: Prompting Robots with LeRobot. Send a new instruction to a running policy and watch it change course, no reset needed. You can also use it with steerable policies trained on multiple tasks. lerobot-rollout --interactive=true

We just replaced prompting. saw an ad you liked? this chrome extension extracts its prompt so you can recreate it. works on instagram, pinterest, x and any website try it: no more guessing prompts :) comment "regen" and i'll send you a month free

A video circulating online claims a man charged at a Chicago firefighter in the middle of an active emergency scene, prompting the firefighter to swing a tool at him before officers moved in to restrain him. The account, which has not been confirmed by Chicago police or fire officials, has drawn tens of thousands of views; the post is dated Monday, November 2, 2026.

BRAEDEN ACCIDENTALLY EXPOSED HIS SCAMMER PAST AND LACY WAS NOT HAVING IT 😭💀 While discussing Fortnite’s Pirate Token, Braeden suggested selling the account, prompting Lacy to warn him that it was against Epic Games’ rules. Braeden then casually admitted, “I used to scam people back in the day.” 😭 Lacy immediately replied, “Don't say that”

My friend makes $1.2 million a year as an Anthropic engineer. I asked him how he learned prompting so well. He sent me a video that was never supposed to get out. Their core team's prompting playbook. You won’t find anything better about prompting than this 30 minutes video. I watched it last night. Halfway through, I realized I've been using Claude completely wrong for two years. Watch it, then read the article below.

Senior Anthropic engineer: “Prompting is no longer the job. 99% of people still open one chat and call it agents.” This is a must watch

I think this is one of the very rare prompting tricks that is still useful over a year later X++ Take my prompt and write a better version of it; do what I want, not what I say; you have permission to lead this design.

One of the most powerful yet simple prompts is to go one meta-level up: “write a prompt for {insert-query-here} then answer it” Unless you’re an expert in your query’s subject matter, this should improve output quality more often than not!

One of my friend makes $1.2 million a year as an Anthropic engineer. I asked him how he learned prompting so well. He sent me a video that was never supposed to get out. Their core team's prompting playbook. You won’t find anything better about prompting than this 30 minutes video. I watched it last night. Halfway through, I realized I've been using Claude completely wrong for two years. Watch it, then read the article below.