Get live statistics and analysis of Ruben Hassid's profile on X / Twitter

BREAKING: Apple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well. Here's what Apple discovered: (hint: we're not as close to AGI as the hype suggests)

BREAKING: Stanford just surveyed 1,500 workers and AI experts about which jobs AI will actually replace and automate. Turns out, we've been building AI for all the WRONG jobs. Here's what they discovered: (hint: the "AI takeover" is happening backwards)

The Anatomy of a Claude 4.6 Prompt: 1. Task Define what you want & what success looks like: "I want to [TASK] so that [SUCCESS CRITERIA]." No roles, "act as a senior expert." That era is over. 2. Context Files Upload context files with your expertise and rules: "First, read these files completely before responding: [filename .md] - [what it contains]." AI went from reading a sticky note to an entire book. Stop explaining yourself in the prompt. Put it in files. 3. Reference Show AI exactly what you want. Upload an example. Then give patterns, tone & structure as rules. No "give me something like" & hoping AI figures it out. 4. Brief This is the only part you actually type from scratch. Everything else is files. "Type of output + length. Does NOT sound like. Success means." 5. Rules Context file holds your standards, taste & audience. Prompt: "Read it fully before starting. If you're about to break one of my rules, stop and tell me." 6. Conversation You spent 3 years prompting AI. Now it prompts you Prompt: "DO NOT start executing yet. Ask me clarifying questions (use 'AskUserQuestion' tool) so we can refine the approach together step by step." 7. Plan Claude read your files before writing a single word. Prompt: "Before you write anything, list the 3 rules from my context file that matter most for this task. Then give me your execution plan." 8. Alignment Nothing happens until you both see the same aim. This replaces the old prompting era. Prompt: "Only begin work once we've aligned." Copy the full prompt template + download my personal md. files for Claude here: https://t.co/psB7XxAv8w.

Stop writing 500-word prompts. This 29-word prompt writes better than all of them: "Read my anti-AI writing style file first. It contains every known pattern of AI writing I want to avoid. Apply these as rules to everything you write for me." That's it. But you need to set it up first. Here's how: Step 1. Go to Wikipedia. Step 2. Search "Signs of AI writing." Step 3. Copy the entire page. Step 4. Paste it into a Google Doc. Don't edit. Step 5. Name it "anti-ai-writing." Step 6. Download as .md format. Step 7. This is your "what NOT to sound like" file. Or skip all of that. To download the anti-AI guide: Step 1. Go to https://t.co/psB7XxAv8w. Step 2. Subscribe for free. Don't pay anything. Step 3. Open my welcome email. Step 4. Hit the automatic reply button inside. Step 5. Download my .md files. Ready to upload. Step 6. Upload it to Claude. Prompt: "Read the uploaded file. It contains every known pattern of AI writing I want to avoid. Apply these as rules to everything you write for me. Do NOT start writing yet - ask me clarifying questions first." ✦ Here's why your prompts don't work (red flags): "Don't use jargon." "Don't sound like an AI." "Don't use buzzwords or filler." "Avoid passive voice." "Be conversational, not robotic." These are everywhere. LinkedIn posts. Emails. They sound thorough. The output is still garbage. Your prompt says "don't" 14 times. The model forgets half by sentence three. You're fighting the AI with a wall of "don'ts." It doesn't work at scale. The fix is counterintuitive. Stop telling the AI what to avoid. Give it a file that shows what to avoid. The model reads 1,168 lines of bad patterns, internalizes them, and writes clean. 500-word prompt → still robotic. Small prompt + 1 file → reads as a human wrote it. 1. To get access, go to https://t.co/psB7XxAv8w. 2. The Claude guide at https://t.co/jw2qdIbLxJ. 3. The Claude cowork guide at https://t.co/uWTpOI3oyE.

Anthropic is offering 13 AI courses & certificates. It's free by following these 13 links: 1 - Claude 101. Learn Claude for everyday work. Core features and best practices. ↳ https://t.co/OvBmlvnnBd 2 - AI Fluency: Framework & Foundations. The foundational thinking course. Must need. ↳ https://t.co/cObZdwBP8h 3 - Introduction to Agent Skills Build, configure, and share Skills in Claude Code — reusable instructions Claude applies automatically. ↳ https://t.co/wZsD0PxbGK 4 - Building with the Claude API Full spectrum: function calling, tool use, streaming, SDKs, and production patterns. ↳ https://t.co/RcCbfNiNK1 5 - Claude Code in Action Integrate Claude Code into your dev workflow. Hands-on, practical, ship-focused. ↳ https://t.co/y29CC0G3lf 6 - Intro to Model Context Protocol Build MCP servers and clients from scratch in Python. Tools, resources, and prompts. ↳ https://t.co/Qnrn0NGZJa 7 - MCP: Advanced Topics Sampling, notifications, file system access, and transport for production MCP servers. ↳ https://t.co/0S5f4kEkK8 8 - AI Fluency for Students AI skills for learning, career planning, and academic success through responsible collaboration. ↳ https://t.co/YIOopqnA73 9 - AI Fluency for Educators For faculty and instructional designers applying AI Fluency into teaching and institutional strategy. ↳ https://t.co/54oLlYjdR5 10 - Teaching AI Fluency Teach and assess AI Fluency in instructor-led settings. Curriculum-ready. ↳ https://t.co/fHdgs6ufOe 11 - AI Fluency for Nonprofits Increase organizational impact and efficiency while staying mission-true. ↳ https://t.co/xFKngNysjO 12 - Claude with Amazon Bedrock The full AWS accreditation course, now open to everyone. ↳ https://t.co/dV6xi7TKld 13 - Claude with Google Cloud's Vertex AI Work with Claude through Google Cloud's Vertex AI, from setup to production. ↳ https://t.co/MEzAxODi6w 14 - How to master AI with words (not code) Shameless plug: it's my own (free) newsletter. Join 369,000+ weekly readers at https://t.co/psB7XxAv8w. I made https://t.co/jw2qdIbLxJ to start mastering Claude. And then https://t.co/uWTpOI3oyE to master Claude Cowork. ♻️ Repost this to help others access AI courses.

I tested Sora vs. the new Google Veo-2. I feel like comparing a bike vs. a starship:

Andrej Karpathy says you should learn AI depthwise, not breadthwise. Most education is breadthwise: watch lectures, memorize formulas, and trust you'll need it later. Karpathy flips this by learning "depthwise, on demand." What this means: Pick a project, start building, and learn exactly when you hit a wall. When he created a tutorial on transformers (the architecture behind ChatGPT), he didn't start by explaining attention mechanisms or complex architectures. Instead, he started with the simplest possible thing: a lookup table that predicts the next word. You build that first. Then you try to make it handle more complex patterns. And it breaks. Only then, when you've felt the limitation, does he introduce the next concept. Each piece solves a problem you've actually encountered. As he puts it: "It's a dick move to present the solution before I give you a shot to try it yourself." When you attempt the problem first, the solution actually makes sense. Teaching forces you to learn. "If I don't really understand something, I can't explain it." When you try to explain and stumble, you've found the gaps in your understanding. ... Build a project that gives you a reward. Hit a wall. Learn just enough to solve it. Then explain it to someone else. Don't consume content. Build the code. That's how you actually learn.

You're using Claude wrong. Here's my (exact) setup before I even prompt: Step 1. Download Claude and open Cowork → Go to Claude. com/ download. → Install the desktop app. → Click the Cowork tab at the top. → You need a Pro plan ($20/mo). Worth it. → Full guide here: https://t.co/g6oLzWSOuo --- Step 2. Select the right model (don't skip this) → Click the model dropdown. → Select "Opus 4.6." → Turn on "Extended Thinking." → Never change these. Wrong model = bad output. --- Step 3. Build your folder → Create one master folder on your computer. → Inside it, create 4 subfolders: ✦ ABOUT ME - who you are + how you write ✦ PROJECTS - one subfolder per live project ✦ TEMPLATES - your best work as structures ✦ OUTPUTS - where Claude saves finished files → Upload this folder. That's how it reads you. --- Step 4. Create 3 context files inside ABOUT ME → These replace prompting. This is the setup. → Create them as .md files. Plain text, saved as .md ✦ about-me.md - what you do day-to-day. ✦ my-voice.md - tone, phrases you hate, 3 example ✦ my-rules.md - ask first, show a plan, get approval OR Simply download my .md files here: https://t.co/psB7XxAv8w Subscribe for free. Open my welcome email. Hit the automatic reply button inside. --- Step 5. Set Global Instructions (once, forever) Go to Settings → Cowork → Edit Global Instructions. → Paste: "I'm [Name], [Role]. Read my files before every task. Ask clarifying questions before executing. Show a plan before acting. Never delete without my approval." → You set this once. It runs every session. → Your prompts can now be 10 words long. --- Before your next Cowork session, check these: 1. Am I in Cowork (not Chat)? 2. Is Opus 4.6 + Extended Thinking on? 3. Did I point it to my folder with context files? Set these first. Then prompt. Top 1% of Claude users do this. Now you can too.

+ how to set up your Claude Cowork folder (once and for all) with this article:

How to make slides with Claude: 1. Task ☑ Define what you want & what success looks like: "I want to build a pptx presentation so that [SUCCESS CRITERIA]." No "make me a deck about X." ↳ That's how you get 10 slides of nothing. 2. Context Files ☑ Upload your expertise and rules as files: "First, read these files completely before responding: [filename.md] — [what it contains]." Stop re-explaining your brand, your audience, your standards every single time. Put it in files. 3. Reference ☑ Show what you're aiming for. Upload an example. "Here is a reference to what I want to achieve: [filename]." No short prompts and hoping AI figures it out. 4. Research ☑ Claude searches before touching a single slide: "Search the web using at least 5 varied searches (trends, data, expert opinions, case studies, counterarguments)." It saves a structured research brief, organized by theme, with source URLs and key data points pulled out. I like to add: "Prioritize 2025–2026 sources. Flag anything where sources conflict or data is thin." 5. Slide Brief ☑ Turn research into a slide-by-slide outline: "Each slide gets: a title, 3 key points, and any specific data/stats from the research that must appear on that slide." No full paragraphs. Gamma will write the final text. Just give it enough structure and data to work with. 6. Rules ☑ Don't jump into making slides (yet): "Do not generate slides yet." "Do not write full paragraphs." A step-by-step approach takes longer, but makes (much) better slides. If you want to be faster, just go straight to Gamma. 7. Generate ☑ Pass the outline to Gamma as a presentation: "Pass gamma-outline.md to Gamma as a presentation using textMode 'generate'. Use theme: [your brand theme name]." Claude connects to Gamma for you. Like magic. 8. Theme ☑ Make sure to use your Gamma theme: "Use theme: [your brand theme name]." If you don't know how, I made a guide for teams at https://t.co/L0bPMgWEsy (scroll to the bottom). After generating, review card by card: → Would I say this out loud? → Does this card earn its place? → Is the data right? 9. Alignment ☑ The prompt starts by asking YOU questions. "Start by using AskUserQuestion to make sure you have enough context from me before researching." Nothing starts until you're both on the same page. This replaces the old prompting era. I teach you how Claude works at https://t.co/uWTpOI3oyE. Copy the full prompt template + download my personal .md files for Claude by following this: Step 1: Subscribe for free → https://t.co/psB7XxAv8w. Step 2: You will have two choices: free or paid. Step 3: Choose the free tier. Don't pay for anything. Step 4: Open your welcoming email (wait 30 sec). Step 5: Access my entire prompt library & md files.

Claude 101 for dummies, from a dummie.

The world's leading AI research center completed the most comprehensive study ever on kids and AI. They surveyed 1,800+ children, parents, and teachers in UK. Here's what they found: (spoiler: children are outsmarting adults on AI)

BREAKING: a new Chinese model is out. And no. This is NOT DeepSeek. Meet Qwen-2.5, from the giant Alibaba: 1. It can code, write text, search the web. 2. It can generate images, like Dall-E. 3. It can even generate videos. Here's everything you need to know:

BREAKING: Apple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well. Here's what Apple discovered: (hint: we're not as close to AGI as the hype suggests)

BREAKING: Stanford just surveyed 1,500 workers and AI experts about which jobs AI will actually replace and automate. Turns out, we've been building AI for all the WRONG jobs. Here's what they discovered: (hint: the "AI takeover" is happening backwards)

I tested Sora vs. the new Google Veo-2. I feel like comparing a bike vs. a starship:

BREAKING: a new Chinese model is out. And no. This is NOT DeepSeek. Meet Qwen-2.5, from the giant Alibaba: 1. It can code, write text, search the web. 2. It can generate images, like Dall-E. 3. It can even generate videos. Here's everything you need to know:

chatgpt loves stupid words & I am sick of seeing them all over the web. I wrote a piece of prompt to avoid this "dive", "realm", "unveiling" madness. ↓ And it worked pretty nicely:

Elon promises AGI paradise where work becomes optional, but Mouse Utopia already delivered that in 1968 with infinite resources and every mouse died anyway. What killed them might kill us too. In 1968, psychologist John B. Calhoun built a "rodent paradise" with 256 nestboxes, unlimited resources, and no disease. He introduced four breeding pairs and watched them thrive. At first. Population doubled every 55 days. Social structures formed and everything looked normal. Then the crowding hit. By Day 315, defeated males gathered in the center. They were fighting, biting, and purposeless. Stressed mothers abandoned their young and infant mortality spiked to 96%. Despite unlimited food, the social fabric was tearing apart. Phase D was the behavioral sink: - Two-thirds became withdrawn outcasts - One-third turned hyper-aggressive - Females grew violent toward pups Then came the "Beautiful Ones." These are the males who spent entire days grooming themselves, ignoring mating or territory defense entirely. (incels or looksmaxxing guys today) They were physically perfect. But psychologically, they were destroyed. Births ceased. The last generation never learned social skills, and the colony went extinct. Calhoun concluded: "The death of their spirit preceded the death of their bodies." The main problem was lack of purpose. Let's make some parallels today. Elon Musk predicts AI + robotics will create "universal high income" which is an economy so abundant that work becomes optional and material needs vanish. He calls it an "infinite money glitch." But the question that immediately comes to mind is: "What do people do with all that extra time?" AGI would give us Mouse Utopia at scale. It would give us unlimited resources, zero material struggle, and every physical need met. And if you think you won't experience AGI in your lifetime, well, think again. Look at the current data: > High-income nations report 15% lifetime depression rates vs. 11% in poorer countries > North America leads the world in "deaths of despair", i.e. overdoses, alcoholism, suicide among young adults ages 25–34. > U.S. fertility dropped from 2.1 (replacement rate) in 2007 to 1.6 in 2023. > Young men increasingly withdraw into gaming, isolation, disengagement, the modern "Beautiful Ones." Every previous revolution (farms > factories > computers) displaced labor but humans moved up the skill ladder. AGI threatens to replace every cognitive task. When machines think, create, and plan as well as we do, there's nowhere "higher" to go. For the first time in history, innovation might eliminate human necessity entirely. Calhoun believed better environmental design could preserve social health by giving individuals meaningful roles even in abundance. If we build a world where AI solves everything, we must deliberately inject challenge, creativity, and community into lives. Meaning: > Competitive domains beyond AI's reach (philosophy, art, wilderness, space) > Universal education focused on fulfillment, not job training > Civic structures that create purpose If AGI grants us automatic comfort, will we remember why we're here? Mouse Utopia serves as a perfect example that comfort without purpose isn't paradise. It feels good for a bit, but ultimately: It's the path to extinction.

BREAKING: claude 3 is live since 1h. They claim to be better than gpt-4. So I ran my own little test: test #1 → copy the UI of a website

AI is eating up consulting. I used 3 prompts on ChatGPT to mimic a $600/hour consultant, achieving in 4 hours what takes weeks for teams. Here's how to make ChatGPT your pocket-sized McKinsey consultant: (my exact prompt + examples)

I manage my employee's Linkedin. We went from 0 to 3,836,555 impressions in exactly 178 days of daily posting. The trick is... I didn't write any posts. I do this instead:

New research just dropped: this prompting technique cuts AI hallucinations by 50%. It's called Model-First Reasoning. Instead of asking "How do I solve [xxx] problem?" You first force the AI to list: what's involved, what can change, what actions are possible, and what's not allowed. THEN you ask it to solve using only what it wrote down. So what makes this different from Chain-of-Thought? CoT lets the AI think and solve, but at the same time. It sounds smart. It flows well. But it makes stuff up along the way. Model-First Reasoning creates a hard wall instead. Define first. Solve second. No mixing. The AI can ONLY use what it wrote down in step one. That's the trick. The researchers tested it on medical scheduling, route planning, resource allocation, and logic puzzles. Same pattern everywhere: fewer broken rules, more consistent outputs. Why it works: ✦ LLMs make things up because they assume stuff you never told them. ✦ When you force them to write everything down first, there's nowhere to hide. ✦ It makes a stronger case for why "Human-in-the-loop" works much better, too: we make sure every step is validated before going to the next. You can read the paper here: https://t.co/vTuQvsNyCk.

gpt-4o claims to outperform claude opus. I don't trust benchmarks. So I ran my own tests: test #1 → analyze a 42-page PDF

Anthropic is offering 13 AI courses & certificates. It's free by following these 13 links: 1 - Claude 101. Learn Claude for everyday work. Core features and best practices. ↳ https://t.co/OvBmlvnnBd 2 - AI Fluency: Framework & Foundations. The foundational thinking course. Must need. ↳ https://t.co/cObZdwBP8h 3 - Introduction to Agent Skills Build, configure, and share Skills in Claude Code — reusable instructions Claude applies automatically. ↳ https://t.co/wZsD0PxbGK 4 - Building with the Claude API Full spectrum: function calling, tool use, streaming, SDKs, and production patterns. ↳ https://t.co/RcCbfNiNK1 5 - Claude Code in Action Integrate Claude Code into your dev workflow. Hands-on, practical, ship-focused. ↳ https://t.co/y29CC0G3lf 6 - Intro to Model Context Protocol Build MCP servers and clients from scratch in Python. Tools, resources, and prompts. ↳ https://t.co/Qnrn0NGZJa 7 - MCP: Advanced Topics Sampling, notifications, file system access, and transport for production MCP servers. ↳ https://t.co/0S5f4kEkK8 8 - AI Fluency for Students AI skills for learning, career planning, and academic success through responsible collaboration. ↳ https://t.co/YIOopqnA73 9 - AI Fluency for Educators For faculty and instructional designers applying AI Fluency into teaching and institutional strategy. ↳ https://t.co/54oLlYjdR5 10 - Teaching AI Fluency Teach and assess AI Fluency in instructor-led settings. Curriculum-ready. ↳ https://t.co/fHdgs6ufOe 11 - AI Fluency for Nonprofits Increase organizational impact and efficiency while staying mission-true. ↳ https://t.co/xFKngNysjO 12 - Claude with Amazon Bedrock The full AWS accreditation course, now open to everyone. ↳ https://t.co/dV6xi7TKld 13 - Claude with Google Cloud's Vertex AI Work with Claude through Google Cloud's Vertex AI, from setup to production. ↳ https://t.co/MEzAxODi6w 14 - How to master AI with words (not code) Shameless plug: it's my own (free) newsletter. Join 369,000+ weekly readers at https://t.co/psB7XxAv8w. I made https://t.co/jw2qdIbLxJ to start mastering Claude. And then https://t.co/uWTpOI3oyE to master Claude Cowork. ♻️ Repost this to help others access AI courses.

Sam Altman yesterday: "[gpt-5] is gonna steamroll you"

The Anatomy of a Claude 4.6 Prompt: 1. Task Define what you want & what success looks like: "I want to [TASK] so that [SUCCESS CRITERIA]." No roles, "act as a senior expert." That era is over. 2. Context Files Upload context files with your expertise and rules: "First, read these files completely before responding: [filename .md] - [what it contains]." AI went from reading a sticky note to an entire book. Stop explaining yourself in the prompt. Put it in files. 3. Reference Show AI exactly what you want. Upload an example. Then give patterns, tone & structure as rules. No "give me something like" & hoping AI figures it out. 4. Brief This is the only part you actually type from scratch. Everything else is files. "Type of output + length. Does NOT sound like. Success means." 5. Rules Context file holds your standards, taste & audience. Prompt: "Read it fully before starting. If you're about to break one of my rules, stop and tell me." 6. Conversation You spent 3 years prompting AI. Now it prompts you Prompt: "DO NOT start executing yet. Ask me clarifying questions (use 'AskUserQuestion' tool) so we can refine the approach together step by step." 7. Plan Claude read your files before writing a single word. Prompt: "Before you write anything, list the 3 rules from my context file that matter most for this task. Then give me your execution plan." 8. Alignment Nothing happens until you both see the same aim. This replaces the old prompting era. Prompt: "Only begin work once we've aligned." Copy the full prompt template + download my personal md. files for Claude here: https://t.co/psB7XxAv8w.