Grafollogy

@elonmusk are you preparing for it to be replaced by AI?

The matrix was reprogrammed

🎨 The Grok Imagine Prompting Cheat Sheet Stop letting AI guess your camera angles. Most people prompt "Cool cyberpunk character" and get the same boring medium shot every time. To get cinematic results, like the shots in the video below, you need to speak the director's language. I broke down the specific Shot Types into a copy-paste formula for Grok. ⚠️ Pay attention to the "Mistake" section at the bottom, it solves the two most annoying AI habits. Steal the cheat sheet below. 👇 Formula: (Shot Type) + (Art Style) + (Character) + (Clothing) + (Style Details) 1. 📐 Shot Type (The Frame) • Establishing Shot: Far away, environment focus. ⚠️ PRO TIP: If the AI zooms in too close, describe your character as a "tiny silhouette" to force the camera back. • Full Shot: Head to toe. Best for showing off outfits. ⚠️ PRO TIP: If it cuts off the legs (landscape mode), describe the boots and the floor to force the full frame. • Medium Shot: Waist up. The standard "dialogue" shot. • Close-Up: Head and shoulders. Focuses on emotion. • Extreme Close-Up: Macro focus on a specific detail (eye, ring, scar). 2. 🎨 Art Style • 90s Anime Cel-Shaded • Cinematic 35mm Film Photography • Digital Concept Art (Unreal Engine 5) • Dark Fantasy Oil Painting 3. 👤 Character • Cybernetic Street Samurai • High-Elf Diplomat • Noir Detective 4. 🧥 Clothing • Holographic flight jacket • Tattered ceremonial robes • Tactical ballistic vest 5. ✨ Extra Style Details • Volumetric fog & God rays • Golden Hour lighting • Film grain 📋 Copy-Paste Examples • The Scene Setter (Establishing Shot): "Extreme wide establishing shot of a massive fantasy metropolis built into a cliffside. In the distance, a tiny silhouette of a traveler stands on a bridge. Cinematic lighting, epic scale." • The Outfit Showcase (Full Shot): "Full shot of a 90s Anime style Mech Pilot wearing an orange flight suit and heavy magnetic boots, standing on the concrete hangar floor. Cel-shaded details, industrial lighting." • The Emotion (Close-Up): "Close-up of a Hyper-realistic Soldier, intense stare, mud splatters on face, 8k resolution, dramatic shadows." 🛑 Troubleshooting: Common Mistakes & Fixes Mistake #1: The "Vanity" Zoom (Establishing Shot) ❌ Bad Prompt: "Establishing shot of a Cyberpunk hacker wearing a black trench coat with blue neon circuit patterns, high collar, and tactical gear." Why it fails: You described the clothing details too much. The AI panicked and zoomed in to show you the "neon patterns," ignoring your request for a wide shot. ✅ The Fix: "Extreme wide establishing shot of a massive Cyberpunk city. In the distance, a tiny silhouette of a hacker stands on a rooftop." (Describe the environment, not the clothes). Mistake #2: The "Missing Legs" (Full Shot) ❌ Bad Prompt: "Full shot of an anime pilot standing in a hangar." Why it fails: In landscape images, AI hates leaving empty space on the sides. It naturally zooms in to the waist (Cowboy Shot) to fill the frame, cutting off the feet. ✅ The Fix: "Full shot of an anime pilot wearing heavy magnetic boots, standing on the concrete hangar floor." (Describe the footwear and the ground to force the AI to render the bottom of the image).

Ever wondered why the longer your chat grows, the stupider the AI becomes? It might be because you don't understand how context windows work. Let me enlighten you:

If this Karpathy interview doesn't pop the ai bubble, nothing will. 10 brutal quotes: 1. LLMs don’t work yet They don’t have enough intelligence, they’re not multimodal enough, they can’t use computers, and they don’t remember what you tell them. They’re cognitively lacking. It’ll take about a decade to work through all of that. 2. When you boot them up, they always start from zero They have no distillation phase, no process like sleep where what happened gets analyzed and written back into the weights. 3. What’s stored in their weights is only a hazy recollection of the internet It's just a compressed blur of 15 trillion tokens squeezed into a few billion parameters. Their context window is just short-term working memory. 4. They’re good at imitation, terrible at going off the data manifold Too much memory, not enough reasoning. We need to strip away the memorized knowledge and keep the cognitive core: the algorithms, the magic of intelligence, problem-solving, strategy. 5. We’ve probably recreated a cortical tissue, pattern-learning and general, but we’re still missing the rest of the brain No hippocampus for memory. No amygdala for instincts. No emotions or motivations. 6. They memorize perfectly but generalize poorly If you give them random numbers, they can recite them back. No human can do that. That’s the problem: humans forget just enough to be forced to find patterns. 7. Anything truly new, code that’s never been written before, ideas that have no template; they stumble They’re still autocomplete engines with perfect recall and no understanding. Until we find that cognitive core, intelligence stripped of memory but full of reasoning, they’ll stay brilliant mimics, not minds.

@skulthorp It reminds me of this youtu.be/XmTV62mE1PA?si…

This feels like the local "he's nice but not quite right" man has mistakenly entered a "make a video about your community" competition via the local library that was actually intended for young schoolchildren

@HLTCO @AndyMitten

Fantastic from Brighton, this. A massively important message delivered very well.

@HLTCO @R_o_M

The bit at the end….worth watching and sharing.

Save this📍 Best iPhone camera settings for high-resolution photos and stunning 4K quality.

I’ve decided to try a little challenge - turn £1,000 into £10,000 with football bets. I’ll be betting c.10% of bank each time and will update this thread as I go along. I started yesterday with Man City to beat Wolves @ 1.53 so after commission my balance is £1,051.94

@FilmUpdates Moments when Quentin Tarantino drew inspiration from other films and made them his own

Anthropic Academy just released free online courses. No payment required. Here are 6 courses you don't want to miss in 2025:

This guy literally broke down every great AI tool

Introducing "AI for Advertising" A 10-part series on how to use @runwayml throughout the entire creative process: runwayml.com/ai-for-ads

what are large language models actually doing? i read the 2025 textbook "Foundations of Large Language Models" by tong xiao and jingbo zhu and for the first time, i truly understood how they work. here’s everything you need to know about llms in 3 minutes↓

Today we’re releasing GitHub Spark — a new tool in Copilot that turns your ideas into full-stack apps, entirely in natural language.

3 months ago, building an app required: - 6 months of development - $300K budget - Team of 5 devs - Prayer that nothing breaks Yesterday, I created and deployed CoachFlow in 22 minutes. Workflow: ChatGPT - Lovable - Supabase - Cursor step-by-step how:

Microsoft just released their list of the 40 jobs most AI-applicable and the 40 jobs least AI-applicable. This list may have overlap with replaceability and job transformation. (Phlebotomists, you've got nothing to worry about.)