Opus 5.5 + /anatomy-reveal is f*cking insane for motion design • Real 3D anatomy reveals from a photo or name • Exploded views with moving parts • Clean motion films with typography, blur, and studio-level transitions This is basically a motion design studio inside Claude Send these skills to your Claude: typingmind.com/skills/annngu… skills.wheresryan.sh/anatomy

Andrej Karpathy: "Prompting is going away. Delete everything, keep Graph." In just 69 minutes, he shows how to build graphs and why they're the only layer that survives in the end Prompts → Agents → Loops → Graphs a loop keeps one agent running until the job is done a graph decides which agents exist and what each one passes to the next anyone can build an agent, almost nobody builds the graph that runs them watch it today, then save the full guide on graphs below before everyone starts catching up ↓

this is seriously getting out of hand. someone figured out that the most powerful way to use Grok and Claude Opus isn't to ask them questions. it's to make them investigate each other's answers. and the interface looks like something out of a classified intelligence agency. it's called ECLIPSE. most people still open ChatGPT, ask one question, trust the answer and move on. this takes the exact opposite approach. Grok hunts for information. Opus tries to find everything wrong with it. neither gets to call something a discovery until the other has challenged it. the entire setup comes down to 4 moves: → give Grok one question: "what's happening right now that almost nobody is paying attention to?" → let it connect news, market movements, public data and seemingly unrelated events → send those connections to Opus, whose only job is to attack the reasoning, look for missing evidence and expose weak conclusions → put everything into one intelligence terminal where the strongest connections rise to the surface and the noise disappears now look at the screen. every node is a potential connection. every line is a relationship worth questioning. every anomaly is something that might deserve a closer look. and here's what people are missing: the advantage isn't having the smartest AI. it's having two different AIs that aren't allowed to blindly agree. one searches. one challenges. you investigate what survives. no copying answers between 12 tabs. no reading the same explanation rewritten five different ways. no pretending a confident answer is automatically a correct one. 2 models. 1 intelligence terminal. an entirely different way to investigate information. we spent the last three years learning how to talk to AI. the next shift is learning how to make AI systems question each other. and most people are still arguing over which chatbot is better. steal this and read full guide below

Andrej Karpathy: "Prompting is slowly fading away Delete everything else and keep the graph" In this 1-hour lecture, he explains how to build graphs and why they're the layer that survives The part most people overlook: LLMs → Prompts → Agents → Graphs Everything before the graph is just another step The graph is where the system eventually ends up Watch it first Then read the full guide on graph engineering below

Dylan Field (Figma CEO) just released a prompt that turns Opus 5.5 into a design-to-code factory that actually builds and ships working apps from Figma designs. It's f*cking unreal... Send it to Opus 5.5, and thank me later. Then read the full guide for Opus 5.5 Design-to-Code Engineering.