@0x_fokki the part that got me: it rendered a still and fixed the gaps for 3 rounds before touching the film. that's exactly what most people skip. how long did the whole thing take?
the 4 prompts (paste one per new chat):
AI AGENT:
A highly detailed 3D animated feature film character design of an AI AGENT, a fully modeled 3D character that looks ready to drop into a video game or animated movie. A small friendly robot with a large round helmet-like head, a glossy black face screen with big glowing blue pixel eyes, a short antenna, scuffed off-white armor panels with visible wear and dents, standing confidently with hands on hips. Beside it: a long paper scroll checklist unrolling onto the floor with exactly 12 lines, numbered 1 to 12 in correct order, each with an empty checkbox and a blank line, numbers clean and readable with nothing skipped or repeated; on the other side a worn retro computer terminal showing a ">_" prompt, with a glowing blue holographic loading ring floating above it. Realistic material wear, subsurface shading, no logos anywhere, rendered in a modern 3D engine, cinematic 3D rendering, soft studio lighting with gentle rim light, full-body composition, clean white background, vertical 4:5
PROMPT ENGINEER:
A highly detailed 3D animated feature film character design of a PROMPT ENGINEER, a fully modeled 3D character that looks ready to drop into a video game or animated movie. A thoughtful young man with curly brown hair, round wire glasses and light stubble, a yellow pencil tucked behind his ear, one hand on his chin and a knowing half-smile, wearing a chunky dark green knit cardigan with a Fair Isle pattern over a cream button-up shirt, rolled-up brown corduroy trousers with a leather belt, worn brown leather lace-up boots. At his feet: a large unrolled parchment scroll with the handwritten words "You are an expert..." clearly legible, a brass magnifying glass, and a stack of old leather-bound books with a yellow sticky note on top that reads "be concise". All text spelled exactly as written. Rich fabric fibers, realistic material wear, detailed cloth folds, subsurface skin shading, no logos anywhere, rendered in a modern 3D engine, cinematic 3D rendering, soft studio lighting with gentle rim light, full-body composition, clean white background, vertical 4:5
VIBE CODER:
A highly detailed 3D animated feature film character design of a VIBE CODER, a fully modeled 3D character that looks ready to drop into a video game or animated movie. A relaxed young developer with messy dark curly hair, light freckles, sleepy half-closed eyes and a smug little smile, hands in the pockets of an oversized charcoal hoodie, over-ear headphones resting around his neck, baggy olive cargo pants, chunky plain cream sneakers. Next to him on the floor: an open laptop showing a code editor on one side and a photo gallery preview on the other, three crumpled paper coffee cups (one tipped over) and a yellow rubber duck. Rich fabric fibers, realistic material wear, detailed cloth folds, subsurface skin shading, plain unbranded sneakers and laptop, no logos, no brand marks, no stripes or symbols anywhere, rendered in a modern 3D engine, cinematic 3D rendering, soft studio lighting with gentle rim light, full-body composition, clean white background, vertical 4:5
STARTUP FOUNDER:
A highly detailed 3D animated feature film character design of a STARTUP FOUNDER, a fully modeled 3D character that looks ready to drop into a video game or animated movie. A confident young man with tousled dark brown hair and light stubble, gazing upward with a visionary, slightly dreamy look, wearing a black ribbed turtleneck sweater, slim dark grey jeans and plain white sneakers. He holds a smartphone in one hand and hugs a printed pitch deck to his chest with the word "AI-powered" on the cover above a small mountain photo. Behind him: a whiteboard on an easel with a hand-drawn bar chart and an arrow shooting up and to the right. To the side: a small round wooden side table with a potted green plant, a plain silver energy drink can, a spiral notebook and a pen. All text spelled exactly as written. Rich fabric fibers, realistic material wear, detailed cloth folds, subsurface skin shading, plain unbranded phone, can and sneakers, no logos anywhere, rendered in a modern 3D engine, cinematic 3D rendering, soft studio lighting with gentle rim light, full-body composition, clean white background, vertical 4:5
I PAID FOR TWO IMAGE MODELS. THE FREE ONE WON.
same 4 prompts, 4 models, first attempt only. no rerolls
the test: 3D animated characters for tech jobs, with text that has to come out right. a scroll that says "You are an expert...", a sticky note that says "be concise", and a robot next to a checklist numbered 1 to 12
→ GPT (paid): 4/4 clean. every word, every number
→ Grok (paid): broke the checklist. 10, 10, 11, 12, 12. then a second list that skips 3, 7, 9 and 11
→ Gemini (free): broke it too. 9, 9 ... 12, 12. plus fake scribbled text under "You are an expert..."
→ Copilot (free): 1 to 12 in order, every word right, and the most "animated movie" look of the four. it did add the job titles on its own
counting to 12 turned out to be the real test. half the models couldn't do it
my pick for this style: Copilot. free, and on par with paid GPT
all 4 prompts in the reply ↓
@steipete The rule itself might be reasonable, but shipping it silently with no toggle is what makes people nervous. Has anyone seen it documented anywhere?
@PJaccetturo $28K and 62 million views is a better return than most studio films 😂 What took the biggest chunk of the budget, the generations or the edit?
@fluid_ai_ Native sound is the part that got me. A world that hears itself feels way more alive than one that just looks right 🌊 Did you find anything on how long the memory actually lasts before it forgets?
@AIBoticssq Feels more like a correction than a pop to me. The compute is real, the open question is how long investors wait for revenue to catch up 📉 What timeline would you give it?
@0xzivo Seeing the formula makes surge feel a lot less random 🤯 Same 2x demand can mean a small bump or a crazy multiplier, all down to those elasticities. Do they still cap it during emergencies after the 2013 backlash?
# DESIGN.md
## Feel
Warm, calm, editorial. Like a printed menu from a good café, not a SaaS dashboard.
## Color
- Background: #F6F0E6 (cream)
- Text: #2B1D14 (espresso)
- Muted text: #7A6A5C
- Accent: #C2410C (ember), use it for one thing per screen: the main button or one highlight
- Lines: #2B1D14 at 15% opacity
- No gradients. No purple. No glow.
## Type
- Headlines: Charter, Georgia, serif. Big and tight: hero 88px, line-height 0.95, letter-spacing -0.02em
- Body: Inter, 17px, line-height 1.6
- Small labels: Inter, 12px, uppercase, letter-spacing 0.12em
- Max line length 60 characters
## Layout
- Left-aligned, never centered heroes
- 12-column grid, 1200px max width, 32px gutters
- Spacing on an 8px scale: 8, 16, 24, 48, 96
- Sections separated by thin full-width lines, not by background color changes
## Components
- Buttons: solid accent, 2px corners, no shadow. Secondary: text link with an arrow
- Cards: no cards. Use columns with a number on top (01, 02, 03) and a line above
- Icons: none. No emoji
- Prices: big serif numbers, the unit small next to them
## Don't
- No "Welcome to", no "Elevate your…", no exclamation marks
- No stock 3-column cards with icons in circles
- No shadows heavier than 0 1px 0
STOP ASKING CLAUDE FOR "A CLEAN MODERN DESIGN". GIVE IT A DESIGN.md
same prompt, same model, two runs. the only difference is a 35-line file called DESIGN.md
the prompt: "build a landing page for Ember & Oak, a small coffee roastery. hero, three features, pricing, footer. one HTML file"
first: prompt only. purple gradient, centered hero, emoji in circles, "Welcome to...". the page you get when you give the model nothing to go on
then: same prompt + DESIGN.md
what's inside the file:
→ 5 colors with hex codes, and only one accent allowed per screen
→ 2 fonts with exact sizes: serif headlines at 88px, body at 17px
→ layout rules: left-aligned hero, 8px spacing scale, thin lines instead of cards
→ components: buttons with 2px corners, no shadows, prices as big serif numbers with the unit small next to them
→ a don't list: no gradients, no purple, no emoji, no "Welcome to"
→ the feel in one line: "a printed menu from a good café, not a SaaS dashboard"
the don't list is the part I'd never skip. tell the model what to avoid and it stops reaching for the same defaults
write it once, drop it into every project, and every new page starts from your style instead of the model's
the full DESIGN.md is in the reply ↓
Claude - Grid Effect on a dancing robot
one 10-second dance clip, three prompts, zero video editors. I had Claude write the code that slices the frame into a 6x7 grid and finds the beats in the track (19 of them). Beat Grid and Glitch Spread rendered in under 40 seconds each. Time Echo took 51, because every outer cell pulls frames from the past instead of the present
in order: Beat Grid, Glitch Spread and Time Echo
prompts:
1. Make a vertical music video exactly as long as the track. Split the frame into near-square cells with thin grey lines so the clip still reads as one picture. The middle cells play the clip in sync, each with its own look. Cool blue palette. The outer cells change their look on every beat: halftone, RGB split, scanlines, pixels. Words spell out across a row, one letter per cell. Keep the robot recognizable the whole time
2. Same grid. On every beat two cells glitch and the effect spreads to their neighbors like a chain reaction, then fades out, always revealing the clip underneath. Hot pink and red, words run down a column
3. Same grid. The center plays in real time while the outer cells replay the same moment with delays, reversals, freeze frames and stutters, so time ripples outward from the robot on every hit. Warm amber, words fall along a diagonal
the track is a free one from Pixabay