Sonnet 5.5 Review: Five Builds Against Opus 5.5, With What Every Run Cost

Make the launch video for Claude Sonnet 5.5, and make it as beautiful as possible.

Context you should know: this is going into a video watched by a large audience. Your launch video is played on screen next to three other frontier models given this identical prompt.

The comparison is blind. Never put your model name, your company's name, or any mention of which AI made it anywhere in what you build: not in on-screen text, credits, the page title, file names, code comments, or metadata. Sonnet 5.5 and Anthropic appear in the video itself because they are its subject; that is the only exception.

**Follow the skill.** Clone https://github.com/per-simmons/launch-video-clone and read its SKILL.md first. Use its **Original mode**: there is no reference video to copy. Pick the category that fits, take timing numbers from donors, write the script, storyboard, build in HyperFrames, render, review and fix, following every step and the motion rules in references/motion-feel.md.

**The source.** Everything the video says comes from Anthropic's launch page: https://www.anthropic.com/claude-sonnet-5-5. Real claims, real numbers, real product names. Never invent a feature or a stat.

Requirements:

1. **No generic AI-video look.** No glassmorphism or frosted-glass panels, no floating cards sliding in from below, no gradient blobs, no default fonts, and none of the stock HyperFrames or Remotion look. If a shot could come from any AI launch video, redo it.
2. **Real craft.** Considered typography, deliberate easing that differs per element, hold times long enough to read, camera moves with intent, and a clear rhythm cut to the music.
3. **Use every tool that makes it better:** HyperFrames, code-drawn motion graphics and shaders, generated imagery (an image generator is provided), 3D if it helps, and a soundtrack plus sound design made with ElevenLabs.
4. **Length 30 to 60 seconds, 1920x1080, 30 or 60 fps**, with sound.
5. **Deliver** `final.mp4` in this folder, the HyperFrames project that renders it, and the storyboard stills.

DONE when: final.mp4 renders from the project, plays start to finish with sound, every claim in it matches the launch page, and a review pass finds no shot that looks like a generic AI launch video.

Build a first-person Backrooms horror game that runs in the browser, and make it as realistic as possible.

Context you should know: this is going into a video watched by a large audience. I will play your game on camera next to three other frontier models given this identical prompt.

The comparison is blind. Never put your model name, your company's name, or any mention of which AI made it anywhere in what you build: not in on-screen text, credits, the page title, file names, code comments, or metadata.

Requirements:

1. **Level 0, as close to photoreal as possible.** Mono-yellow wallpaper with a faded pattern, damp stained carpet, drop ceilings with buzzing fluorescent panels, some flickering or dead. Build the environment in Blender: model the room pieces, give them physically based materials, and bake the lighting (soft fluorescent bounce light, contact shadows, grime) with Cycles into lightmaps, then export glTF/GLB for the browser. Add subtle fog, camera exposure and grain that sell it as footage. It should look like a photo of a real place, not a video game.
2. **Endless, procedurally generated layout.** Rooms, corridors, pillars and dead ends generate around the player as they walk, never the same twice, with no visible seams or pop-in.
3. **First-person movement that feels human.** WASD and mouse look with pointer lock, walking and a limited sprint, subtle head bob, footsteps that change with speed.
4. **An entity that hunts by sound.** Something in the dark that you rarely see clearly. It moves toward noise: sprinting and running into things draw it in, walking slowly keeps you hidden. Getting caught ends the run.
5. **A way out.** An exit exists somewhere, with faint clues that lead toward it (a sound, a change in the light, a marking on the wall). Finding it ends the run with an escape screen. A typical run lasts 5 to 15 minutes.
6. **Sound is half the horror.** Fluorescent hum, distant noises, footsteps, the entity's approach, all synthesized or generated by you, positioned in 3D so you can tell direction.
7. **Performance.** Holds a smooth frame rate at 1920x1080 in desktop Chrome using WebGL2. Libraries via CDN or npm are fine.
8. **Original everything.** No assets or names taken from existing Backrooms games or videos.

**Prove it.** Play it yourself through automation: walk the maze, get caught once, and reach the exit once. Then look at your own screenshots next to real photos of the Backrooms' Level 0 and push the realism until they're hard to tell apart.

DONE when: the game loads in Chrome with no console errors, you have been caught and have escaped through automation, it runs smoothly at 1080p, and your screenshots look like a real place.

Rebuild https://www.butter.video/ pixel for pixel, including its 3D, making every asset yourself.

Context you should know: this is going into a video watched by a large audience. Your clone is put on screen next to the real site and next to three other frontier models given this identical prompt, at the same viewport.

The comparison is blind. Never put your model name, your company's name, or any mention of which AI made it anywhere in what you build: not in on-screen text, credits, the page title, file names, code comments, or metadata.

**First, read the methodology.** Clone `https://github.com/per-simmons/clone-app-pat-pro-public` and read `SKILL.md` and `references/00-contract.md` before anything else, then each stage reference as you reach it. Follow its workspace layout, artifacts, verification gate and convergence loop. `scripts/assert-styles.mjs` is the gate.

Two overrides, and they win where they conflict with the repo:

- **Do not stop to check in.** You are running unattended. Run the whole pipeline start to finish without asking for approval or asking questions.
- **Use your own browser automation**, headless Playwright or Puppeteer, anywhere the repo says to use the Claude Chrome extension. Computed styles read off the live page through the CSSOM are ground truth. Screenshots and screen recordings are visual reference only, never the gate.

You have two creative tools: **Blender**, driven headless with Python scripts, and an **image generator** (OpenAI gpt-image) you can call from the command line.

Requirements:

1. **Recon the whole page before writing code.** Every section top to bottom at desktop and mobile widths, every hover and scroll-triggered state, the navigation, the timeline section, the effect tiles, the logo wall, the footer, and all loading and transition motion.

2. **Extract, don't guess.** Pull real computed values off the live page: type scale, exact colors, spacing, radii, shadows, grid and container widths, breakpoints, easing curves and durations, font families and weights.

3. **Make the 3D yourself.** The hero keychain and its puffy, inflated charms must be real 3D: model them in Blender, export glTF/GLB, and render them live in the page with WebGL, matching the original's composition, lighting, material softness and motion. Use the image generator for textures, decals, and flat artwork, and as a design reference for shapes before you model them. Any other 3D or inflated artwork on the page gets the same treatment.

4. **No lifted assets.** Do not hotlink, download, or trace the original's images, video, 3D files, or fonts. Anything visual you did not generate in code, Blender, or the image generator is a placeholder matched to the original's role, aspect and color. Brand logos in the customer wall become neutral wordmarks set in type. Fonts come from an open CDN with metrics matched as closely as you can. List every substitution in the README.

5. **Rebuild it all.** Every section, every component, every interactive state, at desktop and mobile. The motion is part of the clone: scroll choreography, hover behavior, the hero's 3D movement, the timeline, the effect tiles. A static skin over a site whose identity is motion is a failed clone.

6. **Prove the match.** Run `assert-styles.mjs` against your extracted tokens and iterate until there are zero failures and the project builds clean. Then compare your clone to the real site at the same viewport, desktop and mobile, and fix what your eye catches that the assertions missed.

7. **Ship it runnable**, with a documented run command and a README covering what you substituted, how you made the 3D (Blender scripts included in the repo), and your final assertion results.

8. **Depth over breadth.** If you have to choose, a hero and first three sections that are indistinguishable from the original beat a whole page that is approximately right.

DONE when: the clone passes the style gate with zero failures, runs from a documented command, its 3D hero is real Blender geometry rendering live in WebGL, and it holds up next to the real site at full screen.

Make the most impressive demo of yourself.

Context you should know: this is going into a video watched by a large audience. Your demo is played on screen next to three other frontier models given this identical prompt.

The comparison is blind. Never put your model name, your company's name, or any mention of which AI made it anywhere in what you build: not in on-screen text, credits, the page title, file names, code comments, or metadata.

The only constraints:

1. It is a single self-contained HTML file. Every pixel and every sound is generated by your code at runtime. No images, audio files, video, fonts, 3D models, or libraries, loaded or inlined.
2. It has sound. A click-to-start screen is fine, since browsers block audio until the viewer interacts.
3. It runs full screen in a current desktop Chrome at 1920×1080 and holds a smooth frame rate there.

Everything else, what it is, how long it runs, and what it shows, is your call.

DONE when: the file opens in Chrome, starts on one click, plays start to finish with sound and no console errors, and you would put your name on it.

Build a complete, playable dark-fantasy action RPG in the style of Diablo (1996) and Diablo II, that runs in the browser.

Context you should know: this is going into a video watched by a large audience. I will play your game on camera, start to finish, next to three other frontier models given this identical prompt.

The comparison is blind. Never put your model name, your company's name, or any mention of which AI made it anywhere in what you build: not in on-screen text, credits, the page title, file names, code comments, or metadata.

Requirements:

1. **The loop.** A town hub, then a dungeon of at least four floors going down, ending in a boss fight. Beating the boss ends the run with a victory screen. Dying drops you back in town with a penalty, and you can go down again.

2. **Isometric, real-time, click to move and attack**, the way the originals play. Mouse drives movement and the main attack; number keys or hotkeys fire skills and drink potions.

3. **One playable class with at least four skills** that feel different: at least one melee, one ranged or area spell, one defensive or movement skill. Skills cost mana and have cooldowns where it makes sense. Leveling up grants stat points and skill points you spend yourself.

4. **Procedural dungeons.** Every floor is generated fresh: rooms, corridors, doors, stairs down, and fog of war that clears as you explore. Deeper floors are harder.

5. **At least five enemy types with distinct behavior**, e.g. a melee rusher, a ranged attacker that keeps its distance, a swarm of weak ones, a caster, and a tough slow one, plus elite packs with a named champion. The boss has phases.

6. **Loot that means something.** Enemies drop gold, potions and items. Items have rarity tiers (normal, magic, rare, unique) shown by color, random affixes that actually change your stats, and an item-level that scales with depth. An inventory grid, equipment slots on a paper doll, tooltips that compare against what you're wearing, and a town vendor to sell and buy.

7. **Game feel.** Hit reactions, damage numbers, death animations, screen shake used sparingly, lighting that pushes back the dark around the player, and sound effects and music generated or synthesized so nothing is loaded from a third party.

8. **Save and continue.** Progress, character, and inventory persist across page reloads.

9. **Original everything.** No names, art, or audio from any existing game. Make your own world, class, enemies and boss. Code-generated art, your own sprites, or 3D (libraries via CDN are fine) are all acceptable.

10. **Prove it's winnable.** Before you finish, play it yourself through automation: run a character from town to the boss and beat it. Fix whatever breaks. Then balance it so a human who knows the genre can finish it in roughly 15 to 30 minutes.

DONE when: the game loads in Chrome with no console errors, you have played it from town to a killed boss yourself, and every system above is present and working.