testarossa

ai researcher | content creator

dm open

[testarossa @rossaxbt]

OPUS 5.5 IS ALL YOU NEED FOR MOTION DESIGN

this launch video cost $0 and was made entirely with code

everyone else on X says the same shit, then sends you to a website or an MCP

this is completely free and uses 0 external tools
take the prompt and try it in your Claude ↓

<inputs>
Ask me for: a one-word brand name for the wordmark (a verb works best), 9 to 12 high-res photos, a royalty-free track around 120 BPM with a drop and a quiet breakdown (Mixkit, free for commercial use), and a free stock clip of a plain wall with moving plant shadows (Pexels).
</inputs>

<direction>
An Apple-keynote-style launch film, 2D only, in one continuous take. Each scene grows out of the last: no fades, blurs or cuts. Objects transform instead. Text rises from a mask line, icons spring up from zero, bars draw across the screen, pages push forward, and a black shape fills the frame before shrinking into the next scene. Use a warm off-white canvas, black UI and iOS 26 liquid glass over the photos. Archivo (wdth 125, weight 800) for the wordmark, Geist for the UI. A cursor triggers every change with actual clicks, drags and long-presses. Zoom the camera screen-studio style so each moment fills the square, and scale the cursor with it.
Banned: crossfades, blur-ins, brightness "developing", 3D flips, particles, glows, holds longer than 1s, anything that feels like a template.
</direction>

<structure>
120 BPM, 54 beats, with something happening on every beat.
Open: the wordmark compresses into its own period like an accordion. The dot expands into a black pill, and a label rises inside it. Click: six iris blades close over the label, then snap open onto a photo. The circle turns into a square and shrinks. A grid unfolds behind it like a paper map (center, plus, corners), rearranges into a bento, and a click zooms into one tile, landing right on the drop.
Glass: a glass word appears letter by letter, then melts into a droplet that stretches into a glass toolbar. The adjust icon turns it into a slider. Dragging changes the photo lighting from day to golden hour (two aligned shots), while the held knob becomes a glass lens. It rises into a glass orb, the next photo opens inside it as a circle, and the orb grows into a lock screen with glass clock digits, a date and a home bar that stretches into a glass music player.
Stage: the lock screen pulls back to reveal a phone, with the bezel growing from the screen edge. The Dynamic Island stretches like liquid, pinches off, flies across and expands into a Mac window that rolls up like a blind. Long-press the wallpaper and drag it onto a Safari tab. The page pushes in; when you drop the image, it becomes the hero of a landing page. Scroll: the hero transforms into a framed print on a product card, with the mat and molding growing from the photo's edge. Choose a frame color (it paints across) and a size, then the nav button flies down and becomes "Order print".
Order: one black shape keeps changing: Ordered ✓ → Printing % → On its way (a van on a route) → Delivered ✓.
Wall: the delivered circle expands until black fills the frame, holds for one beat, then shrinks into the framed print hanging in the real wall footage. The same iris opens onto the print and closes again. The frame fills the screen, contracts into the pill → the dot → the letters spring back out on the returning beat. Last frame = first frame.
</structure>

<build>
1. One HTML file, square 1440x1440. Compute every style from time inside an async seek(t): no CSS transitions, timers or state carried between frames.
2. Use closed-form step responses for springs. When a value has multiple targets, add one spring per change so it remains a pure function of time.
3. Liquid glass: each glass element keeps its own clone of the scene behind it. Filter that clone with an SVG feImage displacement map (a rounded-rect distance field) through three feDisplacementMaps at slightly different scales for chromatic edges, then add a rim light. For glass letters, use a canvas distance field per glyph to create the map, mask and highlights.
4. Goo: apply blur and an alpha threshold, then composite the source on top so the glass stays sharp inside.
5. Iris: place 6 blades around a hexagonal aperture. Each blade uses its two vertices, both edge extensions and the SHORT arc between them.
6. Wordmark squeeze: move every letter toward the dot by the same factor and adjust its drawn width to match (narrow the wdth axis, scale the rest), keeping the letters in contact.
7. Footage: re-encode it all-intra (ffmpeg -g 1), load it as a blob URL and await "seeked" before drawing each frame.
8. Sound: use a downloaded SFX for every event (Mixkit), never synthesized, and position each by its measured peak. Start the song on a downbeat: land the zoom on the drop, place the wall in the breakdown and bring back the wordmark with the beat. Loudnorm to -14 LUFS.
9. Render with Playwright: blend 4 subframes per frame using ffmpeg tmix at 60fps. Check one frame per beat, then look for single-frame pops (frame-difference spikes 3x higher than their neighbours).
</build>

<gotchas>
backdrop-filter: url() misreads displacement maps in Chromium, so clone the scene instead. A flood needs to extend beyond the corners and take about 0.3s; otherwise, half the screen changes in a single frame. A child set to visibility: visible can show through a hidden parent, so use inherit. Text swapping inside a morphing shape needs its own mask. python http.server can't range-seek video, so use the blob URL.
</gotchas>

<start>
Ask me for the inputs, then show me the beat map and 4 stills (open, glass, stage, wall) before writing the full film.
</start>

[rari @0xwhrrari]

Opus 5.5 can make a video

The hard part is making the next one better

That takes a studio, not a prompt

I broke down how to build it ↓ https://t.co/EXinI060Cr

[testarossa @rossaxbt]

opus 5.5 is insanely good at motion design

this whole video is code, with 0 after effects

i’m open sourcing the prompt template behind these motion designs

grab it and recreate them ↓

<inputs>
Ask me for: 8 to 12 UI states the shape should turn into (e.g. button, loader, player, slider, toggle, tabs, chart, command palette, toast), a pure black-and-white palette or one accent color, and a royalty-free track around 120 BPM (e.g. from Mixkit, free for commercial use).
</inputs>

<direction>
Dribbble-level UI motion. One shape, no cuts: each state is the same element changing size, radius and color, while its content swaps with a quick blur. A cursor triggers every change through actual clicks and drags. Use a light warm-gray canvas, black-and-white components and one clean UI font (Geist). Springs throughout, with only a slight overshoot. Zoom the camera so each state fills the frame. Match the final frame to the first for a seamless loop.
Banned: bouncy easing, particle bursts, glows, gradients on UI chrome, inconsistent icon strokes, dead time, anything that feels like a template.
</direction>

<structure>
120 BPM, 7 bars, with an action on every beat.
Button → loader → check → dynamic island → music player with a play/pause morph → scrub the progress bar → it turns into a volume slider that stretches when dragged past max → a toggle switches on the beat → its knob becomes a liquid tab indicator → the tabs expand into a chart that draws itself, with a tooltip on hover → it folds into ⌘K → type to filter → enter → toast → back to the button.
</structure>

<build>
1. One HTML file, square 1440x1440. Compute every style from time inside seek(t): no CSS transitions, timers or state carried between frames.
2. Use closed-form step responses for springs. If a value changes target multiple times, add one spring for each change so it remains a pure function of time.
3. Give the tab indicator’s two edges separate springs, letting the leading edge stretch ahead of the trailing one. Use the same approach for the toggle knob.
4. Make drags direct: while the cursor is held down, calculate the value from its position. On release, spring back from that position.
5. Analyze the song with numpy to find the beat grid and begin on a downbeat. Position each UI sound using its measured peak.
6. Render with Playwright: 4 subframes per frame, blended with ffmpeg tmix for motion blur at 60fps.
7. Render one frame per beat before the full render. Fix anything off-grid, cramped or difficult to read.
</build>

<gotchas>
Don’t use will-change on anything the camera scales, or the text will look blurry. Text swapping inside a morphing container needs separate enter and exit timing to avoid overlap. Make the final frame identical to the first including cursor position and speed or the loop will stutter.
</gotchas>

<start>
Ask me for the inputs, then show me the state list on the beat grid before writing any code.
</start>

[testarossa @rossaxbt]

opus 5.5 is insanely good at motion design

this whole video is code, with 0 after effects

i’m open sourcing the prompt template behind these motion designs

grab it and recreate them ↓

<inputs>
Ask me for: 8 to 12 UI states the shape should turn into (e.g. button, loader, player, slider, toggle, tabs, chart, command palette, toast), a pure black-and-white palette or one accent color, and a royalty-free track around 120 BPM (e.g. from Mixkit, free for commercial use).
</inputs>

<direction>
Dribbble-level UI motion. One shape, no cuts: each state is the same element changing size, radius and color, while its content swaps with a quick blur. A cursor triggers every change through actual clicks and drags. Use a light warm-gray canvas, black-and-white components and one clean UI font (Geist). Springs throughout, with only a slight overshoot. Zoom the camera so each state fills the frame. Match the final frame to the first for a seamless loop.
Banned: bouncy easing, particle bursts, glows, gradients on UI chrome, inconsistent icon strokes, dead time, anything that feels like a template.
</direction>

<structure>
120 BPM, 7 bars, with an action on every beat.
Button → loader → check → dynamic island → music player with a play/pause morph → scrub the progress bar → it turns into a volume slider that stretches when dragged past max → a toggle switches on the beat → its knob becomes a liquid tab indicator → the tabs expand into a chart that draws itself, with a tooltip on hover → it folds into ⌘K → type to filter → enter → toast → back to the button.
</structure>

<build>
1. One HTML file, square 1440x1440. Compute every style from time inside seek(t): no CSS transitions, timers or state carried between frames.
2. Use closed-form step responses for springs. If a value changes target multiple times, add one spring for each change so it remains a pure function of time.
3. Give the tab indicator’s two edges separate springs, letting the leading edge stretch ahead of the trailing one. Use the same approach for the toggle knob.
4. Make drags direct: while the cursor is held down, calculate the value from its position. On release, spring back from that position.
5. Analyze the song with numpy to find the beat grid and begin on a downbeat. Position each UI sound using its measured peak.
6. Render with Playwright: 4 subframes per frame, blended with ffmpeg tmix for motion blur at 60fps.
7. Render one frame per beat before the full render. Fix anything off-grid, cramped or difficult to read.
</build>

<gotchas>
Don’t use will-change on anything the camera scales, or the text will look blurry. Text swapping inside a morphing container needs separate enter and exit timing to avoid overlap. Make the final frame identical to the first including cursor position and speed or the loop will stutter.
</gotchas>

<start>
Ask me for the inputs, then show me the state list on the beat grid before writing any code.
</start>

[rari @0xwhrrari]

Opus 5.5 can make a video

The hard part is making the next one better

That takes a studio, not a prompt

I broke down how to build it ↓ https://t.co/EXinI060Cr

[testarossa @rossaxbt]

Sam Altman (CEO of OpenAI):

"You don't need to write every prompt yourself

Build loops and graphs that write the next one for you"

Prompts → GPT Dots → Agents → Loops → Graphs

In 78 minutes, he explains how to use LLMs at a level most people never reach

Goal → Run → Check → Route → Repeat

That's the difference between asking AI for help and building a system that keeps working for you

Same model, same tokens, completely different workflow

This talk is worth more than most $1,500 paid AI courses

Bookmark and watch it today

Then save the full GPT Dots and graph engineering guide below ↓

[testarossa @rossaxbt]

Sam Altman (CEO of OpenAI):

"You don't need to write every prompt yourself

Build loops and graphs that write the next one for you"

Prompts → GPT Dots → Agents → Loops → Graphs

In 78 minutes, he explains how to use LLMs at a level most people never reach

Goal → Run → Check → Route → Repeat

That's the difference between asking AI for help and building a system that keeps working for you

Same model, same tokens, completely different workflow

This talk is worth more than most $1,500 paid AI courses

Bookmark and watch it today

Then save the full GPT Dots and graph engineering guide below ↓

[rari @0xwhrrari]

Most people will use Dots like a smarter chat and miss the point

The real shift is AI that keeps working between prompts while the important decisions stay with you

I broke down how Dots, Space, Astra, Sol, and Codex fit together ↓ https://t.co/31fW4gHM5U

[testarossa @rossaxbt]

Anthropic Research Lead:

"99% of our engineers run swarms of 300+ self-improving agents"

"Now everyone is building agentic graphs"

In a 20-minute session, an Anthropic team member breaks down how graph engineering turns isolated agents into systems that improve themselves

The real setup is Claude running through graph workflows, plan mode, and dynamic orchestration

Agents → Loops → Graphs → Self-Improving Systems

Better than most $2,300 graph engineering courses

Bookmark and watch the talk

Then read the article below

[testarossa @rossaxbt]

@0xwhrrari 48 percent is a crazy result for a live video interaction

[testarossa @rossaxbt]

Anthropic Research Lead:

"99% of our engineers run swarms of 300+ self-improving agents"

"Now everyone is building agentic graphs"

In a 20-minute session, an Anthropic team member breaks down how graph engineering turns isolated agents into systems that improve themselves

The real setup is Claude running through graph workflows, plan mode, and dynamic orchestration

Agents → Loops → Graphs → Self-Improving Systems

Better than most $2,300 graph engineering courses

Bookmark and watch the talk

Then read the article below

[rari @0xwhrrari]

Opus 5.5 can make a video

The hard part is making the next one better

That takes a studio, not a prompt

I broke down how to build it ↓ https://t.co/EXinI060Cr

[testarossa @rossaxbt]

SpaceXAI engineer and ex-Cursor:

"I don't prompt my ~20 GrokBot agents anymore

I built a 24/7 system once
Now it automates 90% of my life and prompts itself"

"Instead of delegating tasks like 99% of people, I delegate the delegation

One Chief of Staff activates the rest of the bots
The result is a system managing 950K leads"

GrokBot → Chief of Staff → Agent Teams → Delegated Work → Autonomous System

In this 55-minute course, SpaceXAI breaks down the shift to GrokBot and her best workflow

This is worth more than 10 hours of other agent courses

Watch how SpaceXAI builds GrokBot

Then learn the rules behind the system and run it yourself ↓

[testarossa @rossaxbt]

SpaceXAI engineer and ex-Cursor:

"I don't prompt my ~20 GrokBot agents anymore

I built a 24/7 system once
Now it automates 90% of my life and prompts itself"

"Instead of delegating tasks like 99% of people, I delegate the delegation

One Chief of Staff activates the rest of the bots
The result is a system managing 950K leads"

GrokBot → Chief of Staff → Agent Teams → Delegated Work → Autonomous System

In this 55-minute course, SpaceXAI breaks down the shift to GrokBot and her best workflow

This is worth more than 10 hours of other agent courses

Watch how SpaceXAI builds GrokBot

Then learn the rules behind the system and run it yourself ↓

[rari @0xwhrrari]

xAI quietly dropped 15 official grok bot guides and almost nobody is talking about it

Every single one written by the team that built grok

This section is free

Pick a guide, follow it, ship your bot

Most people are still guessing how to build one

15 official guides are already out and cost nothing

Bookmark this and check the guides below ⭣

[testarossa @rossaxbt]

Anthropic hired this engineer at $250K–$750K a year because he knows how to build harnesses for multi-agent systems

In a 15-minute workshop, he shows exactly how to build one from scratch

AI → Agents → Harness → Loops → Graphs

step 1 → start with the Claude Agent SDK — the harness handles loops, context, and sandboxing

step 2 → separate the brain from the hands — reasoning in one place, tools in a sandbox, 60% faster to first token

step 3 → run it server-side and log every step — close your laptop and it keeps running, crashes resume from the log

step 4 → make failure cheap — retry dead sandboxes and replay lost context instead of starting over

step 5 → turn yesterday's logs into new memory and skills — the harness wakes up smarter

Anthropic calls this "dreaming"

Most people spend weeks building this by hand

You don't have to

Bookmark and watch it

Then read the full harness engineering guide below ↓

[testarossa @rossaxbt]

Anthropic hired this engineer at $250K–$750K a year because he knows how to build harnesses for multi-agent systems

In a 15-minute workshop, he shows exactly how to build one from scratch

AI → Agents → Harness → Loops → Graphs

step 1 → start with the Claude Agent SDK — the harness handles loops, context, and sandboxing

step 2 → separate the brain from the hands — reasoning in one place, tools in a sandbox, 60% faster to first token

step 3 → run it server-side and log every step — close your laptop and it keeps running, crashes resume from the log

step 4 → make failure cheap — retry dead sandboxes and replay lost context instead of starting over

step 5 → turn yesterday's logs into new memory and skills — the harness wakes up smarter

Anthropic calls this "dreaming"

Most people spend weeks building this by hand

You don't have to

Bookmark and watch it

Then read the full harness engineering guide below ↓

[Mori @0xjmori]

Harness Engineering could be the missing layer between smart models and reliable AI agents.

It gives agents context, safe tools, durable state, verification and recovery.

In this article, I show you how. https://t.co/RwgSSyxHUx

[testarossa @rossaxbt]

Google just released a free 1-hour course on Graph Engineering

From one agent to complete Loops and Graphs

Prompts → Agents → Memory → Loops → MCP → Graphs

0% → 00:00 - Build your first AI agent
15% → 08:24 - Give your agent memory
50% → 28:34 - Build agentic loops
65% → 40:04 - Create your own MCP
100% → 1:00:22 - Master graph engineering

Free and easily the strongest graph engineering course I've seen

Most people stop after memory and call it a complete system

The final twenty minutes reveal the layer that sits above everything

Model → Context → Memory → Loops → Graphs → Autonomous Systems

Same model, same tokens, completely different workflow

Watch it today

Then read the step-by-step guide below and save it before everyone catches on ↓

[testarossa @rossaxbt]

Google just released a free 1-hour course on Graph Engineering

From one agent to complete Loops and Graphs

Prompts → Agents → Memory → Loops → MCP → Graphs

0% → 00:00 - Build your first AI agent
15% → 08:24 - Give your agent memory
50% → 28:34 - Build agentic loops
65% → 40:04 - Create your own MCP
100% → 1:00:22 - Master graph engineering

Free and easily the strongest graph engineering course I've seen

Most people stop after memory and call it a complete system

The final twenty minutes reveal the layer that sits above everything

Model → Context → Memory → Loops → Graphs → Autonomous Systems

Same model, same tokens, completely different workflow

Watch it today

Then read the step-by-step guide below and save it before everyone catches on ↓

[rari @0xwhrrari]

https://t.co/3ANIWs48lJ

[testarossa @rossaxbt]

@0xwhrrari this is probably the best prompt for jev
thanks rari

[testarossa @rossaxbt]

Google engineer:

"Build a harness that runs self-improving agent workflows 24/7 with loops and graphs

This is the new engineering job"

"At Google, 90% of engineers already run dozens of agentic workflows through their harnesses

This is what the next era of engineering looks like"

Agents → Harness → Loops → Graphs → Feedback → Self-Improving Systems

In this 1-hour conversation, a Google engineer breaks down the future of AI engineering

Prompts → Orchestration → Verification → Autonomous Workflows

Easily worth more than 10 paid agentic courses

Bookmark and watch it tonight

Then read the article below to learn how to build a self-improving agent harness

[testarossa @rossaxbt]

Google engineer:

"Build a harness that runs self-improving agent workflows 24/7 with loops and graphs

This is the new engineering job"

"At Google, 90% of engineers already run dozens of agentic workflows through their harnesses

This is what the next era of engineering looks like"

Agents → Harness → Loops → Graphs → Feedback → Self-Improving Systems

In this 1-hour conversation, a Google engineer breaks down the future of AI engineering

Prompts → Orchestration → Verification → Autonomous Workflows

Easily worth more than 10 paid agentic courses

Bookmark and watch it tonight

Then read the article below to learn how to build a self-improving agent harness

[rari @0xwhrrari]

https://t.co/3ANIWs48lJ

[testarossa @rossaxbt]

SpaceXAI engineer Lauren Tan:

"99% of people are using GrokBot wrong

At SpaceXAI, one engineer can now run an entire team of agents"

GrokBot → Managers → Autonomous Agents → Full Agent Teams

GrokBot is turning SpaceXAI engineers into operators of autonomous systems

In a 1-hour talk, Lauren reveals how to unlock 100% of the agentic tools you already use

Prompt → Delegate → Execute → Review → Improve

Worth more than most $2,000 agentic courses online

Bookmark and watch it today

Then read how to build your own GrokBot agent team from scratch in the article below

[testarossa @rossaxbt]

SpaceXAI engineer Lauren Tan:

"99% of people are using GrokBot wrong

At SpaceXAI, one engineer can now run an entire team of agents"

GrokBot → Managers → Autonomous Agents → Full Agent Teams

GrokBot is turning SpaceXAI engineers into operators of autonomous systems

In a 1-hour talk, Lauren reveals how to unlock 100% of the agentic tools you already use

Prompt → Delegate → Execute → Review → Improve

Worth more than most $2,000 agentic courses online

Bookmark and watch it today

Then read how to build your own GrokBot agent team from scratch in the article below

[rari @0xwhrrari]

https://t.co/GoJ0DWB7Ve

[testarossa @rossaxbt]

SpaceXAI engineer Lauren Tan:

"I'm running 20+ GrokBot agents with /loop and /goal inside pstack

My bots ship code while I sleep

At SpaceXAI, 85% of engineers already run 10+ GrokBot agents as a team

One Chief of Staff agent knows every bot and manages the entire system"

GrokBot → /loop → /goal → Chief of Staff → Agent Teams

In a 1-hour workshop, Lauren shows how to build a full GrokBot team from scratch

Research → Code → Review → Ship

Worth more than most $1,500 agent engineering courses

Bookmark and watch it today

Then read the full article on building a GrokBot agent team from scratch