Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

here’s how to make game models with claude opus 5.5 + blender... opus writes python and builds every model in blender, part by part. the trick is treating every model as code, but there’s a smart way to set it up: - step 1: connect opus 5.5 to blender...

rewind02's profile picture

rewind

7,206 subscribers

69,669 Aufrufe • vor 6 Tagen •via X (Twitter)

GamingWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

game studios are cooked how i build a cozy farm game solo with Opus 5.5 and Unity 6 the trick is building it like a studio, one department per prompt: step 1 -> connect Claude Code to Unity 6 and Blender through MCP step 2 -> write a 1-page doc: plant > water > harvest > sell, 4 seasons step 3 -> generate every model in Tripo: farmer, barn, windmill, crops step 4 -> Opus cleans them in Blender and builds the island in Unity step 5 -> one system per prompt: planting, growth timers, market, coins step 6 -> Opus playtests with an autopilot and lists bugs before fixing any who does what: > tripo: every model > unity 6: the world, physics, ui > opus 5.5: scripts, scene setup, playtests > you: play it and say what feels off the rule that saves it... build one system, play it, then the next what should i build next?
0:15

game studios are cooked how i build a cozy farm game solo with Opus 5.5 and Unity 6 the trick is building it like a studio, one department per prompt: step 1 -> connect Claude Code to Unity 6 and Blender through MCP step 2 -> write a 1-page doc: plant > water > harvest > sell, 4 seasons step 3 -> generate every model in Tripo: farmer, barn, windmill, crops step 4 -> Opus cleans them in Blender and builds the island in Unity step 5 -> one system per prompt: planting, growth timers, market, coins step 6 -> Opus playtests with an autopilot and lists bugs before fixing any who does what: > tripo: every model > unity 6: the world, physics, ui > opus 5.5: scripts, scene setup, playtests > you: play it and say what feels off the rule that saves it... build one system, play it, then the next what should i build next?

Mnimiy

76,534 Aufrufe • vor 7 Tagen

here's how to build a cozy fishing game with opus 5.5 + blender + unity 6... the trick is never asking for "a fishing game" in one prompt, but there's a smart way to set it up: - step 1: connect opus 5.5 to blender (blender mcp) and to unity 6 (unity mcp) - step 2: write a 1-page game doc first: top-down camera, row > find a spot > cast > reel, a creel with 8 slots, time of day - step 3: in blender, opus builds the assets: the rowboat, the fisher with the straw hat, the cabin, the dock, rocks, pines - step 4: export everything as .fbx with one stylized palette, so the whole world matches - step 5: in unity 6, opus lays out the level: the river, the waterfall pool, shallow water shaders, fish swimming in schools - step 6: then the systems, one at a time: rowing controls, fishing spot triggers, casting, a tension bar for reeling, the fish list - step 7: last, the ui: the creel counter (3/8), the "new fishing spot" popup, a catch card ("silver bream"), button hints who does what: - blender: every mesh and material - unity 6: the world, water, physics, ui - opus 5.5: modeling scripts, c# scripts, scene setup in both apps - you: playtest and say what feels off and the rule that saves the project... build one system and play it before the next. if rowing feels bad, casting will feel worse
0:14

here's how to build a cozy fishing game with opus 5.5 + blender + unity 6... the trick is never asking for "a fishing game" in one prompt, but there's a smart way to set it up: - step 1: connect opus 5.5 to blender (blender mcp) and to unity 6 (unity mcp) - step 2: write a 1-page game doc first: top-down camera, row > find a spot > cast > reel, a creel with 8 slots, time of day - step 3: in blender, opus builds the assets: the rowboat, the fisher with the straw hat, the cabin, the dock, rocks, pines - step 4: export everything as .fbx with one stylized palette, so the whole world matches - step 5: in unity 6, opus lays out the level: the river, the waterfall pool, shallow water shaders, fish swimming in schools - step 6: then the systems, one at a time: rowing controls, fishing spot triggers, casting, a tension bar for reeling, the fish list - step 7: last, the ui: the creel counter (3/8), the "new fishing spot" popup, a catch card ("silver bream"), button hints who does what: - blender: every mesh and material - unity 6: the world, water, physics, ui - opus 5.5: modeling scripts, c# scripts, scene setup in both apps - you: playtest and say what feels off and the rule that saves the project... build one system and play it before the next. if rowing feels bad, casting will feel worse

rewind

52,654 Aufrufe • vor 9 Tagen

indie studios, hello how i add fishing to my cozy farm game with Opus 5.5 the trick is adding one new verb per zone. this zone's verb is fishing: step 1 -> Claude Code drives Unity 6 via unity-mcp, Blender via blender-mcp step 2 -> village as a new scene, farm HUD carried over as one prefab step 3 -> Tripo for the set: pier, lighthouse, 4 boats, crab traps, fish stall step 4 -> Opus rigs the cast in Blender and builds the water with URP shaders step 5 -> fishing as one system: cast, tension bar, catch card, coins step 6 -> 12 fish species in a sheet, Opus balances rarity and prices before code step 7 -> ElevenLabs for splashes, gulls, reel clicks. Cinemachine follows the player who does what: > tripo: every new model > unity 6: scenes, water, lighting > opus 5.5: c# scripts, rigging, the fish economy > you: fish until it feels right one new zone, one new verb. the farm plays the same, the island just got bigger next zone: the mine or the forest?
0:15

indie studios, hello how i add fishing to my cozy farm game with Opus 5.5 the trick is adding one new verb per zone. this zone's verb is fishing: step 1 -> Claude Code drives Unity 6 via unity-mcp, Blender via blender-mcp step 2 -> village as a new scene, farm HUD carried over as one prefab step 3 -> Tripo for the set: pier, lighthouse, 4 boats, crab traps, fish stall step 4 -> Opus rigs the cast in Blender and builds the water with URP shaders step 5 -> fishing as one system: cast, tension bar, catch card, coins step 6 -> 12 fish species in a sheet, Opus balances rarity and prices before code step 7 -> ElevenLabs for splashes, gulls, reel clicks. Cinemachine follows the player who does what: > tripo: every new model > unity 6: scenes, water, lighting > opus 5.5: c# scripts, rigging, the fish economy > you: fish until it feels right one new zone, one new verb. the farm plays the same, the island just got bigger next zone: the mine or the forest?

Mnimiy

24,011 Aufrufe • vor 6 Tagen

Holy sh*t, I just turned my TV into Jarvis with Opus 5.5 + ChatGPT voice mode I reverse-engineered my Samsung TV with Opus 5.5... 1 sentence out loud = 6 Claude Code agents opening on my living room TV. here's the full guide step by step: step 1 → put your Samsung Smart TV and your laptop on the same Wi-Fi step 2 → paste the prompt below into Claude Code on Opus 5.5 with a photo of Settings → Support → About This TV step 3 → Opus maps how the TV takes orders and finds the loophole: Samsung's own remote-control API on your home network can open any web page in the TV browser step 4 → it spins up 6 Claude Code agents in a tmux grid on the laptop and streams them as a private page on your Wi-Fi only step 5 → it builds a tiny "Jarvis" connector with one single tool: open the agent wall. ChatGPT voice mode is the ears, the connector is the hands step 6 → press Allow on the TV once, the last time you touch the remote step 7 → say "Open Claude Code CLI on my TV" and watch the windows pop in one by one the result: the laptop does the work, the TV is the control room... p.s: works on most Samsung Smart TVs with Tizen. mine in the video runs Smart Hub. The remote now lives in a drawer Find full prompt below Then read the article below on how to reverse-engineer anything
0:14

Holy sh*t, I just turned my TV into Jarvis with Opus 5.5 + ChatGPT voice mode I reverse-engineered my Samsung TV with Opus 5.5... 1 sentence out loud = 6 Claude Code agents opening on my living room TV. here's the full guide step by step: step 1 → put your Samsung Smart TV and your laptop on the same Wi-Fi step 2 → paste the prompt below into Claude Code on Opus 5.5 with a photo of Settings → Support → About This TV step 3 → Opus maps how the TV takes orders and finds the loophole: Samsung's own remote-control API on your home network can open any web page in the TV browser step 4 → it spins up 6 Claude Code agents in a tmux grid on the laptop and streams them as a private page on your Wi-Fi only step 5 → it builds a tiny "Jarvis" connector with one single tool: open the agent wall. ChatGPT voice mode is the ears, the connector is the hands step 6 → press Allow on the TV once, the last time you touch the remote step 7 → say "Open Claude Code CLI on my TV" and watch the windows pop in one by one the result: the laptop does the work, the TV is the control room... p.s: works on most Samsung Smart TVs with Tizen. mine in the video runs Smart Hub. The remote now lives in a drawer Find full prompt below Then read the article below on how to reverse-engineer anything

Codez

58,569 Aufrufe • vor 1 Tag

Claude Code vs Blender is getting f*cking ridiculous One approach builds a jet engine by hand The other turns a written description into a programmable 3D scene with rotating turbines, mechanical components, realistic materials, and cinematic camera movement And the difference goes way beyond modeling speed Traditional Blender workflow: > MODEL individual mechanical components > POSITION and assemble the geometry > CONFIGURE materials, lighting, and cameras > ANIMATE every moving mechanism > REWORK the scene when specifications change Claude Code + Blender Python: > GENERATE geometry from parameters > ASSEMBLE components programmatically > CONTROL turbine rotation through variables > AUTOMATE lighting and camera movements > REBUILD variations by editing the script The interesting part isn't that AI magically replaces Blender It's that Claude Code can operate Blender through Python, turning repetitive manual work into a reproducible system Want to test the difference? Open Claude Code and ask: "Generate a Blender Python script for a detailed turbofan engine with separate compressor and turbine stages, parameterized blade counts, independent shaft rotation, metallic materials, and a cinematic camera orbit Keep the geometry modular and expose the main parameters so I can regenerate variations without remodeling everything" Blender remains the rendering engine Claude Code changes how you build and control the scene Bookmark this workflow before your next 3D project
0:12

Claude Code vs Blender is getting f*cking ridiculous One approach builds a jet engine by hand The other turns a written description into a programmable 3D scene with rotating turbines, mechanical components, realistic materials, and cinematic camera movement And the difference goes way beyond modeling speed Traditional Blender workflow: > MODEL individual mechanical components > POSITION and assemble the geometry > CONFIGURE materials, lighting, and cameras > ANIMATE every moving mechanism > REWORK the scene when specifications change Claude Code + Blender Python: > GENERATE geometry from parameters > ASSEMBLE components programmatically > CONTROL turbine rotation through variables > AUTOMATE lighting and camera movements > REBUILD variations by editing the script The interesting part isn't that AI magically replaces Blender It's that Claude Code can operate Blender through Python, turning repetitive manual work into a reproducible system Want to test the difference? Open Claude Code and ask: "Generate a Blender Python script for a detailed turbofan engine with separate compressor and turbine stages, parameterized blade counts, independent shaft rotation, metallic materials, and a cinematic camera orbit Keep the geometry modular and expose the main parameters so I can regenerate variations without remodeling everything" Blender remains the rendering engine Claude Code changes how you build and control the scene Bookmark this workflow before your next 3D project

Lummox

32,617 Aufrufe • vor 3 Tagen

it's f*cking insane.. Anthropic just dropped a Claude Code setup that makes tokens up to 97% cheaper Opus brains, Sonnet bill: > Sonnet runs your session and writes the code > Haiku subagents grab the small tasks > Opus steps in only when Sonnet gets stuck > it checks the work, digs into the problem and puts Sonnet back on track $19.50 saved on every 1M tokens a Haiku 5.5 subagent writes, compared with Opus 5.5 one command sets it up: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents the easiest money you'll save on Claude Code this year
0:18

it's f*cking insane.. Anthropic just dropped a Claude Code setup that makes tokens up to 97% cheaper Opus brains, Sonnet bill: > Sonnet runs your session and writes the code > Haiku subagents grab the small tasks > Opus steps in only when Sonnet gets stuck > it checks the work, digs into the problem and puts Sonnet back on track $19.50 saved on every 1M tokens a Haiku 5.5 subagent writes, compared with Opus 5.5 one command sets it up: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents the easiest money you'll save on Claude Code this year

Mnimiy

55,980 Aufrufe • vor 12 Tagen

I vibe coded this AfterEffects Animation in 45 minutes. Step 1: I used Cursor to Generate a type of code called extendscript/java script... No clue what that means, but it worked. Step 2: I ran the script in after effects... ChatGPT voice the whole time guiding me through the process of importing scripts and running it Step 3: I made changes with Composer, just like normal except now after effects is my "localhost:3000" that's just how i think about it in my head. Every time you make changes, you do have to run the script again manually. But I did 7-8 iterations and got this. Step 4: I went to Suno to generate the music. Then elevenlabs to generate the sound effects (wind) and voice. Step 5: Tossed them into premiere, adjusted the audio levels to not be so abrupt... then export.
0:15

I vibe coded this AfterEffects Animation in 45 minutes. Step 1: I used Cursor to Generate a type of code called extendscript/java script... No clue what that means, but it worked. Step 2: I ran the script in after effects... ChatGPT voice the whole time guiding me through the process of importing scripts and running it Step 3: I made changes with Composer, just like normal except now after effects is my "localhost:3000" that's just how i think about it in my head. Every time you make changes, you do have to run the script again manually. But I did 7-8 iterations and got this. Step 4: I went to Suno to generate the music. Then elevenlabs to generate the sound effects (wind) and voice. Step 5: Tossed them into premiere, adjusted the audio levels to not be so abrupt... then export.

Riley Brown

33,684 Aufrufe • vor 1 Jahr

a🧵on how to do the movable crater tech, You will learn this step by step, It should only take a couple of minutes to do it so lock in, Simple Overview: 1) Draw a black texture that represents a crack (use lasso or draw then fill tool) 2) Use a png to svg converter to make it into svg (you MUST make the crack black!) 3) Make the mesh of the crater 4) Export it as fbx and Import it in Roblox Studio 5) Create a viewport put the thing inside play with some lighting,material of crater n ur done 6) Make another viewport and make it so that it duplicates the character of the player every frame and puts in the viewport so that you can see it to be above the crater viewport Now for the detailed tutorial:
0:13

a🧵on how to do the movable crater tech, You will learn this step by step, It should only take a couple of minutes to do it so lock in, Simple Overview: 1) Draw a black texture that represents a crack (use lasso or draw then fill tool) 2) Use a png to svg converter to make it into svg (you MUST make the crack black!) 3) Make the mesh of the crater 4) Export it as fbx and Import it in Roblox Studio 5) Create a viewport put the thing inside play with some lighting,material of crater n ur done 6) Make another viewport and make it so that it duplicates the character of the player every frame and puts in the viewport so that you can see it to be above the crater viewport Now for the detailed tutorial:

QwinkleTee

40,103 Aufrufe • vor 1 Jahr

Claude Code just reverse-engineered my Wi-Fi router... found why it was so f*cking slow and fixed it in 5 minutes check yours, here's full guide step by step: step 1 → paste prompt below into Claude Code with photo of your router and tell it what's wrong. If you just want a diagnosis, it works too step 2 → it gives you one command to save your router password to your keychain, run it - the password never touches the chat step 3 → Claude shows each fix with the old and new value, you just say yes step 4 → the rest is on Claude: it backs up every setting, finds what's killing your speed (crowded channel, wrong band, narrow width, old WI-FI mode, lag) and re-tests after every fix the result: before and after speed in one line, and a router that takes orders from chat: "who's on my WI-FI", "reboot the router" and other... p.s: works with most routers, if yours is different, just tell Claude Code and it'll find another way in Try right now, don't forget me later. Then read article below shows how to reverse-engineer anything:
0:17

Claude Code just reverse-engineered my Wi-Fi router... found why it was so f*cking slow and fixed it in 5 minutes check yours, here's full guide step by step: step 1 → paste prompt below into Claude Code with photo of your router and tell it what's wrong. If you just want a diagnosis, it works too step 2 → it gives you one command to save your router password to your keychain, run it - the password never touches the chat step 3 → Claude shows each fix with the old and new value, you just say yes step 4 → the rest is on Claude: it backs up every setting, finds what's killing your speed (crowded channel, wrong band, narrow width, old WI-FI mode, lag) and re-tests after every fix the result: before and after speed in one line, and a router that takes orders from chat: "who's on my WI-FI", "reboot the router" and other... p.s: works with most routers, if yours is different, just tell Claude Code and it'll find another way in Try right now, don't forget me later. Then read article below shows how to reverse-engineer anything:

codila

203,687 Aufrufe • vor 2 Tagen

THIS IS F*CKING BRILLIANT. Anthropic’s docs describe one of the smartest ways to run Opus three models work on one task and each does only the part it’s cheapest at. start Claude Code like this: claude -> model sonnet -> advisor opus you stop paying Opus prices for work that doesn’t need Opus > Sonnet runs the session and edits the code > Haiku 5.5 searches the repo and docs, at up to 40x less per token than Opus 5.5 > Opus waits as the advisor and reads the whole session, tool calls included Claude usually calls Opus at three points: > before it locks a plan > when the same error comes back > right before it says it’s done Sonnet drives. Haiku scouts. Opus signs off and if you go one step lower, most of an agent’s day is tiny choices like picking a file or a tool, or deciding whether to retry. Jev takes those first, so Sonnet and Opus only see the moments that are really open the whole setup Sonnet runs the main session Explore on Haiku 5.5 searches and pulls docs, read-only Opus on call as the advisor give Claude Code this setup and the prompt below ↓ “Set up my Claude Code exactly like this: Main model Sonnet, advisor Opus, saved as advisorModel in my settings. One read-only subagent named exactly Explore, on claude-haiku-5-5, to replace the built-in one. One line in CLAUDE.md: ask the advisor before locking a plan, after the same error twice, and before calling a task done, not more often. Check what could turn the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) and only report it. Show every change as a diff first. Don’t edit anything until I say go.” before you turn it on: every advisor call re-reads the whole transcript with no cache. on a 200k session that’s about $0.80 in input, against $0.04 for a normal request. keep it to a few calls the built-in Explore agent runs on your main model unless a subagent is named exactly Explore. any other name does nothing turning the advisor on or off keeps your prompt cache. switching models rebuilds it it needs the Anthropic API, and it stays off if telemetry is disabled bookmark it before your next long session
0:17

THIS IS F*CKING BRILLIANT. Anthropic’s docs describe one of the smartest ways to run Opus three models work on one task and each does only the part it’s cheapest at. start Claude Code like this: claude -> model sonnet -> advisor opus you stop paying Opus prices for work that doesn’t need Opus > Sonnet runs the session and edits the code > Haiku 5.5 searches the repo and docs, at up to 40x less per token than Opus 5.5 > Opus waits as the advisor and reads the whole session, tool calls included Claude usually calls Opus at three points: > before it locks a plan > when the same error comes back > right before it says it’s done Sonnet drives. Haiku scouts. Opus signs off and if you go one step lower, most of an agent’s day is tiny choices like picking a file or a tool, or deciding whether to retry. Jev takes those first, so Sonnet and Opus only see the moments that are really open the whole setup Sonnet runs the main session Explore on Haiku 5.5 searches and pulls docs, read-only Opus on call as the advisor give Claude Code this setup and the prompt below ↓ “Set up my Claude Code exactly like this: Main model Sonnet, advisor Opus, saved as advisorModel in my settings. One read-only subagent named exactly Explore, on claude-haiku-5-5, to replace the built-in one. One line in CLAUDE.md: ask the advisor before locking a plan, after the same error twice, and before calling a task done, not more often. Check what could turn the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) and only report it. Show every change as a diff first. Don’t edit anything until I say go.” before you turn it on: every advisor call re-reads the whole transcript with no cache. on a 200k session that’s about $0.80 in input, against $0.04 for a normal request. keep it to a few calls the built-in Explore agent runs on your main model unless a subagent is named exactly Explore. any other name does nothing turning the advisor on or off keeps your prompt cache. switching models rebuilds it it needs the Anthropic API, and it stays off if telemetry is disabled bookmark it before your next long session

rvaniaaa

62,223 Aufrufe • vor 10 Tagen

all GPT models and DeepSeek 4.1 are FREE on ZansLab right now an Indonesian AI gateway just unlocked free access to every GPT model plus DeepSeek 4.1 for vibe coding, no top-up needed, just sign up what you get: > GPT-6 Astra free > GPT-6 Sol free > GPT-6 Luna free > GPT-5.6 Sol free > DeepSeek 4.1 free > and Claude models also available on the platform how to claim (under 2 min): step 1: go to step 2: sign up with email and password no card, no top-up needed step 3: create an API key from the API Keys page step 4: set base URL to works in any OpenAI-compatible client, Cursor, Claude Code, Codex, custom scripts step 5: pick a model and start vibe coding important: > this is a third-party proxy so don't send any sensitive data through it > free access reportedly lasts until next week per the source > these free tiers rarely stick around, grab it while it's up
0:16

all GPT models and DeepSeek 4.1 are FREE on ZansLab right now an Indonesian AI gateway just unlocked free access to every GPT model plus DeepSeek 4.1 for vibe coding, no top-up needed, just sign up what you get: > GPT-6 Astra free > GPT-6 Sol free > GPT-6 Luna free > GPT-5.6 Sol free > DeepSeek 4.1 free > and Claude models also available on the platform how to claim (under 2 min): step 1: go to step 2: sign up with email and password no card, no top-up needed step 3: create an API key from the API Keys page step 4: set base URL to works in any OpenAI-compatible client, Cursor, Claude Code, Codex, custom scripts step 5: pick a model and start vibe coding important: > this is a third-party proxy so don't send any sensitive data through it > free access reportedly lasts until next week per the source > these free tiers rarely stick around, grab it while it's up

Rivon

18,632 Aufrufe • vor 21 Tagen

$35 OF FREE CLAUDE OPUS 5 CREDITS FOR A WEEK, NO CARD ANYWHERE • the credit > Sign up with Google and the trial activates on its own, nothing to claim manually: > Opus 5 sits alongside Opus 4.8, Sonnet 4.6 and Haiku on the same key. > The window runs a week from activation. • wiring it up > base url: > model id: claude-opus-5 > In OpenCode Desktop hit Ctrl+, and add a custom provider with the id aerolink. > The same key drops into Codex, Cursor and Claude Code with nothing else changed. One key, not locked to one client -> every tool that takes a custom OpenAI-compatible endpoint reads it the same way. It routes through a third-party proxy rather than an official Anthropic channel, so keep client work off it ↓
0:16

$35 OF FREE CLAUDE OPUS 5 CREDITS FOR A WEEK, NO CARD ANYWHERE • the credit > Sign up with Google and the trial activates on its own, nothing to claim manually: > Opus 5 sits alongside Opus 4.8, Sonnet 4.6 and Haiku on the same key. > The window runs a week from activation. • wiring it up > base url: > model id: claude-opus-5 > In OpenCode Desktop hit Ctrl+, and add a custom provider with the id aerolink. > The same key drops into Codex, Cursor and Claude Code with nothing else changed. One key, not locked to one client -> every tool that takes a custom OpenAI-compatible endpoint reads it the same way. It routes through a third-party proxy rather than an official Anthropic channel, so keep client work off it ↓

slash1s

21,111 Aufrufe • vor 2 Monaten

Took Andrej Karpathy's advice and started asking the agent for more visuals to walk through code. He's right. These models are so capable now. Here I asked for a before-and-after HTML explainer on a PR that adds caching to our mobile app. Opus 5.5 gave a step-by-step diagram of the new flow, screenshots, and pointed me to the code worth reviewing. No skills being used here; it just knew what to show. Saved a lot of time and let me align on architecture before opening GitHub
0:19

Took Andrej Karpathy's advice and started asking the agent for more visuals to walk through code. He's right. These models are so capable now. Here I asked for a before-and-after HTML explainer on a PR that adds caching to our mobile app. Opus 5.5 gave a step-by-step diagram of the new flow, screenshots, and pointed me to the code worth reviewing. No skills being used here; it just knew what to show. Saved a lot of time and let me align on architecture before opening GitHub

Ben Holmes

58,468 Aufrufe • vor 18 Tagen

THIS IS A PURE F*CKING GOLDMINE the best REA trick almost nobody runs yet. The idea: REA takes the app apart, Jev keeps only what's proven, and a fresh Opus 5.5 rebuilds the feature from that alone. Nothing gets copied and no guess makes it into the code, because the builder never sees the original, only the spec Jev signed off on. You just connect REA like this: npx rea-agents setup here's the split: → REA reads the feature down to the binary and writes every rule into SPEC.md → Jev checks each rule against REA's evidence and sends back anything unproven → a fresh Opus 5.5 session gets only SPEC.md and rebuilds the feature → Haiku 5.5 runs the tests against 3 intentionally broken versions Opus only shows up at three moments: → rebuilding from the approved spec → the checks Jev marks as unclear → signing off before anything ships REA reads. Jev judges. Opus rebuilds. That's the clean-room rule in one line: the model that saw the original never writes the code, and the model that writes the code never sees the original. the full tree > REA reads the app and writes SPEC.md with evidence for every rule > Jev approves or returns each rule > Opus 5.5 rebuilds from the approved SPEC.md in a fresh session > Haiku 5.5 runs the tests and the 3 broken versions > Jev routes unclear checks back to Opus > /goal keeps going until all 3 broken versions fail paste the tree and this prompt into Claude Code ↓ "Set up a clean-room rebuild around this tree: 1. Use REA to investigate [FEATURE] in [APP]. Write every behavior and rule into SPEC.md, each with the evidence REA found. 2. Send each rule to Jev. Any rule without evidence goes back to REA. 3. Start a fresh session with only SPEC.md. Rebuild the feature on Opus 5.5 without opening the original. 4. Write tests on Haiku 5.5 plus 3 intentionally broken versions. Use /goal until the rebuild passes and all 3 broken versions fail. Show me SPEC.md first. Nothing gets built until I say go." ↳ save it, it'll come in handy.
0:20

THIS IS A PURE F*CKING GOLDMINE the best REA trick almost nobody runs yet. The idea: REA takes the app apart, Jev keeps only what's proven, and a fresh Opus 5.5 rebuilds the feature from that alone. Nothing gets copied and no guess makes it into the code, because the builder never sees the original, only the spec Jev signed off on. You just connect REA like this: npx rea-agents setup here's the split: → REA reads the feature down to the binary and writes every rule into SPEC.md → Jev checks each rule against REA's evidence and sends back anything unproven → a fresh Opus 5.5 session gets only SPEC.md and rebuilds the feature → Haiku 5.5 runs the tests against 3 intentionally broken versions Opus only shows up at three moments: → rebuilding from the approved spec → the checks Jev marks as unclear → signing off before anything ships REA reads. Jev judges. Opus rebuilds. That's the clean-room rule in one line: the model that saw the original never writes the code, and the model that writes the code never sees the original. the full tree > REA reads the app and writes SPEC.md with evidence for every rule > Jev approves or returns each rule > Opus 5.5 rebuilds from the approved SPEC.md in a fresh session > Haiku 5.5 runs the tests and the 3 broken versions > Jev routes unclear checks back to Opus > /goal keeps going until all 3 broken versions fail paste the tree and this prompt into Claude Code ↓ "Set up a clean-room rebuild around this tree: 1. Use REA to investigate [FEATURE] in [APP]. Write every behavior and rule into SPEC.md, each with the evidence REA found. 2. Send each rule to Jev. Any rule without evidence goes back to REA. 3. Start a fresh session with only SPEC.md. Rebuild the feature on Opus 5.5 without opening the original. 4. Write tests on Haiku 5.5 plus 3 intentionally broken versions. Use /goal until the rebuild passes and all 3 broken versions fail. Show me SPEC.md first. Nothing gets built until I say go." ↳ save it, it'll come in handy.

Archive

59,706 Aufrufe • vor 6 Tagen

Kimi K3 is a wildly creative model. I asked it to design Dieter Rams' Braun T3 radio in adam. It wrote the CAD, then decided the STEP wasn't enough, piped it into Blender on my Mac and lit a full product shoot in three colorways.
0:10

Kimi K3 is a wildly creative model. I asked it to design Dieter Rams' Braun T3 radio in adam. It wrote the CAD, then decided the STEP wasn't enough, piped it into Blender on my Mac and lit a full product shoot in three colorways.

Zach Dive

24,322 Aufrufe • vor 3 Monaten

everyone's sharing motion graphic videos that Opus 5.5 made, and it's genuinely insane everyone says they created it with "one prompt", but my one prompt video looked mid so i went through a bunch of these videos to see how they were actually made, and found the workflow that works here's how to generate pro level motion graphic videos w/ opus: 1. get reference videos to direct from -> pick 1-2 videos whose style you want and tell opus to match them. naming a style works way better than describing one without a reference, opus falls back to its default look: centered text, gradient background, everything fading in that's why so many of these videos look the same. a reference gives it the pacing, the type and the transitions to copy 2. install HyperFrames or Remotion so opus can build the video both let opus write every scene as code and render it straight to mp4. no video editor without one, opus can only describe a video or hand you a rough html page you have to screen record with it, every frame is exact, and when you ask for a change it edits one line and re-renders instead of starting over 3. install 21st for high quality components in the video real buttons, cards and UI components made by design engineers, instead of whatever opus invents on the spot without it, opus draws your product UI from scratch and it looks off. wrong spacing, placeholder boxes, fake-looking buttons anyone who's used good software can feel it in a second, and the whole video reads as cheap 4. steps 1-3 were context + setup. now dump all of it into opus your brand (logo, colors, fonts), screenshots of your real product, the reference video, and a quick braindump of how you see the video then ask for 3 storyboard variants without this, opus guesses your colors, your font and what your product even does. the video could be for any startup with it, it could only be yours. and 3 variants means you pick a direction instead of fixing the first idea it had 5. pick the storyboard you like ask for one still frame per scene before anything moves. fixing a storyboard is way cheaper than fixing a render without this step, you only find out scene 4 is wrong after the whole thing is animated, and every fix means re-rendering. a still frame takes seconds to change 6. let claude cook then give notes like a director: "slow every zoom to 0.7x", "hard cut here", "push in on the button" without notes, the first render is usually 80% there, and that last 20% is what makes it look pro. vague notes like "make it better" get random changes. camera words get exactly the change you want everyone has the same model. the context you give it is what makes it look pro let it cooookk
0:11

everyone's sharing motion graphic videos that Opus 5.5 made, and it's genuinely insane everyone says they created it with "one prompt", but my one prompt video looked mid so i went through a bunch of these videos to see how they were actually made, and found the workflow that works here's how to generate pro level motion graphic videos w/ opus: 1. get reference videos to direct from -> pick 1-2 videos whose style you want and tell opus to match them. naming a style works way better than describing one without a reference, opus falls back to its default look: centered text, gradient background, everything fading in that's why so many of these videos look the same. a reference gives it the pacing, the type and the transitions to copy 2. install HyperFrames or Remotion so opus can build the video both let opus write every scene as code and render it straight to mp4. no video editor without one, opus can only describe a video or hand you a rough html page you have to screen record with it, every frame is exact, and when you ask for a change it edits one line and re-renders instead of starting over 3. install 21st for high quality components in the video real buttons, cards and UI components made by design engineers, instead of whatever opus invents on the spot without it, opus draws your product UI from scratch and it looks off. wrong spacing, placeholder boxes, fake-looking buttons anyone who's used good software can feel it in a second, and the whole video reads as cheap 4. steps 1-3 were context + setup. now dump all of it into opus your brand (logo, colors, fonts), screenshots of your real product, the reference video, and a quick braindump of how you see the video then ask for 3 storyboard variants without this, opus guesses your colors, your font and what your product even does. the video could be for any startup with it, it could only be yours. and 3 variants means you pick a direction instead of fixing the first idea it had 5. pick the storyboard you like ask for one still frame per scene before anything moves. fixing a storyboard is way cheaper than fixing a render without this step, you only find out scene 4 is wrong after the whole thing is animated, and every fix means re-rendering. a still frame takes seconds to change 6. let claude cook then give notes like a director: "slow every zoom to 0.7x", "hard cut here", "push in on the button" without notes, the first render is usually 80% there, and that last 20% is what makes it look pro. vague notes like "make it better" get random changes. camera words get exactly the change you want everyone has the same model. the context you give it is what makes it look pro let it cooookk

Rexan Wong

641,168 Aufrufe • vor 27 Tagen

how to start a faceless youtube channel in 2026 with affiliates that actually makes money i've written 5,000+ scripts across 50+ niches. here's the exact process i'd follow if i had to start from $0 tomorrow STEP 1 - pick a niche with money in it, not one you "like" a million views from teenagers and a million views from 55-year-olds are not the same paycheck. finance, retirement, sleep, and world politics pay 5-10x what entertainment does because the advertisers are different. boring + high CPM beats fun + broke. every time. STEP 2 - steal what already works don't reinvent anything. find 5 channels that went from 10k to 100k recently (not the giants the ones who just broke through) and study what they changed. their titles, their hooks, their first 30 seconds. STEP 3 - the script is 70% of everything a mediocre video with a great script beats a beautiful video with a boring one every single time. cold open on the most intense moment. new question every 30 seconds. never let them guess what's coming next. if you can delete a sentence and lose nothing, delete it. STEP 4 - package it or it dies nobody sees the video. they see the title and thumbnail first. one visual, one emotion, 3 words max on the thumbnail. a title that makes NOT clicking feel like a mistake. 40 good videos die every day because of 40 bad titles. STEP 5 - make money before youtube pays you affiliate links in the description from video 1. an email freebie by week 2. a $19 guide by month 2. you should earn before adsense ever turns on. waiting for monetization is the #1 beginner mistake. STEP 6 - read the retention graph like scripture it tells you the exact second people left and why. cliff in the first 30s = fix your intro. dip in the middle = that's the sentence that bored them. it's the only feedback that matters. that's it. that's the whole game. the niche is your ceiling. the script decides how close you get to it. i post this stuff daily. follow so you don't have to learn it the slow, expensive way like i did.
0:12

how to start a faceless youtube channel in 2026 with affiliates that actually makes money i've written 5,000+ scripts across 50+ niches. here's the exact process i'd follow if i had to start from $0 tomorrow STEP 1 - pick a niche with money in it, not one you "like" a million views from teenagers and a million views from 55-year-olds are not the same paycheck. finance, retirement, sleep, and world politics pay 5-10x what entertainment does because the advertisers are different. boring + high CPM beats fun + broke. every time. STEP 2 - steal what already works don't reinvent anything. find 5 channels that went from 10k to 100k recently (not the giants the ones who just broke through) and study what they changed. their titles, their hooks, their first 30 seconds. STEP 3 - the script is 70% of everything a mediocre video with a great script beats a beautiful video with a boring one every single time. cold open on the most intense moment. new question every 30 seconds. never let them guess what's coming next. if you can delete a sentence and lose nothing, delete it. STEP 4 - package it or it dies nobody sees the video. they see the title and thumbnail first. one visual, one emotion, 3 words max on the thumbnail. a title that makes NOT clicking feel like a mistake. 40 good videos die every day because of 40 bad titles. STEP 5 - make money before youtube pays you affiliate links in the description from video 1. an email freebie by week 2. a $19 guide by month 2. you should earn before adsense ever turns on. waiting for monetization is the #1 beginner mistake. STEP 6 - read the retention graph like scripture it tells you the exact second people left and why. cliff in the first 30s = fix your intro. dip in the middle = that's the sentence that bored them. it's the only feedback that matters. that's it. that's the whole game. the niche is your ceiling. the script decides how close you get to it. i post this stuff daily. follow so you don't have to learn it the slow, expensive way like i did.

Tryahd

42,048 Aufrufe • vor 1 Monat

ChatGPT's coolest new feature now works on ANY AI model... and nobody is talking about it i asked two models to plan my day in San Francisco: Opus 5.5 on one side, Kimi K3 on the other neither one sent back a wall of text... both built me a map, photos and a route i can click through you can have your own agents answer like this, inside your app or anything you build, on whatever model you want i wrote the full step by step below:
0:17

ChatGPT's coolest new feature now works on ANY AI model... and nobody is talking about it i asked two models to plan my day in San Francisco: Opus 5.5 on one side, Kimi K3 on the other neither one sent back a wall of text... both built me a map, photos and a route i can click through you can have your own agents answer like this, inside your app or anything you build, on whatever model you want i wrote the full step by step below:

Machina

15,944 Aufrufe • vor 5 Tagen

how I make videos with Claude in 5 steps most AI videos look the same because people skip straight to “make me a video” I run every video through the same 5 steps instead. each one hands a real file to the next > reference spec.md I show Claude a video I actually like it breaks down why it works: the pacing, where the first motion lands, the cut rhythm > data data.json real numbers before anything moves every figure has a source, so nothing on screen is made up > story story.md one point, one hero number, three beats decided before the motion, so the video is about something > motion Scene.tsx every frame written as code with Remotion and a motion-design skill nothing is random, so every word, number and timing stays editable > direct timing.ts I give notes in plain words “title is a beat late” one line changes, nothing else breaks ship final.mp4 it renders stills and checks them against the reference and the data nothing goes out until I approve it why it works: no video model, so no re-rolls same input, same result, every time you always know which step is the problem most people jump to step 4. the real difference is step 1 and step 5 full setup, prompt and the 10 open-source skills are in the article
0:18

how I make videos with Claude in 5 steps most AI videos look the same because people skip straight to “make me a video” I run every video through the same 5 steps instead. each one hands a real file to the next > reference spec.md I show Claude a video I actually like it breaks down why it works: the pacing, where the first motion lands, the cut rhythm > data data.json real numbers before anything moves every figure has a source, so nothing on screen is made up > story story.md one point, one hero number, three beats decided before the motion, so the video is about something > motion Scene.tsx every frame written as code with Remotion and a motion-design skill nothing is random, so every word, number and timing stays editable > direct timing.ts I give notes in plain words “title is a beat late” one line changes, nothing else breaks ship final.mp4 it renders stills and checks them against the reference and the data nothing goes out until I approve it why it works: no video model, so no re-rolls same input, same result, every time you always know which step is the problem most people jump to step 4. the real difference is step 1 and step 5 full setup, prompt and the 10 open-source skills are in the article

Francesco

48,284 Aufrufe • vor 6 Tagen

motion designers are in serious danger, here is why an AI agent can now model a 3D scene in Blender, animate a website and render a finished MP4. you describe it, the agent builds it. three repos doing exactly that: -> HyperFrames: write HTML, get a video. made by HeyGen for AI agents. ask for a 10-second product intro with a fade-in title and background music, and the agent plans it, animates it and renders the MP4 -> MCP for Blender: connects Blender to Claude or any other model. the agent creates objects, builds scenes and edits them in real 3D while you watch -> GSAP skills: the official skills that teach coding agents to animate the web properly with GSAP. timelines, scroll effects, the stuff premium landing pages are made of the setup for HyperFrames in Claude Code is two lines: claude plugin marketplace add heygen-com/hyperframes claude plugin install hyperframes@hyperframes then just type /hyperframes:hyperframes and describe your video. the stack in one line: Blender for the 3D, GSAP for the motion, HyperFrames for the final render. bookmark this before your next client asks for a promo video.
0:19

motion designers are in serious danger, here is why an AI agent can now model a 3D scene in Blender, animate a website and render a finished MP4. you describe it, the agent builds it. three repos doing exactly that: -> HyperFrames: write HTML, get a video. made by HeyGen for AI agents. ask for a 10-second product intro with a fade-in title and background music, and the agent plans it, animates it and renders the MP4 -> MCP for Blender: connects Blender to Claude or any other model. the agent creates objects, builds scenes and edits them in real 3D while you watch -> GSAP skills: the official skills that teach coding agents to animate the web properly with GSAP. timelines, scroll effects, the stuff premium landing pages are made of the setup for HyperFrames in Claude Code is two lines: claude plugin marketplace add heygen-com/hyperframes claude plugin install hyperframes@hyperframes then just type /hyperframes:hyperframes and describe your video. the stack in one line: Blender for the 3D, GSAP for the motion, HyperFrames for the final render. bookmark this before your next client asks for a promo video.

kiosa

60,385 Aufrufe • vor 5 Tagen