正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

this is crazy... the guy reverse-engineered his Meta Ray-Bans 3 with Opus 5.5 into a 3,000+ Elo chess engine he built AI chess cheat glasses on Opus 5.5 + Jev and open-sourced the whole workflow here's how it works step by step: step 1 → install it on your... Mac with one command: npx chesshacker setup. It downloads Stockfish from GitHub and verifies the checksum step 2 → put on Meta Ray-Bans and video-call your own Mac on WhatsApp. The glasses see the board, the Mac sees what the glasses see step 3 → the Mac grabs frames straight from the call window. About 1 per second while it waits for the opponent, 1 every 3 seconds on your turn step 4 → Jev runs a cheap pre-check on every frame: is the board readable, is a hand over it, did a piece move? No change means no expensive AI call step 5 → only then Opus 5.5 reads the board. The app compares it with the position it already knows and accepts a move only if it's legal step 6 → Stockfish thinks for half a second and picks the best reply, with an eval like +1.5 or "mate in 3" step 7 → macOS speaks it through a virtual mic into the WhatsApp call: "Rook a to d1". You hear it in your ear step 8 → on the Mac a command center shows everything live: whose turn it is, the suggested move with a confidence bar, the move list and a log under the hood: → if Opus loses track of the board, the glasses say "Lost track of the board" and you fix it with undo or by typing the move → if Stockfish crashes, it restarts once and says "Something went wrong. Still trying" → every game is saved as a PGN file, API keys live in the macOS Keychain → an overlay draws the suggested move as an arrow on the live video, ready for OBS Clone his workflow below Then read the guide on how to reverse-engineer anything with Opus 5.5.show more

Movez

45,673 subscribers

182,461 次观看 • 15 小时前 •via X (Twitter)

科学技术游戏

Anya Rossi• Live Now

Private livecam show

16 条评论

Codez 的头像

Codez15 小时前

bro, this is trully insane !

Movez 的头像

Movez15 小时前

yeah mate and his workflow is open-soursed !

Juan D. Gon 的头像

Juan D. Gon8 小时前

That's not fun at all! 😂

shmidt 的头像

shmidt14 小时前

damn its crazy

Wow Cool 的头像

Wow Cool10 小时前

Stop encouraging this behavior by sharing how to do it. This is pathetic.

def not sofia 的头像

def not sofia8 小时前

Well said!

Cooler 的头像

Cooler13 小时前

cheater

LittlePoly 的头像

LittlePoly14 小时前

I can’t believe this stuff is opened sourced

Serg 的头像

Serg11 小时前

Great use and creativity.

Ginger Goblin 🍀 的头像

Ginger Goblin 🍀8 小时前

impressive hack. just keep it out of rated games, engine help there is cheating and gets accounts banned. as a training tool though? very cool

Troubling Mind (Fringe Theory, Peer Morality) 的头像

Troubling Mind (Fringe Theory, Peer Morality)9 小时前

Vernor Vinge predicted this.

dasv 的头像

dasv12 小时前

So he cheated

Beliy 的头像

Beliy13 小时前

Is this cheating?

AGI in our lifetime 的头像

AGI in our lifetime9 小时前

Cheating at chess is like mussitation, you can do it but its like making out with your sister!

Henrikh 的头像

Henrikh14 小时前

i recently saw this guy on insta

Dennis Rongo 的头像

Dennis Rongo8 小时前

Why even bother you playing at this point. I like the various ways you can get creative with AI but this is not it.

相关视频

I turned my DJI Mavic into a home security drone with REA & Opus 5.5. this f*cking is insane.. I reverse-engineered my DJI drone with Opus 5.5 no cloud. no GPS on the target. it all runs on the phone. iPhone or Android. here's the build step by step: step 1 → plug a spare phone into the Mavic remote and paste the prompt below into Claude Code on Opus 5.5 step 2 → Opus checks your drone against the DJI Mobile SDK v5 list. not on it? stop there. no firmware hacks step 3 → it builds a small app on the official DJI SDK: Swift for iPhone, Kotlin for Android step 4 → sync with the alarm: Home Assistant sees it trigger → push to your phone → one tap "Launch" step 5 → eyes: a tiny YOLO model on the phone's chip. Core ML on iPhone, LiteRT on Android step 6 → memory: a Kalman filter. he runs behind a fence → LOCKED → COASTING → re-locks on the same ID step 7 → hands: Virtual Stick at 10 Hz. box center → yaw, box size → distance, never closer than 8 m step 8 → at the property line it stops, climbs to 30 m and keeps the camera on him until he's out of sight step 9 → lands back on the pad. the clip with track, distance and timestamps is already on your phone the alarm wakes you up. the drone already knows where he went... Find full prompt below Then, read the article below on how to reverse-engineer anything with Opus 5.5.

I turned my DJI Mavic into a home security drone with REA & Opus 5.5. this f*cking is insane.. I reverse-engineered my DJI drone with Opus 5.5 no cloud. no GPS on the target. it all runs on the phone. iPhone or Android. here's the build step by step: step 1 → plug a spare phone into the Mavic remote and paste the prompt below into Claude Code on Opus 5.5 step 2 → Opus checks your drone against the DJI Mobile SDK v5 list. not on it? stop there. no firmware hacks step 3 → it builds a small app on the official DJI SDK: Swift for iPhone, Kotlin for Android step 4 → sync with the alarm: Home Assistant sees it trigger → push to your phone → one tap "Launch" step 5 → eyes: a tiny YOLO model on the phone's chip. Core ML on iPhone, LiteRT on Android step 6 → memory: a Kalman filter. he runs behind a fence → LOCKED → COASTING → re-locks on the same ID step 7 → hands: Virtual Stick at 10 Hz. box center → yaw, box size → distance, never closer than 8 m step 8 → at the property line it stops, climbs to 30 m and keeps the camera on him until he's out of sight step 9 → lands back on the pad. the clip with track, distance and timestamps is already on your phone the alarm wakes you up. the drone already knows where he went... Find full prompt below Then, read the article below on how to reverse-engineer anything with Opus 5.5.

Codez

161,667 次观看 • 16 小时前

here’s how to build a game-ready room in blender and move it into unreal engine 5 with claude opus 5.5... nobody opened a 3d app by hand, and now it runs in real time the trick is letting opus decide how each object gets made, smart way to set it up: - step 1: connect opus 5.5 to blender through blender mcp - step 2: give it one reference image for the room: layout, mood, light - step 3: simple objects get modeled directly in blender (walls, desk, shelves, boxes, blinds) - step 4: complex props get a reference image first, then tripo turns it into 3d (chair, monitors, figurines) - step 5: opus cleans up the tripo props in blender and places them in the room - step 6: light the scene in blender until the stills look right - step 7: have opus port the whole scene from blender to unreal engine 5 - step 8: the room now runs live in the engine, ready for gameplay the agent works, you direct. he still checked every result and gave notes along the way

here’s how to build a game-ready room in blender and move it into unreal engine 5 with claude opus 5.5... nobody opened a 3d app by hand, and now it runs in real time the trick is letting opus decide how each object gets made, smart way to set it up: - step 1: connect opus 5.5 to blender through blender mcp - step 2: give it one reference image for the room: layout, mood, light - step 3: simple objects get modeled directly in blender (walls, desk, shelves, boxes, blinds) - step 4: complex props get a reference image first, then tripo turns it into 3d (chair, monitors, figurines) - step 5: opus cleans up the tripo props in blender and places them in the room - step 6: light the scene in blender until the stills look right - step 7: have opus port the whole scene from blender to unreal engine 5 - step 8: the room now runs live in the engine, ready for gameplay the agent works, you direct. he still checked every result and gave notes along the way

rewind

82,159 次观看 • 8 天前

build an open-world combat prototype in unreal engine with claude opus 5.5... in just a few days the trick is letting opus direct the work inside the engine. here’s the workflow: - step 1: connect opus 5.5 to unreal engine through mcp - step 2: generate the character in tripo ai with smart mesh p2 for a clean low-poly mesh - step 3: clean the asset up in blender, then import it into unreal - step 4: have opus build the map: terrain, hills, paths, autumn trees, flower meadows - step 5: add movement and sword attacks on top of unreal’s third person template - step 6: have opus add sword trails with niagara - step 7: make the grass react: it burns and darkens wherever the blade hits - step 8: run through the world and fix what looks off up close effects should touch the world. a sword trail is nice (dev: xikhar)

build an open-world combat prototype in unreal engine with claude opus 5.5... in just a few days the trick is letting opus direct the work inside the engine. here’s the workflow: - step 1: connect opus 5.5 to unreal engine through mcp - step 2: generate the character in tripo ai with smart mesh p2 for a clean low-poly mesh - step 3: clean the asset up in blender, then import it into unreal - step 4: have opus build the map: terrain, hills, paths, autumn trees, flower meadows - step 5: add movement and sword attacks on top of unreal’s third person template - step 6: have opus add sword trails with niagara - step 7: make the grass react: it burns and darkens wherever the blade hits - step 8: run through the world and fix what looks off up close effects should touch the world. a sword trail is nice (dev: xikhar)

rewind

19,036 次观看 • 1 天前

Claude Opus 5.5 just reverse-engineered my CarPlay... 1 voice command + 5 min = total control: CarPlay that obeys me, ads skipped, any app on the dash and that’s just the beginning here’s the full guide step by step: step 1 → plug your iPhone into the car and put your laptop on the same hotspot step 2 → paste the prompt below into Claude Code with a photo of your head unit step 3 → unlock the hidden engineering menu - Claude tells you the exact button combo on the wheel step 4 → hit “allow” on the screen once - last time you lift a finger step 5 → say “Hey Claude, open the Roadster launch on CarPlay” - it opens YouTube, types the search, hits play step 6 → add any app straight from GitHub - no App Store, no CarPlay whitelist the result: you talk, the dash moves. anything you can say, your car can do... p.s: works on almost any CarPlay head unit. Mine in the video is a BMW iDrive Try it now, you’re welcome. Then read the article below on how to reverse-engineer anything:

Claude Opus 5.5 just reverse-engineered my CarPlay... 1 voice command + 5 min = total control: CarPlay that obeys me, ads skipped, any app on the dash and that’s just the beginning here’s the full guide step by step: step 1 → plug your iPhone into the car and put your laptop on the same hotspot step 2 → paste the prompt below into Claude Code with a photo of your head unit step 3 → unlock the hidden engineering menu - Claude tells you the exact button combo on the wheel step 4 → hit “allow” on the screen once - last time you lift a finger step 5 → say “Hey Claude, open the Roadster launch on CarPlay” - it opens YouTube, types the search, hits play step 6 → add any app straight from GitHub - no App Store, no CarPlay whitelist the result: you talk, the dash moves. anything you can say, your car can do... p.s: works on almost any CarPlay head unit. Mine in the video is a BMW iDrive Try it now, you’re welcome. Then read the article below on how to reverse-engineer anything:

Codez

127,742 次观看 • 8 天前

how to create a local game using Claude Opus 5.5 and Unity 6... a beach, a pier, a day/night cycle, real fishing controls the trick is never asking for “a fishing game” in one prompt: - step 1: create a unity 6 project (urp template) and install unity’s plugin in claude code - step 2: greybox the level with simple shapes and a camera, no art yet - step 3: add the core mechanic in one prompt, then play it until it feels right - step 4: generate models in tripo, clean them up with opus in blender, import as fbx - step 5: add light, water, effects and sound last - step 6: have opus playtest it with an autopilot and list the bugs before fixing anything who does what: > unity 6: the world, physics, ui > tripo + blender: every model > opus 5.5: scripts, scene setup, cleanup, tests > you: play it and decide what stays commit after every step that works. one bad prompt then costs you seconds, not an evening

how to create a local game using Claude Opus 5.5 and Unity 6... a beach, a pier, a day/night cycle, real fishing controls the trick is never asking for “a fishing game” in one prompt: - step 1: create a unity 6 project (urp template) and install unity’s plugin in claude code - step 2: greybox the level with simple shapes and a camera, no art yet - step 3: add the core mechanic in one prompt, then play it until it feels right - step 4: generate models in tripo, clean them up with opus in blender, import as fbx - step 5: add light, water, effects and sound last - step 6: have opus playtest it with an autopilot and list the bugs before fixing anything who does what: > unity 6: the world, physics, ui > tripo + blender: every model > opus 5.5: scripts, scene setup, cleanup, tests > you: play it and decide what stays commit after every step that works. one bad prompt then costs you seconds, not an evening

rewind

38,620 次观看 • 11 天前

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓

Carnage

16,674 次观看 • 1 个月前

Claude Opus 5.5 just hacked my TV box and turned it into Mac Mini... my AI agents now run 24/7 on free box from my TV provider while I sleep (every step on video) 1 reverse-engineering prompt + guide below = you don't need $899 Mac Mini: step 1 → that box behind your TV is a Linux computer, Claude does the thinking in the cloud, TV box just runs the tools step 2 → Claude Code x-rays it from prompt below + one photo step 3 → it installs a real Linux shell built for your chip, many boxes run 32-bit Android, so the wrong build won't even install step 4 → then it adds a wake lock + battery whitelist, so Android can't kill your agent in the background like normal apps step 5 → it wires the agent to your own Telegram bot: answers only you, zero open ports, your API key never touches the chat step 6 → close your laptop and set a task once, it runs all night with zero babysitting step 7 → optional: hook your TV up as a live terminal and watch the agent think and write every line of code in real time the result: $899 Mac Mini is faster with 8x the RAM, but for small 24/7 AI tasks - TV box does the job (but 8 TV boxes still cost less than one $899 Mac Mini) p.s: this methodworks on Android TV, Google TV and Fire TV boxes on Android 7+, mine has just 2 GB of RAM different box? let Claude Code figure it out Run it today. Then read article below on how to reverse-engineer anything:

Claude Opus 5.5 just hacked my TV box and turned it into Mac Mini... my AI agents now run 24/7 on free box from my TV provider while I sleep (every step on video) 1 reverse-engineering prompt + guide below = you don't need $899 Mac Mini: step 1 → that box behind your TV is a Linux computer, Claude does the thinking in the cloud, TV box just runs the tools step 2 → Claude Code x-rays it from prompt below + one photo step 3 → it installs a real Linux shell built for your chip, many boxes run 32-bit Android, so the wrong build won't even install step 4 → then it adds a wake lock + battery whitelist, so Android can't kill your agent in the background like normal apps step 5 → it wires the agent to your own Telegram bot: answers only you, zero open ports, your API key never touches the chat step 6 → close your laptop and set a task once, it runs all night with zero babysitting step 7 → optional: hook your TV up as a live terminal and watch the agent think and write every line of code in real time the result: $899 Mac Mini is faster with 8x the RAM, but for small 24/7 AI tasks - TV box does the job (but 8 TV boxes still cost less than one $899 Mac Mini) p.s: this methodworks on Android TV, Google TV and Fire TV boxes on Android 7+, mine has just 2 GB of RAM different box? let Claude Code figure it out Run it today. Then read article below on how to reverse-engineer anything:

codila

55,706 次观看 • 7 天前

Claude Opus 5.5 just reverse-engineered my TV... 1 prompt + 5 min = total control: 10x faster UI, ads blocked, any app from GitHub and that's just the beginning here's full guide step by step: step 1 → put your computer and TV on the same Wi-Fi network step 2 → paste the prompt below into Claude Code with a photo of your TV step 3 → unlock the hidden Developer menu with your remote - Claude tells you what to press step 4 → hit "allow" on the TV - it's last time you touch the remote step 5 → say yes to the cleanup: no ad rows, no bloat, 2x faster UI - all reversible step 6 → install any open-source app straight from GitHub - no Play Store the result: now anything you can think of, your TV can do... p.s: works on almost any TV. Mine in the video is from 2017 Try it now, you're welcome. Then read article below on how to reverse-engineer anything:

Claude Opus 5.5 just reverse-engineered my TV... 1 prompt + 5 min = total control: 10x faster UI, ads blocked, any app from GitHub and that's just the beginning here's full guide step by step: step 1 → put your computer and TV on the same Wi-Fi network step 2 → paste the prompt below into Claude Code with a photo of your TV step 3 → unlock the hidden Developer menu with your remote - Claude tells you what to press step 4 → hit "allow" on the TV - it's last time you touch the remote step 5 → say yes to the cleanup: no ad rows, no bloat, 2x faster UI - all reversible step 6 → install any open-source app straight from GitHub - no Play Store the result: now anything you can think of, your TV can do... p.s: works on almost any TV. Mine in the video is from 2017 Try it now, you're welcome. Then read article below on how to reverse-engineer anything:

codila

575,487 次观看 • 8 天前

here's how to make a cozy fishing game solo with Claude Opus 5.5 + Blender + 3D AI + Unity 6... the trick is giving every tool one job, but there's a smart way to set it up: - step 1: generate every 3D model with Tripo Smart Mesh P2: palms, rocks, the pier, the boat, the hut, the character - step 2: connect Claude Code to Blender through MCP - step 3: Opus 5.5 sets up each model in Blender: scale, pivots, materials, clean export - step 4: Opus animates in Blender too: the character's walk, the cast, the rod, the boat on the water - step 5: bring everything into Unity 6 and build the world: forest, river, waterfall, beach, pier - step 6: add the systems one at a time: walking, fishing, bait choice, a time of day - step 7: play it after every step and fix one thing at a time who does what: > Tripo: the 3D models > Opus 5.5 + Blender: setup and animation > Unity 6: the world and the game one person, one stack, one game you'd actually want to play

here's how to make a cozy fishing game solo with Claude Opus 5.5 + Blender + 3D AI + Unity 6... the trick is giving every tool one job, but there's a smart way to set it up: - step 1: generate every 3D model with Tripo Smart Mesh P2: palms, rocks, the pier, the boat, the hut, the character - step 2: connect Claude Code to Blender through MCP - step 3: Opus 5.5 sets up each model in Blender: scale, pivots, materials, clean export - step 4: Opus animates in Blender too: the character's walk, the cast, the rod, the boat on the water - step 5: bring everything into Unity 6 and build the world: forest, river, waterfall, beach, pier - step 6: add the systems one at a time: walking, fishing, bait choice, a time of day - step 7: play it after every step and fix one thing at a time who does what: > Tripo: the 3D models > Opus 5.5 + Blender: setup and animation > Unity 6: the world and the game one person, one stack, one game you'd actually want to play

rewind

232,113 次观看 • 14 天前

here's how to build a game in Unreal Engine with Claude Opus 5.5... the trick is letting Opus work inside the live editor, but there's a smart way to set it up: - step 1: Unreal Engine 5 + the Third Person template, so you can walk and jump from minute one - step 2: enable Unreal MCP and AllToolsets in the editor, start the server - step 3: install Epic's plugin in Claude Code and have Opus read the project before it changes anything - step 4: one prompt builds a playable base level: a valley, a dirt path, a town at the end, 3 glowing collectibles - step 5: test the whole route with the default mannequin before any custom art - step 6: bring in a rigged character on the UE5 Mannequin skeleton, Opus swaps it in and wires walk, run and jump - step 7: import your forest and town assets, Opus places them along the route - step 8: refine in small batches: vegetation, lighting, a minimap, the town entrance and the rule that saves the project... a successful tool call doesn't mean the level is right check the editor after every batch, and never change terrain, lighting and character in one prompt

here's how to build a game in Unreal Engine with Claude Opus 5.5... the trick is letting Opus work inside the live editor, but there's a smart way to set it up: - step 1: Unreal Engine 5 + the Third Person template, so you can walk and jump from minute one - step 2: enable Unreal MCP and AllToolsets in the editor, start the server - step 3: install Epic's plugin in Claude Code and have Opus read the project before it changes anything - step 4: one prompt builds a playable base level: a valley, a dirt path, a town at the end, 3 glowing collectibles - step 5: test the whole route with the default mannequin before any custom art - step 6: bring in a rigged character on the UE5 Mannequin skeleton, Opus swaps it in and wires walk, run and jump - step 7: import your forest and town assets, Opus places them along the route - step 8: refine in small batches: vegetation, lighting, a minimap, the town entrance and the rule that saves the project... a successful tool call doesn't mean the level is right check the editor after every batch, and never change terrain, lighting and character in one prompt

rewind

61,390 次观看 • 20 天前

here’s how to build a japanese canal boat game with claude opus 5.5 + unity 6 + blender.. the trick is one system per prompt, smart way to set it up: - step 1: create a unity 6 urp project and connect opus 5.5 through unity’s plugin and blender mcp - step 2: greybox the canal: water channel, stone walls, 2 bridges, docks - step 3: boat physics: throttle, steering, wake trails, speed in knots on the hud - step 4: opus models the props in blender: the covered boat, houses, the vermilion bridge, the pagoda, lanterns - step 5: water shader + day/night cycle + rain, with lanterns that switch on at dusk - step 6: a compass on top and 9 landmarks that unlock on the map (“water gate, 3 of 9”) - step 7: docking lessons: “come alongside the temple steps below 2 kn and press e” - step 8: opus playtests in play mode, reads the console and lists bugs before fixing who does what: > blender: every model > unity 6: the water, the light, the weather, the ui > opus 5.5: boat physics, quests, scene setup, tests > you: steer it and say what feels off i like to test every feature at night in the rain. if it still looks good there, it’ll look good everywhere.

here’s how to build a japanese canal boat game with claude opus 5.5 + unity 6 + blender.. the trick is one system per prompt, smart way to set it up: - step 1: create a unity 6 urp project and connect opus 5.5 through unity’s plugin and blender mcp - step 2: greybox the canal: water channel, stone walls, 2 bridges, docks - step 3: boat physics: throttle, steering, wake trails, speed in knots on the hud - step 4: opus models the props in blender: the covered boat, houses, the vermilion bridge, the pagoda, lanterns - step 5: water shader + day/night cycle + rain, with lanterns that switch on at dusk - step 6: a compass on top and 9 landmarks that unlock on the map (“water gate, 3 of 9”) - step 7: docking lessons: “come alongside the temple steps below 2 kn and press e” - step 8: opus playtests in play mode, reads the console and lists bugs before fixing who does what: > blender: every model > unity 6: the water, the light, the weather, the ui > opus 5.5: boat physics, quests, scene setup, tests > you: steer it and say what feels off i like to test every feature at night in the rain. if it still looks good there, it’ll look good everywhere.

rewind

17,666 次观看 • 6 天前

i built a small playable game in Unreal Engine with Claude Opus 5.5... no blueprints by hand, Claude worked inside the running editor the trick is the live connection, but there's a smart way to set it up: - step 1: Unreal Engine 5.8 + a Third Person project, under source control - step 2: enable Unreal MCP and AllToolsets, start the server - step 3: install Epic's free plugin for Claude Code and start Claude in the project folder - step 4: build a greybox level first: a path, a walled village, a tower you can see from the start - step 5: add the rules: 3 orbs, a locked gate, "You made it", R to restart - step 6: add one enemy, then health, then your attack, one feature per prompt - step 7: only then make it look good: your character, real assets, lighting and every prompt follows the same 4 rules... - say what "done" means - say what must not change - ask for a list of everything it touched - no silent workarounds: if it can't do it, it stops and says so the full course is in the article 👇🏻

i built a small playable game in Unreal Engine with Claude Opus 5.5... no blueprints by hand, Claude worked inside the running editor the trick is the live connection, but there's a smart way to set it up: - step 1: Unreal Engine 5.8 + a Third Person project, under source control - step 2: enable Unreal MCP and AllToolsets, start the server - step 3: install Epic's free plugin for Claude Code and start Claude in the project folder - step 4: build a greybox level first: a path, a walled village, a tower you can see from the start - step 5: add the rules: 3 orbs, a locked gate, "You made it", R to restart - step 6: add one enemy, then health, then your attack, one feature per prompt - step 7: only then make it look good: your character, real assets, lighting and every prompt follows the same 4 rules... - say what "done" means - say what must not change - ask for a list of everything it touched - no silent workarounds: if it can't do it, it stops and says so the full course is in the article 👇🏻

rewind

62,470 次观看 • 21 天前

claude opus 5.5 can now build, rig and animate full 3d scenes inside blender... the trick is letting opus orchestrate instead of model, but there’s a smart way to set it up: - step 1: install blender 5.2.2 and the official blender mcp server - step 2: open claude, pick opus 5.5 on high effort, run /mcp to confirm blender is connected - step 3: install blender kit (edit > preferences > install from disk) for 140k+ free models, materials and hdris - step 4: ask opus “can you see the blender kit library?” so it runs a test search before you build - step 5: paste a reference image and a plain prompt. talk to it like a junior 3d designer, no structured prompts - step 6: for characters, ask for the rig in the same prompt (“keep it realistic, rig it for smooth animation”) - step 7: render a 480p preview first, then the final render (1080p can take 1-2 hours) who does what: - blender kit: chairs, couches, cars, wood beams, textures - opus 5.5: writes the code, places assets, sets lights, rigs, animates - blender: renders every frame - you: review and fix the small stuff by hand and the rule that saves the project... never let opus build a chair from scratch. it burns tokens and still looks fake. pull the asset and let opus arrange it i like to check animations step by step before the final render. a glitch you miss early costs you 2 hours later

claude opus 5.5 can now build, rig and animate full 3d scenes inside blender... the trick is letting opus orchestrate instead of model, but there’s a smart way to set it up: - step 1: install blender 5.2.2 and the official blender mcp server - step 2: open claude, pick opus 5.5 on high effort, run /mcp to confirm blender is connected - step 3: install blender kit (edit > preferences > install from disk) for 140k+ free models, materials and hdris - step 4: ask opus “can you see the blender kit library?” so it runs a test search before you build - step 5: paste a reference image and a plain prompt. talk to it like a junior 3d designer, no structured prompts - step 6: for characters, ask for the rig in the same prompt (“keep it realistic, rig it for smooth animation”) - step 7: render a 480p preview first, then the final render (1080p can take 1-2 hours) who does what: - blender kit: chairs, couches, cars, wood beams, textures - opus 5.5: writes the code, places assets, sets lights, rigs, animates - blender: renders every frame - you: review and fix the small stuff by hand and the rule that saves the project... never let opus build a chair from scratch. it burns tokens and still looks fake. pull the asset and let opus arrange it i like to check animations step by step before the final render. a glitch you miss early costs you 2 hours later

rewind

134,662 次观看 • 14 天前

here's how to build a game like this with Claude Opus 5.5 + Blender + Unreal Engine + Meshy... the trick is giving every tool one job, but there's a smart way to set it up: - step 1: install Claude Code, Unreal Engine 5 and Blender 5.1+, all free except the Claude plan - step 2: connect Blender through its MCP add-on, and Meshy through Meshy MCP with an API key - step 3: brainstorm 5 game ideas with Opus first, pick one, have it expand the idea before anything gets built - step 4: tell it your GPU, so it pushes the graphics as far as your machine can run - step 5: Meshy generates the props and characters, Opus imports them into Blender and cleans them up - step 6: Opus brings everything into Unreal: the level, lighting, HUD, minimap - step 7: play it, then add one feature per prompt: combat, enemies, quests who does what: > Meshy: the 3D models > Blender: cleanup, placement, materials > Unreal: lighting, physics, the actual game > Opus: runs all three from one chat and the real cost... one full first build took about 4 hours and ~19% of a weekly Max plan build the first level well, then the next ones go much faster because the assets already exist

here's how to build a game like this with Claude Opus 5.5 + Blender + Unreal Engine + Meshy... the trick is giving every tool one job, but there's a smart way to set it up: - step 1: install Claude Code, Unreal Engine 5 and Blender 5.1+, all free except the Claude plan - step 2: connect Blender through its MCP add-on, and Meshy through Meshy MCP with an API key - step 3: brainstorm 5 game ideas with Opus first, pick one, have it expand the idea before anything gets built - step 4: tell it your GPU, so it pushes the graphics as far as your machine can run - step 5: Meshy generates the props and characters, Opus imports them into Blender and cleans them up - step 6: Opus brings everything into Unreal: the level, lighting, HUD, minimap - step 7: play it, then add one feature per prompt: combat, enemies, quests who does what: > Meshy: the 3D models > Blender: cleanup, placement, materials > Unreal: lighting, physics, the actual game > Opus: runs all three from one chat and the real cost... one full first build took about 4 hours and ~19% of a weekly Max plan build the first level well, then the next ones go much faster because the assets already exist

rewind

193,609 次观看 • 18 天前

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

delost

397,521 次观看 • 12 天前

Your CLAUDE.md is making Opus 5.5 dumber, and the fix is one command "double check your work" and "think step by step" they were written for older models on Opus 5.5 they slow it down and make the output worse Lance Martin at Anthropic built the fix: /claude-api prompt-audit > scans your skills, CLAUDE.md and prompts > cuts every line that holds the model back > rewrites the rest with Anthropic's Opus 5.5 guidance 5 minutes later your setup finally speaks the language of the model you're paying for

Your CLAUDE.md is making Opus 5.5 dumber, and the fix is one command "double check your work" and "think step by step" they were written for older models on Opus 5.5 they slow it down and make the output worse Lance Martin at Anthropic built the fix: /claude-api prompt-audit > scans your skills, CLAUDE.md and prompts > cuts every line that holds the model back > rewrites the rest with Anthropic's Opus 5.5 guidance 5 minutes later your setup finally speaks the language of the model you're paying for

Mr. Buzzoni

11,988 次观看 • 21 天前

here's how to build a game like this with Claude Opus 5.5 + Blender + Unity 6... the trick is preparing everything before Opus writes a single line, but there's a smart way to set it up: - step 1: connect Claude Code to Unity and Blender through MCP - step 2: write one big brief: the world, the mechanics, the UI, the mood, plus reference images - step 3: add a CLAUDE.md with your rules, and design docs as the single source of truth so Opus never guesses - step 4: split the work into subagents: design, modeling, textures, and one reviewer that only looks and approves - step 5: Opus models the assets in Blender: the island, palms, pier, boat, fishing hut - step 6: it builds a greybox in Unity first, plays it, fixes it, and repeats - step 7: mechanics one layer at a time: walking, casting, bait, catching, day and night - step 8: you watch and give feedback with a reason: "too dark at dusk", "cut the water stripes" and the two rules that make it work... the agent that builds is never the one that approves every fix gets written into a file, so the next project starts smarter start small, a fishing game is the perfect first project

here's how to build a game like this with Claude Opus 5.5 + Blender + Unity 6... the trick is preparing everything before Opus writes a single line, but there's a smart way to set it up: - step 1: connect Claude Code to Unity and Blender through MCP - step 2: write one big brief: the world, the mechanics, the UI, the mood, plus reference images - step 3: add a CLAUDE.md with your rules, and design docs as the single source of truth so Opus never guesses - step 4: split the work into subagents: design, modeling, textures, and one reviewer that only looks and approves - step 5: Opus models the assets in Blender: the island, palms, pier, boat, fishing hut - step 6: it builds a greybox in Unity first, plays it, fixes it, and repeats - step 7: mechanics one layer at a time: walking, casting, bait, catching, day and night - step 8: you watch and give feedback with a reason: "too dark at dusk", "cut the water stripes" and the two rules that make it work... the agent that builds is never the one that approves every fix gets written into a file, so the next project starts smarter start small, a fishing game is the perfect first project

rewind

178,421 次观看 • 16 天前

$JEV + OPUS 5.5 IS INSANE FOR BUILDING A COMPANY BRAIN I pulled the whole architecture out of the TypeSafe and Anthropic docs and packed it into a 14-page PDF the 10 steps: 1. meet the pair > Opus 5.5 thinks, Jev decides, your code holds the branch 2. stop asking a text generator for a yes or no > Jev returns a typed answer with a calibrated probability in 0.44s for $0.00035 3. ask everything at once > Choice, Score and Noul run in parallel, so the fourth question costs almost nothing 4. branch on the number > 0.999 goes straight into the if statement. ~99% of turns end right here 5. stop routing blind > Opus 5.5 to Sonnet and back costs 5.84 against 3.32 for staying on 5.5 6. keep one context warm > cache reads at $0.20 per Mtok are 20x cheaper than a fresh load 7. escalate the hard part > the toughest 1% goes to Opus 5.5 with 1M context and 66.4% on Terminal-Bench 4.0 8. score every chunk on every query > keep whole, summarize or drop. the context gets rebuilt each turn 9. gate the actual command > every bash call gets classified before it runs, inside your own code 10. judge 100% of runs > $3.50 a day for 10,000 traces, and it matched the human label on all 500 decisions the result: a while loop that paid a frontier model for every tiny call turns into a brain that spends a fraction of a cent to notice and pays properly only when it has to think the person who brings this into their team walks into the budget meeting with the AI bill cut and the output up the PDF maps the company brain. the loop side of it - how Jev takes a Claude bill from $765 to $3 a month - is in the article below ↓$

JEV + OPUS 5.5 IS INSANE FOR BUILDING A COMPANY BRAIN I pulled the whole architecture out of the TypeSafe and Anthropic docs and packed it into a 14-page PDF the 10 steps: 1. meet the pair > Opus 5.5 thinks, Jev decides, your code holds the branch 2. stop asking a text generator for a yes or no > Jev returns a typed answer with a calibrated probability in 0.44s for $0.00035 3. ask everything at once > Choice, Score and Noul run in parallel, so the fourth question costs almost nothing 4. branch on the number > 0.999 goes straight into the if statement. ~99% of turns end right here 5. stop routing blind > Opus 5.5 to Sonnet and back costs 5.84 against 3.32 for staying on 5.5 6. keep one context warm > cache reads at $0.20 per Mtok are 20x cheaper than a fresh load 7. escalate the hard part > the toughest 1% goes to Opus 5.5 with 1M context and 66.4% on Terminal-Bench 4.0 8. score every chunk on every query > keep whole, summarize or drop. the context gets rebuilt each turn 9. gate the actual command > every bash call gets classified before it runs, inside your own code 10. judge 100% of runs > $3.50 a day for 10,000 traces, and it matched the human label on all 500 decisions the result: a while loop that paid a frontier model for every tiny call turns into a brain that spends a fraction of a cent to notice and pays properly only when it has to think the person who brings this into their team walks into the budget meeting with the AI bill cut and the output up the PDF maps the company brain. the loop side of it - how Jev takes a Claude bill from $765 to $3 a month - is in the article below ↓

Mr. Buzzoni

103,282 次观看 • 29 天前

JEV + SONNET 5.5 is the most dangerous combo in design right now... That's not a screen recording you're watching - It's a live website - and here is how it came together Step 1: I went through oryzo frame by frame and took its grammar (the pacing, the type, the way the camera moves) Step 2: The whole scroll hangs on one hero object, so I rebuilt Claude's pixel mascot in code from 500 voxels without downloading a single 3D file Step 3: Each frame depends only on the scroll position, with no timers and nothing random, so the same spot in the scroll always gives you the same frame and the site renders straight into a film Step 4: Jev handles the routing, so scenes, 3D and copy go to Sonnet 5.5 while the frame by frame taste review goes to Opus 5.5 Step 5: Four Sonnet 5.5 agents worked in parallel and had four scenes built in roughly 24 minute Step 6: Nothing ships until every still has been looked at, and whatever looks cheap gets rebuilt You and I are using the same model. What changes the result is the harness you build around it Prompt's in the comments

JEV + SONNET 5.5 is the most dangerous combo in design right now... That's not a screen recording you're watching - It's a live website - and here is how it came together Step 1: I went through oryzo frame by frame and took its grammar (the pacing, the type, the way the camera moves) Step 2: The whole scroll hangs on one hero object, so I rebuilt Claude's pixel mascot in code from 500 voxels without downloading a single 3D file Step 3: Each frame depends only on the scroll position, with no timers and nothing random, so the same spot in the scroll always gives you the same frame and the site renders straight into a film Step 4: Jev handles the routing, so scenes, 3D and copy go to Sonnet 5.5 while the frame by frame taste review goes to Opus 5.5 Step 5: Four Sonnet 5.5 agents worked in parallel and had four scenes built in roughly 24 minute Step 6: Nothing ships until every still has been looked at, and whatever looks cheap gets rebuilt You and I are using the same model. What changes the result is the harness you build around it Prompt's in the comments

Carnage

13,981 次观看 • 27 天前

THIS IS AN ABSOLUTE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: Opus 5.5 writes the entire plan as a script, and a swarm of cheaper agents executes it. Bigger jobs and far fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just start Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only steps in at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, you'll reach for it on every big task.

THIS IS AN ABSOLUTE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: Opus 5.5 writes the entire plan as a script, and a swarm of cheaper agents executes it. Bigger jobs and far fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just start Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only steps in at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet ships. JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, you'll reach for it on every big task.

Callan

13,934 次观看 • 10 天前