Pinned Tweet
Got my first repost from Elon Musk
Honestly, it's inspiring when the world's first trillionaire reposts your content
It feels like social proof that I should keep improving my content and myself as an expert
X is the best platform for getting quality content noticed and selling services at a high ticket
The repost feels great. Creating useful content feels better. Back to work
grokbot it's an agent with its own identity, its own computer, and it stays on when you're not
here's what "active AI employee" actually looks like in the demo:
- chief of staff agent - checks in on your other agents, reads your calendar, dispatches tasks to the right one automatically
- shopping agent - logged into your accounts, books tickets, buys groceries, reports back
- marketing agent - signed into your actual linkedin, browses your past posts for tone, then writes and publishes a new one on its own
- engineering agents - self-triage bug reports, kick off cloud coding agents, come back with a pull request, a screenshot, and a video of the fix
the interface isn't a dashboard, it's a chat - same shape as texting a coworker, no tool calls to babysit
the number that matters more than any of the demos: grok 4.6 scored 70.8% on cursor bench at $2.81 a task, fable 5 max scored 70.5% at $17.32
same capability, 6x the cost difference - that's the unlock that makes running a fleet of these actually affordable instead of a novelty
rewind retweeted
ghost hunter is back, this time in a clock tower i built in unreal engine 5 with claude opus 5.5..
new mechanic: echo shift
here’s the workflow:
- step 1: build echo shift as a system: q swaps two versions of the same room (past / present)
- step 2: greybox the tower: stairs, a broken bridge, the gear room, a ballroom, the clock chamber
- step 3: puzzles that need both timelines: the bridge only exists in the past, the ghost dancers only show in the present
- step 4: chain the goals: reach the clock chamber > find the winding key > hold e to power the core
- step 5: payoff: the clock face lights up and the whole city below wakes up (“clock tower restored”)
- step 6: lumen per timeline (warm lamps in the past, cold blue in the present), niagara for the ghosts and the energy core
- step 7: models from tripo, cleaned up by opus in blender, imported as fbx
- step 8: opus plays through both timelines, reads the output log and lists bugs before fixing
who does what:
> unreal engine 5: the tower, lumen, niagara, ui
> tripo + blender: the gears, the clock, the energy core, the ballroom
> opus 5.5: echo shift, puzzles, level setup, playtests
build the mechanic before the map. every room in the tower exists to use echo shift
i built a ghost-hunting game in unreal engine 5 with claude opus 5.5...
there’s a smart way to set it up:
- step 1: start a ue5 project from the third person template, connect opus 5.5 through unreal mcp
- step 2: keep the template’s movement, let opus build on top of it
- step 3: greybox 5 rooms: gallery, library, music room, attic, observatory
- step 4: vacuum beam + ghosts that get pulled in + a “captured 0/3” hud
- step 5: puzzles: hidden bookshelf door, moon lens in the attic, the lens fixes the observatory
- step 6: lumen per room (blue = haunted, gold = restored), niagara for the beam and stars
- step 7: models from tripo, cleaned up by opus in blender, imported as fbx
- step 8: opus playtests, reads the output log, lists bugs before fixing
who does what:
> unreal engine 5: the mansion, lumen, niagara, ui
> tripo + blender: the hero, the piano, the bookshelves, the telescope
> opus 5.5: blueprints and c++, level setup, effects, play tests
> you: play it and say what feels off
one system per prompt, and commit after every system that works
ghost hunter is back, this time in a clock tower i built in unreal engine 5 with claude opus 5.5..
new mechanic: echo shift
here’s the workflow:
- step 1: build echo shift as a system: q swaps two versions of the same room (past / present)
- step 2: greybox the tower: stairs, a broken bridge, the gear room, a ballroom, the clock chamber
- step 3: puzzles that need both timelines: the bridge only exists in the past, the ghost dancers only show in the present
- step 4: chain the goals: reach the clock chamber > find the winding key > hold e to power the core
- step 5: payoff: the clock face lights up and the whole city below wakes up (“clock tower restored”)
- step 6: lumen per timeline (warm lamps in the past, cold blue in the present), niagara for the ghosts and the energy core
- step 7: models from tripo, cleaned up by opus in blender, imported as fbx
- step 8: opus plays through both timelines, reads the output log and lists bugs before fixing
who does what:
> unreal engine 5: the tower, lumen, niagara, ui
> tripo + blender: the gears, the clock, the energy core, the ballroom
> opus 5.5: echo shift, puzzles, level setup, playtests
build the mechanic before the map. every room in the tower exists to use echo shift
i built a ghost-hunting game in unreal engine 5 with claude opus 5.5...
there’s a smart way to set it up:
- step 1: start a ue5 project from the third person template, connect opus 5.5 through unreal mcp
- step 2: keep the template’s movement, let opus build on top of it
- step 3: greybox 5 rooms: gallery, library, music room, attic, observatory
- step 4: vacuum beam + ghosts that get pulled in + a “captured 0/3” hud
- step 5: puzzles: hidden bookshelf door, moon lens in the attic, the lens fixes the observatory
- step 6: lumen per room (blue = haunted, gold = restored), niagara for the beam and stars
- step 7: models from tripo, cleaned up by opus in blender, imported as fbx
- step 8: opus playtests, reads the output log, lists bugs before fixing
who does what:
> unreal engine 5: the mansion, lumen, niagara, ui
> tripo + blender: the hero, the piano, the bookshelves, the telescope
> opus 5.5: blueprints and c++, level setup, effects, play tests
> you: play it and say what feels off
one system per prompt, and commit after every system that works
rewind retweeted
Jensen Huang: “… the founders of Higgsfield are visionary in the work that they do … but these are some of the brightest people in the world.”
We're grateful to Jensen and the teams at NVIDIA and TCV for believing in us. Both companies have joined Higgsfield as investors in our Series B
extension.
Since our August Series B:
• We’ve crossed $1 billion in annualized revenue.
• Enterprise contracts are up 71%, growing 100%+ month-over-month
• We’ve grown from 30 million to over 40 million users globally.
TCV has backed Netflix, Facebook, ByteDance and Spotify, companies that changed how people create and consume media. NVIDIA has powered every generation of Higgsfield, from L40 and A40 GPUs through Hopper and Blackwell, with Vera Rubin next to meet growing demand.
Thank you to our creators and customers for building with us every day, and to everyone at Higgsfield whose work brought us here.
The full Bloomberg Announcement is linked below.
Higgsfield, an AI video startup founded by a former Snap executive, said it has attracted investment from Nvidia and TCV to help fund global infrastructure and hiring to capture growing demand. bloomberg.com/news/articles/…
rewind retweeted
with no coding background built a game in 6 weeks with claude opus 5.5 + godot...
there’s a smart way to set it up:
- step 1: run opus 5.5 in claude code inside your godot project
- step 2: build one feature, test it in the game, adjust until it feels right, then start the next
- step 3: generate reference images in your game’s style with codex/astra
- step 4: save every image prompt that works as json, and use them to guide the next generations so the style doesn’t drift
- step 5: make the big 3d assets in tripo p2 from those references
- step 6: model the small props in blender, then texture them in tripo with matching refs (cheaper)
- step 7: animate in cascadeur
- step 8: document every vfx and shader in obsidian so the look stays consistent
who does what:
> opus 5.5: most of the code
> codex/astra: references and assets
> tripo p2: the big 3d models
> godot: custom tools, headless scripts, the game
one json file of good prompts is why every character, monster and prop looks like it belongs in the same game (dev: afterthewinddev)
one concept art image into a real 3d level with claude opus 5.5 + godot...
opus “churned for 33m 5s”
the trick is scoring the render against the reference instead of eyeballing it, smart way to set it up:
- step 1: pick one reference image as the target look
- step 2: have opus generate the level in code from a seed (rust + godot 4.7)
- step 3: build everything from small pieces: single stones, mixed flagstones, single planks, chains
- step 4: skip textures: stone, wood, brass, cloth and flame are all procedural shaders
- step 5: have opus write a script that compares the render with the reference (color, light, contrast, detail) and gives a 0-100 score
- step 6: fix the scene first: lighting, haze, layout
- step 7: auto-fit a color grade (lut) to the reference as the final step
- step 8: loop: render > score > side-by-side > change one thing
i like this way more than image gen > 3d model > cleanup
one generator instead of 100 assets, and no generation credits burned
with no coding background built a game in 6 weeks with claude opus 5.5 + godot...
there’s a smart way to set it up:
- step 1: run opus 5.5 in claude code inside your godot project
- step 2: build one feature, test it in the game, adjust until it feels right, then start the next
- step 3: generate reference images in your game’s style with codex/astra
- step 4: save every image prompt that works as json, and use them to guide the next generations so the style doesn’t drift
- step 5: make the big 3d assets in tripo p2 from those references
- step 6: model the small props in blender, then texture them in tripo with matching refs (cheaper)
- step 7: animate in cascadeur
- step 8: document every vfx and shader in obsidian so the look stays consistent
who does what:
> opus 5.5: most of the code
> codex/astra: references and assets
> tripo p2: the big 3d models
> godot: custom tools, headless scripts, the game
one json file of good prompts is why every character, monster and prop looks like it belongs in the same game (dev: afterthewinddev)
one concept art image into a real 3d level with claude opus 5.5 + godot...
opus “churned for 33m 5s”
the trick is scoring the render against the reference instead of eyeballing it, smart way to set it up:
- step 1: pick one reference image as the target look
- step 2: have opus generate the level in code from a seed (rust + godot 4.7)
- step 3: build everything from small pieces: single stones, mixed flagstones, single planks, chains
- step 4: skip textures: stone, wood, brass, cloth and flame are all procedural shaders
- step 5: have opus write a script that compares the render with the reference (color, light, contrast, detail) and gives a 0-100 score
- step 6: fix the scene first: lighting, haze, layout
- step 7: auto-fit a color grade (lut) to the reference as the final step
- step 8: loop: render > score > side-by-side > change one thing
i like this way more than image gen > 3d model > cleanup
one generator instead of 100 assets, and no generation credits burned
rewind retweeted
Epic Games released an official plugin that lets Claude Code control Unreal Engine directly...
hundreds of editor tools across 30+ toolsets, installed straight from anthropic’s official plugin marketplace.
here’s how to set it up:
- step 1: in claude code run /plugin install unreal-engine-skills-for-claude-code@claude-plugins-official
- step 2: in unreal, enable the modelcontextprotocol and alltoolsets plugins
- step 3: open the editor console and run ModelContextProtocol.StartServer (default port 8000)
- step 4: run ModelContextProtocol.GenerateClientConfig ClaudeCode to create the connection config
- step 5: in claude code run /mcp and check that unreal-mcp is connected
- step 6: test it: “list all actors in the current level”
for teams: add the plugin to .claude/settings.json and everyone who opens the project gets prompted to install it
commit before every long session. claude edits live assets and can move or delete them in one call
github.com/EpicGames/unreal-…
Epic Games released an official plugin that lets Claude Code control Unreal Engine directly...
hundreds of editor tools across 30+ toolsets, installed straight from anthropic’s official plugin marketplace.
here’s how to set it up:
- step 1: in claude code run /plugin install unreal-engine-skills-for-claude-code@claude-plugins-official
- step 2: in unreal, enable the modelcontextprotocol and alltoolsets plugins
- step 3: open the editor console and run ModelContextProtocol.StartServer (default port 8000)
- step 4: run ModelContextProtocol.GenerateClientConfig ClaudeCode to create the connection config
- step 5: in claude code run /mcp and check that unreal-mcp is connected
- step 6: test it: “list all actors in the current level”
for teams: add the plugin to .claude/settings.json and everyone who opens the project gets prompted to install it
commit before every long session. claude edits live assets and can move or delete them in one call
github.com/EpicGames/unreal-…
rewind retweeted
one concept art image into a real 3d level with claude opus 5.5 + godot...
opus “churned for 33m 5s”
the trick is scoring the render against the reference instead of eyeballing it, smart way to set it up:
- step 1: pick one reference image as the target look
- step 2: have opus generate the level in code from a seed (rust + godot 4.7)
- step 3: build everything from small pieces: single stones, mixed flagstones, single planks, chains
- step 4: skip textures: stone, wood, brass, cloth and flame are all procedural shaders
- step 5: have opus write a script that compares the render with the reference (color, light, contrast, detail) and gives a 0-100 score
- step 6: fix the scene first: lighting, haze, layout
- step 7: auto-fit a color grade (lut) to the reference as the final step
- step 8: loop: render > score > side-by-side > change one thing
i like this way more than image gen > 3d model > cleanup
one generator instead of 100 assets, and no generation credits burned
here’s how to build an ori-style platformer with gpt image 2.5 + tripo + claude opus 5.5...
playable on desktop and mobile
the trick is “make it exist first, then make it good”, there’s a smart way to set it up:
- step 1: mock up the mood in gpt image 2.5: night storm, piers, wrecks, one glowing boss
- step 2: turn the mockups into 3d models with tripo p2: the giant, the ships, the piers, the buoys
- step 3: clean the models up in blender: scale, pivots, low poly so they run on mobile
- step 4: make the hero a 2d sprite (run, jump, attack) and drop it into the 3d world
- step 5: have opus 5.5 write the game: movement, jumps, camera, rain, water
- step 6: build the boss around one readable rule: the giant’s light shows where its fist will land
- step 7: add sfx and music from elevenlabs
- step 8: deploy to vercel and send the link
ship an ugly version that works before you polish anything
a playable grey box beats a beautiful mockup
one concept art image into a real 3d level with claude opus 5.5 + godot...
opus “churned for 33m 5s”
the trick is scoring the render against the reference instead of eyeballing it, smart way to set it up:
- step 1: pick one reference image as the target look
- step 2: have opus generate the level in code from a seed (rust + godot 4.7)
- step 3: build everything from small pieces: single stones, mixed flagstones, single planks, chains
- step 4: skip textures: stone, wood, brass, cloth and flame are all procedural shaders
- step 5: have opus write a script that compares the render with the reference (color, light, contrast, detail) and gives a 0-100 score
- step 6: fix the scene first: lighting, haze, layout
- step 7: auto-fit a color grade (lut) to the reference as the final step
- step 8: loop: render > score > side-by-side > change one thing
i like this way more than image gen > 3d model > cleanup
one generator instead of 100 assets, and no generation credits burned
here’s how to build an ori-style platformer with gpt image 2.5 + tripo + claude opus 5.5...
playable on desktop and mobile
the trick is “make it exist first, then make it good”, there’s a smart way to set it up:
- step 1: mock up the mood in gpt image 2.5: night storm, piers, wrecks, one glowing boss
- step 2: turn the mockups into 3d models with tripo p2: the giant, the ships, the piers, the buoys
- step 3: clean the models up in blender: scale, pivots, low poly so they run on mobile
- step 4: make the hero a 2d sprite (run, jump, attack) and drop it into the 3d world
- step 5: have opus 5.5 write the game: movement, jumps, camera, rain, water
- step 6: build the boss around one readable rule: the giant’s light shows where its fist will land
- step 7: add sfx and music from elevenlabs
- step 8: deploy to vercel and send the link
ship an ugly version that works before you polish anything
a playable grey box beats a beautiful mockup
rewind retweeted
any video on your X feed is now a template...
see a video you love, tag @kylon_ai under it, and get your own version back in the replies.
here’s how to use it without just copying:
- step 1: find a video whose pacing caught your attention
- step 2: comment @kylon_ai with your idea: “same timing, make it about my coffee app”
- step 3: get your version back as a full project, not just a file
- step 4: your team leaves notes right on the video: “warmer light here”, “swap the logo, keep the timing”
- step 5: keep the rhythm, rebuild the story around what your product actually does
comment @kylon_ai under any video you love. quote + repost this to get your first month of kylon free 👇
🤝 Paid partnership
Copying is easy. Making it yours is hard.
Meet Kylon Annotations: analyze, annotate and remix to add your team's taste together.
Drop a video below and @kylon_ai , we'll remix for you.
any video on your X feed is now a template...
see a video you love, tag @kylon_ai under it, and get your own version back in the replies.
here’s how to use it without just copying:
- step 1: find a video whose pacing caught your attention
- step 2: comment @kylon_ai with your idea: “same timing, make it about my coffee app”
- step 3: get your version back as a full project, not just a file
- step 4: your team leaves notes right on the video: “warmer light here”, “swap the logo, keep the timing”
- step 5: keep the rhythm, rebuild the story around what your product actually does
comment @kylon_ai under any video you love. quote + repost this to get your first month of kylon free 👇
🤝 Paid partnership
Copying is easy. Making it yours is hard.
Meet Kylon Annotations: analyze, annotate and remix to add your team's taste together.
Drop a video below and @kylon_ai , we'll remix for you.
rewind retweeted
build a medieval town for an open-world game with claude opus 5.5 + blender + image gen...
the trick is building a kit, not a town, smart way to set it up:
- step 1: generate concept art of the town: castle on a hill, ring streets, central plaza
- step 2: generate references for each building type: timber house, stone house, tower, wall
- step 3: have opus model a modular kit in blender: walls, roofs, doors, windows, stairs
- step 4: have opus combine the kit into 5-10 house variants with different roof colors
- step 5: export to unreal engine and lay out the town in code: plaza > ring streets > houses
- step 6: place the castle, the walls and the towers on the high ground
- step 7: fill the gaps: trees, flowers, statues, fences, a forest around the town
- step 8: walk it in third person and fix anything that looks off up close
who does what:
> image gen: the look of every building
> blender + opus: the modular kit and the variants
> unreal engine: terrain, lighting, the open world
> opus 5.5: layout code, placement, fixes
> you: direction, and walking every street
make 10 good house variants and let code place 500. modeling 500 houses by hand takes forever (Founder: Shikhar)
build a medieval town for an open-world game with claude opus 5.5 + blender + image gen...
the trick is building a kit, not a town, smart way to set it up:
- step 1: generate concept art of the town: castle on a hill, ring streets, central plaza
- step 2: generate references for each building type: timber house, stone house, tower, wall
- step 3: have opus model a modular kit in blender: walls, roofs, doors, windows, stairs
- step 4: have opus combine the kit into 5-10 house variants with different roof colors
- step 5: export to unreal engine and lay out the town in code: plaza > ring streets > houses
- step 6: place the castle, the walls and the towers on the high ground
- step 7: fill the gaps: trees, flowers, statues, fences, a forest around the town
- step 8: walk it in third person and fix anything that looks off up close
who does what:
> image gen: the look of every building
> blender + opus: the modular kit and the variants
> unreal engine: terrain, lighting, the open world
> opus 5.5: layout code, placement, fixes
> you: direction, and walking every street
make 10 good house variants and let code place 500. modeling 500 houses by hand takes forever (Founder: Shikhar)
rewind retweeted
dead internet theory is starting to feel less like a theory...
now anyone with an idea can run their own higgsfield content factory
experts said 90% of online content could be ai-generated by 2026. it’s 2026
remember when a weird video meant some guy actually filmed it?
🤝 Paid partnership
dead internet theory is starting to feel less like a theory...
now anyone with an idea can run their own higgsfield content factory
experts said 90% of online content could be ai-generated by 2026. it’s 2026
remember when a weird video meant some guy actually filmed it?
🤝 Paid partnership
rewind retweeted
space bunny was minimax m3.1 flash all along...
the anonymous model that sat at #1 on openrouter for 10 straight days (56.7t tokens) and #1 on opencode for 12 days (106t) finally has a name
so i used it to build a content planner from scratch
the trick is giving it the whole picture at once, smart way to set it up:
- step 1: connect minimax m3.1 flash to claude code and set effort to max
- step 2: dump everything into one prompt: niche, audience, my last 50 posts, what performed and what flopped. the 1m-token context takes it all
- step 3: have it build the app: a 30-day calendar, a hook bank, post drafts per platform
- step 4: add a “why it worked” analyzer that reads my top posts and pulls out the patterns
- step 5: generate a week of posts in my format, then rewrite the weak ones
- step 6: test it, fix the bugs, ship it
what a build like this costs: under $0.50 at api prices (rough math: ~1.5m tokens in, ~300k out)
why it’s cheap enough to run every day:
> $0.15 per 1m input tokens, $0.60 output, $0.015 cached
> 70% lower cost on agentic tasks than the previous minimax model
> 73.7% on deepswe v1.1, close to top coding models
> 200+ tokens per second output
don’t compare price per token, compare the price of a finished task. that’s where this model wins
space bunny was minimax m3.1 flash all along...
the anonymous model that sat at #1 on openrouter for 10 straight days (56.7t tokens) and #1 on opencode for 12 days (106t) finally has a name
so i used it to build a content planner from scratch
the trick is giving it the whole picture at once, smart way to set it up:
- step 1: connect minimax m3.1 flash to claude code and set effort to max
- step 2: dump everything into one prompt: niche, audience, my last 50 posts, what performed and what flopped. the 1m-token context takes it all
- step 3: have it build the app: a 30-day calendar, a hook bank, post drafts per platform
- step 4: add a “why it worked” analyzer that reads my top posts and pulls out the patterns
- step 5: generate a week of posts in my format, then rewrite the weak ones
- step 6: test it, fix the bugs, ship it
what a build like this costs: under $0.50 at api prices (rough math: ~1.5m tokens in, ~300k out)
why it’s cheap enough to run every day:
> $0.15 per 1m input tokens, $0.60 output, $0.015 cached
> 70% lower cost on agentic tasks than the previous minimax model
> 73.7% on deepswe v1.1, close to top coding models
> 200+ tokens per second output
don’t compare price per token, compare the price of a finished task. that’s where this model wins
rewind retweeted
you don't prompt a video anymore, you direct it kling 4.0 on Higgsfield lets you set start, middle and end frames, so you storyboard the key beats and control the pacing instead of regenerating 20 times and hoping.
🤝 Paid partnership
rewind retweeted
Kling is back.
Kling 4.0 is now live on Higgsfield.
> Omni Reference: characters, objects and audio in one generation
> 30-second scenes in a single pass
> Start, middle and end frames to direct every beat
> Native 4K coming soon
Available now on Higgsfield.
rewind retweeted
full office in 3d with claude opus 5.5 + blender...
a few reference shots in, 1,876 objects out
a smart way to set it up:
- step 1: connect opus 5.5 to blender via mcp, send 2-3 reference shots
- step 2: set a fixed camera matching the reference
- step 3: build the room shell first: walls, windows, blinds
- step 4: add big furniture, check against the reference, lock it
- step 5: fill each zone with clutter: desk, shelves, sill, floor
- step 6: add close-up detail where the camera looks most
- step 7: assign materials, then match the reference light
- step 8: render, compare side by side, fix one thing per prompt
i like to keep the reference camera fixed the whole time
same angle every stage, so you instantly see what’s still missing
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