← Back to leaderboard
everestchris6

Chris

Verifiedactive
@everestchris6

Founder - https://t.co/uvz6ynKEF5

25,780 followers · 74 following · Last polled 1h ago
Perf. Score
37.4
Rank #315
Value Score
—
set rates to compute
Median views
1.3K
p25 896 · trailing 7d
Followers
26K
+0.2% 7d
ER (impr.)
1.64%
eng ÷ impressions
ER (foll.)
0.73%
eng ÷ followers
Est. CPM
—
needs a rate
WoW views
-82.0%
▼ falling

Rates & value · est. from 1.3K median organic views

Quote tweet
—
no CPM
Post
—
no CPM
Thread
—
no CPM
Retweet
—
no CPM
rate age unknown (pre-audit import)

Trends

Follower growth
Median views / day
Engagement rate
View distribution · trailing-7d posts

Each blue dot is one organic post. The Performance Score ranks by the median (1.3K), not the mean (11K) — so a single viral post doesn't inflate a creator's reach. The p25 floor (896) is the level 75% of posts clear.

Recent posts · ranked by views

PostPostedViewsLikesRepostsRepliesQuotesBookmarksER
claude opus 5.5 completely solved three.js it took a floor plan and turned it into a 3d house you can walk through home builders pay $5k to $10k per floor plan for this, so buyers can tour a home before it's built and change things if needed here's how to automate client acquisition: > scrape builder sites for plans with no model home > give the plan and their photos to opus 5.5 > it builds the house to scale as a walkable site > send the builder their own plan before you pitch > charge per plan to do the rest of their catalog > rerun it on every new plan they launch give this prompt to your agent to get started: "here's a floor plan and photos for one house. build it as a three.js site i can walk through in the browser, to scale from the plan, with every room, finish and piece of furniture matched to the photos. the bar is the photos themselves. split the house into pieces you can judge separately, and give each one a builder and a separate critic with fresh context. the critic compares a screenshot of our room with the matching photo, picks the better one, names the biggest gap, and sends it back. keep looping until ours wins or i stop you, and tell me anything you couldn't match."frozen9d ago312K4.2K328111405.7K3.32%
https://t.co/LFt7R4cIP8
frozen
25d ago
244K
306
26
4
3
933
0.52%
this is the only prompt you need to make high-end motion videos with claude opus 5.5 ------------------------------ <role> you design and build motion videos entirely in code, with gsap for the animation and three.js for any 3d. every decision is judged against the best work in the references, and the video isn't finished until it holds up next to them. </role> <brief> - what the video is for: [product, service or business] - who's watching: [who the viewer is and what they care about] - what they should do at the end: [call to action] - length and sizes: [e.g. 30 seconds, 16:9 and 9:16] - brand: [name, logo files, colours, fonts] - facts file: [path]. this is the only source for any number, name or claim that appears on screen - assets: [footage, photos, screenshots, product files] - style references: [links or a folder of videos whose motion i like] i'm away and won't answer questions. make the calls yourself and keep going until the video passes every check below. </brief> <kit> before anything else, clone and read https://t.co/FMs1prnPP0. read SKILL.md first, then every reference file it points to at the step where it says to read it. its rules, critic prompts, quality bar, 3d patterns, audio tools and scripts override your defaults. </kit> <setup> - build every scene as an html page animated on a single gsap timeline, with three.js for any 3d, all as pinned local files - render the timeline to video frame by frame using the renderer in the kit - use ffmpeg for frames, contact sheets and audio measurement - keep every api key in environment variables. never write a key into any file - render a 5 second test first and confirm it works before building the real video </setup> <study_the_references> if i gave you references, study them before planning anything. - run a fast numeric pass over every frame: how much changed from the last frame, brightness and edge detail, to find every cut and every fast moment - make one overview contact sheet per video, and a dense sheet of one second at 16 to 20 frames a second around every transition - write a note per video: the key moment, how it works, and how it could be used in this video - pull out the motion rules and named techniques that hold across the best ones - references are for study only. never copy their footage, logos, layouts or music if i gave you no references, use the motion notes in the kit. </study_the_references> <motion_principles> 1. the thing in the front of the shot becomes the transition. a title, logo or object moves towards the camera while the next scene is already waiting underneath 2. one object carries the story across shots and keeps its identity, so it reads as one continuous piece 3. one main movement leads, with smaller ones layered under it, all overlapping. the frame never stops and starts all at once 4. the speed always changes. things land slowly enough to read, leave fast, and the next thing slows as it arrives. no linear motion 5. cuts are allowed only when size, direction and subject match on both sides 6. every action produces a visible result. a scan makes findings, a tap makes a new state, a request makes a confirmation 7. type is motion too. big words enter from opposite sides, reveal the next scene, and never sit over busy picture without something behind them to stay readable 8. vary the scale from close, to wide, to overhead, to full-frame type. never repeat the same layout, like a heading over three cards </motion_principles> <storyboard> write a brief and a storyboard before any animation. - one table: time, what's on screen, what this moment is for, how it leaves, and which object carries into the next shot - around 12 to 15 compositions per 30 seconds, each lasting about 1.4 to 3.5 seconds - the main subject fills most of the frame. no small cards floating in empty space - frame one is a finished picture, never a word halfway through flying in - name three signature moments you can describe without using effect names - the video must make sense with the sound off - send the storyboard to a fresh critic and fix what it finds before building </storyboard> <build> - every animated value is a function of timeline time only. no timers, no real-time animation, no unseeded randomness. any frame must render the same every time - write the shared pieces first: colours, fonts, shared 3d models and the exact pixel position of every handoff between scenes - build each scene as its own component with its own test page, rendered to stills and a short clip, and send it to a critic before it joins the film - carried objects land on exactly the same pixels on both sides of a cut - run several builders in parallel on separate sections once the shared pieces exist - don't stop to ask for approval between steps </build> <3d> - only use 3d where it explains something physical or spatial, like layers, parts, placement or scale - light it like a product shoot, with a soft key light from one side and a rim light behind - keep the camera between about 35 and 55 degrees. never look straight down on a large surface, and never end tight on a flat one - style buildings like a premium architectural model with real materials and a base - no floating parts, no gaps where parts meet, no flat black glass, no repeating textures - labels are html positioned from the 3d scene every frame, never text inside the 3d - measure the rendered background pixel and adjust until it matches the brand colour - anything that moves like a real product is measured from real footage frame by frame, and those measurements are the curve </3d> <images_and_footage> - prefer building shots in code. use generated images or clips only for supporting shots, and label anything generated as a concept - upscale and smooth any generated clip to match the rest, and regenerate anything that warps - never generate a fake finished job, fake customer, fake review or fake result </images_and_footage> <audio> - match the music's energy to the picture and the viewer, and keep it low - prefer clean library music and sound effects over generated ones. never name a brand in a music prompt - one short, soft whoosh per real scene change, and small clicks or pops only on real on-screen actions - screen effects for boom, hiss and length before using them, and set each one just above the music in its own frequency range, with a cap so nothing gets harsh - cut every scene change on a beat - always export a music-only version </audio> <critic_loop> the builder never judges its own work. - after the storyboard, each component and each full render, send the render, the brief and the references to a fresh critic that has seen none of the building - never tell a critic what you think you fixed or what you believe about the references. it pulls its own frames and measures for itself - the critic makes a contact sheet every 0.2 seconds plus dense frames around every transition, measures frozen time and loudness, and returns a ranked list of problems with timestamps, ending with ship or one more pass - fix the biggest problem first, render, then send to a new critic that checks every previous item as fixed, partly fixed or still there, and hunts for anything new that broke - keep a ledger of every round: what was found, what changed, and the numbers before and after </critic_loop> <quality_bar> the video isn't done until all of these pass, measured: - no more than about 1 second of frozen screen per 30 seconds, and no still stretch longer than about half a second - frame one is a finished composition - all text meets at least 4.5:1 contrast, and nothing collides with or flies through other text - brand colours in 3d renders match the brand values - loudness is steady and comfortable for web, with no clipping, and effects never louder than the music - a first-time viewer understands it with the sound off - a critic would put it next to the references without it looking weaker. a video with no bugs is not the same as a good video </quality_bar> <honesty> - only put numbers, names and claims on screen that are in the facts file - no invented testimonials, ratings, prices, savings, warranties or results - anything conceptual or generated is labelled as such - in your reports, separate what you measured from what still needs a human to watch or listen </honesty> <deliverables> - the final mp4 in every size requested, at 1080p and 60 frames a second - a music-only version - a contact sheet of the final video - the critic ledger and the final quality bar results - a short note on anything a human should still check </deliverables>frozen23d ago126K1.1K661392.9K3.17%
never thought i’d be saying this so soon, but you literally can’t tell what’s real on the internet anymore this clip is run through higgsfield genjutsu lite btw, and it’s 5x cheaper right now https://t.co/Sqmz7PSKTz1d ago124K7227242155681.14%
this is the only prompt you need to one-shot a viral ai influencer ------------------------------ <role> you build ai influencers that go viral by putting a character people can't forget into a real clip people already know. you find the clip, design the character, render the remake and hand me a post that's ready to go. you measure before you spend and you never post anything yourself. </role> <brief> - character: [path to a reference sheet, or "invent one" plus any steer on age, vibe or look] - niche: [where the clips come from, like hip-hop, sports, nightlife or hustle culture] - caption language: [language] - lane: [fresh, evergreen or both] - render: [kling 3.0 omni or seedance 2.5, plus the most i'll spend per video] - length: [10, 20 or 30 seconds] - no-go list: [people, topics or brands to avoid] if any of this is empty, ask me everything in one message, read the plan back with a cost estimate, then keep going until the post package is ready. </brief> <setup> - apify for instagram, x and tiktok scraping, replicate for every image and video model, yt-dlp for downloads, ffmpeg for trimming, frames, contact sheets and audio - keep every api key in environment variables and never write a key into any file - save everything into one run folder so i can see each step </setup> <how_it_works> - the original clip carries the recognition and the motion, and the character carries the joke - the joke is status contrast. the absurd character takes the place of the coolest person in the clip and inherits their swagger - every remake that blew up came from a single continuous phone take with no hard cuts and one person holding the frame. treat that as a rule </how_it_works> <character> - one signature feature you can read at phone size from across a room, like a hair shape, a beard, sideburns or eyebrows. never a mask or a costume - strange face, immaculately dressed, one loud wardrobe colour that stands out in a dark club and on a grey street - normal body proportions, empty hands, face uncovered, because swap models break on capes, props and masks - never copy a look that's already viral - a short name people can repeat and a one-word catchphrase in the character's own language - the comedy comes from hair, face and clothes, never from ethnicity, disability or body shaming - render a reference sheet with gpt image 2.5 on a light grey studio backdrop: four full-body views on top (front, three-quarter, side, back) and four close-ups below (deadpan, laughing, shouting with a hand up, side profile of the signature feature) - it has to look like a real person photographed with a camera. if the feature drifts between panels or anything looks cgi, render it again </character> <find_the_trend> fresh lane: - clips only stay remakeable for about a week, so this runs daily - scrape the last 4 days from big repost pages in the niche like worldstar, pubity, daquan, rap, complex, houseofhighlights and overtime - grow the page list from every "via @" and "🎥: @" credit and every tagged account, and keep any repost page over 100k followers - search x for native videos in the niche with high likes from the last 3 days, for cross-platform proof evergreen lane: - scrape the top posts of the ai influencers already going viral and work out which original clip each hit remakes. a clip that already worked as a remake for one character will work again with another - search for the most quoted clips in the niche (famous interviews, walk-outs, freestyles, flexes, dance moments) and pull them from youtube - an old clip that shows up again in this week's fresh scrape gets a bonus - prefer real phone or interview footage over film and tv, which gets claimed and muted </find_the_trend> <score> - fresh: plays against that page's usual plays, plays per hour since posting, and whether the same clip or its audio is spreading across pages and platforms - evergreen: total plays across every copy you found, whether another ai influencer already remade it and beat their usual numbers, and whether it's resurfacing this week - drop anything older than 7 days in the fresh lane, because pinned posts leak into scrapes - expect sports broadcasts and press conferences to top the numbers, which is why the gate below decides </score> <swap_gate> - download the top 15 from each lane - count hard cuts with ffmpeg scene detection, and pass at 0 or 1 in the part you'll use - make an 8 frame contact sheet and look at it. pass only if one person is on screen most of the time with their face and upper body visible, it's real footage (not a broadcast, a stream overlay or a multi-camera edit), and that person is doing something and is the coolest one in the clip - if captions, tweet cards or frames are burned in over the person, trace the clean original through the caption credit and use that - reject anything with a minor as the subject, a private person being humiliated, injury, violence, crime, tragedy, politics, or anything on my no-go list - show me the top 3 with a frame strip, the scores, who gets replaced, the one-line joke and the cost for each render option, and let me pick </swap_gate> <render> both options take the real clip and the reference sheet with one prompt: "replace [person described by position and clothing] with the man in the image. keep his exact motion, gestures, mouth movement and timing. keep every other person, object, the location, camera shake, framing and lighting the same. no text." kling 3.0 omni (cheaper, about $0.28 a second): - video editing mode, with the clip as the base video and the sheet as the reference image, original sound kept - each piece has to be under 10.0 seconds, at least 720 pixels on every side, with square pixels, so re-encode first - for anything longer, split into pieces under 9.5 seconds at calm moments where the person is clearly visible, and render every piece with the exact same sheet and prompt - compare the last frame of each piece with the first frame of the next, and re-render any piece where the face, hair or outfit jumps - join the pieces with no audio, then lay the original audio back over the whole thing as one track seedance 2.5 (premium, about $0.97 a second with a video input): - up to 30 seconds in one pass with no seams and the best consistency - editing mode with the clip as the reference video and the sheet as the reference image, then lay the original audio back on never use kling motion control for this, because it rebuilds the whole scene from its image and rejects crowded clips. never use gemini omni edit mode either, because it blocks any video with a real person in it </render> <check> - make a contact sheet of the finished video and look at every frame - re-render once if the signature feature morphs, anyone except the target changes, text appears that wasn't there, or hands melt at a key moment - never do more than 2 render attempts without asking me </check> <post> - caption in my language, deadpan, in character, under 6 words, never explaining the joke - tag the person replaced and the original creator, because that's how the original artist ends up seeing it - turn on instagram's ai label for the post and the profile, since unlabelled ai accounts lose reach - fresh clips go out while the original is still inside its week, and evergreen clips go out at the account's best hour - first comment from the account is "follow for more" or the catchphrase - never launch or promote a token, and never imply the original person endorsed the character </post> <learn> - log every post with the lane, scores, render option, cost, and plays at 24 and 72 hours - the next time you run, scrape the account first and fill those columns in - after 10 posts, compare plays against each score and each lane, shift the weighting toward whatever actually predicted views, and write down what changed </learn> <honesty> - only put numbers on screen or in captions that you scraped or measured - mark anything you guessed rather than measured - if no clip passes the gate today, say so instead of forcing a weak one </honesty> <deliverables> - the final mp4 at the source resolution, with the original audio - the reference sheet - a short note on why this clip won and why the runners-up lost - the caption, tags and posting time - total spend, and anything a human should still check </deliverables> ```frozen17d ago120K486341038821.17%
you can literally one-shot a viral ai influencer in 5 minutes here how to make $$$ with it: - scrapes the clips going viral in your niche - scores which ones a character can step into - designs the character and its full reference sheet - swaps the character into the clip it picked - turns the views into a paid setup guide here's the full prompt:frozen17d ago71K40012834721.26%
claude opus 5.5 made this whole video the only claude code skill you need to make videos like this for businesses it plans every shot, builds the 3d components, handles the editing and sound, and runs every cut past a critic until it's good enough to sell repo link: https://t.co/vsM6cRgG9Afrozen25d ago69K326191128881.79%
this is a way bigger opportunity than it looks business owners in niches like construction, hvac, roofing, are never going to or set up their own ai agents, and they don’t want to learn what any of it is. but they’re already familiar with imessage, so you can just set this up for them and charge them a setup fee.frozen7d ago51K447182508762.70%
https://t.co/mKxlOhuSj9frozen29d ago34K12113822861.28%
hermes + claude opus 5.5 + jev = automated sales sales is the same few steps every day, and businesses lose customers in them - find where a business is losing its sales - put a number on what each gap costs - turn the fix into a workflow that runs - answer every single lead fast, at any hour - keep following up until they reply, then stop - hand the ones who reply to the owner just wrote a whole guide on how you can set this up:frozen29d ago33K185141003351.67%
https://t.co/1VWxnavjOhfrozen22d ago31K487221350.63%
claude opus 5.5 is f*cking insane it just one-shotted this whole video, and every frame of it is code. with the right setup you can easily sell videos like this to businesses just wrote a whole guide on how to set this up: https://t.co/XuYW4rcY0Cfrozen25d ago29K181131013201.81%
here's a business model you can run with dots on autopilot someone made nearly $200k setting up openclaw for businesses, and dots is easier since they already use chatgpt - finds businesses losing money on admin - makes a video of a dot in their trade - it chases invoices and answers their leads - every reply waits for the owner's approval first - they watch the video and pay right there - you charge monthly to keep their dot tuned - it all reaches them on a postcard with a qr just wrote a whole guide on how you can set this up:frozen22d ago27K13612912651.58%
i built a free library of 70+ video components you can use in your videos agentic video editing is getting so good you can basically one shot a high quality video now they're all code btw, so your agent can customize every part of the component to fit your video you can access it here for completely free: https://t.co/rVzyPJr1vIfrozen5d ago18K329292426105.58%
https://t.co/xK3IUiekeCfrozen18d ago14K8121011571.86%
claude opus 5.5 + three.js is literally AGI it one-shotted a commercial for apple's new homeview from one prompt, and every frame in this video is code here's the process it runs: > studies the reference film and measures it > storyboards every shot before writing code > builds and tests each element on its own > scores every render with a separate critic agent this is the only prompt you need to make videos like this: <role> you are a principal motion designer and real-time graphics engineer. you make product launch films entirely in three.js, every frame code, to the standard of the brand's own films. you prove quality with measurements and independent critics, not adjectives. </role> <brief> - the product, and the 3-5 facts the film may state (verbatim, nothing invented) - the reference film to beat - length, aspect and resolution - never show: [logos, people, footage you don't own] </brief> <study> read the reference frame by frame and turn it into numbers: cut rhythm, camera speeds, the hero motion curve, type size and timing, stage colour. those numbers are the bar. measure it, never copy it. </study> <build> - storyboard first: one table of time, shot, what it proves and the cut out. 2-3 s per shot, and frame 0 is already the money shot - one seek clock: every pixel is a pure function of time - build every element (the device, its screen ui, each shot, the type) alone in its own lab before it joins the film - the screen ui is code, the type is drawn on canvas, and every threshold is a crossfade (hard ones flash for a frame) </build> <loop> - builder and critic are always separate agents. the critic starts fresh every round, judges the rendered frames against the reference, scores them and names the single biggest gap. the builder fixes only that - blind test: mix your frames with the reference's. if a judge can tell which is which, it isn't done - wow gate: split the film into 3 s windows. every one must be a yes </loop> <sound> - one real track, lined up so its own final hit lands on the end card and played as one continuous piece. cut on its beat - a clean, real sound on every small move, with the hero moments clearly audible - music quiet (about -34 lufs), and always a music-only version </sound> <qa> render at 60fps and measure frozen frames, one-frame pops, black frames and loudness. then watch it like the client would: empty space, text over text, labels that lie, shots that linger. </qa>frozen8d ago11K733831482.13%
i put together 20 FREE guides on ai systems you can sell to businesses each guide is the full build, end to end with every prompt included - prospect lists, pre-qualified for you - personalised demos for every lead - outreach to the decision maker - automated booking and follow-ups - recovering money businesses are owed - pricing that pays on results you can get them here for free: https://t.co/rVzyPJr1vIfrozen28d ago5.1K57661903.17%
this is the only prompt you need to one-shot a studio-level 3d website with claude opus 5.5 ------------------------------ <role> you are a principal real-time graphics engineer and technical director. you build scroll-driven websites in raw three.js to the standard of an award-winning studio: a custom hdr render pipeline, chapters composited from their own render targets, shader-driven transitions, procedural scenes with baked light, camera flights keyed to scroll, and one motion clock that holds the dom and webgl on the same frame. you work from a reference you mean to beat, never one you mean to copy. you turn its frames into a bar anyone can inspect, break the page into elements that can be judged alone, and put each one through builder and critic rounds until it clears that bar. you prove the result with frame-perfect 60fps films and optical-flow motion analysis, not adjectives. you estimate cost before you spend, and you report only what you measured. </role> <brief> - concept: [what the site is for, the brand name (yours, never the reference's), and the one-line story it tells as you scroll] - reference to beat: [a url or a screen recording of a site whose motion you love, plus how far to go, like "the first 3 sections"] - style: [describe it, or "interview me"] - sections and copy: [your list and words, or "write it"] - 3d: [models you own (glb), "procedural", or "generate"] - image budget: [gpt image 2.5 on replicate, the most you'll spend in total] - targets: [desktop first or mobile too, and the slowest machine it has to hold 60fps on] - no-go list: [brands, marks, people or topics to avoid] - extras: [a 60fps film of the full scroll, a side-by-side against the reference, or both] if any of this is empty, interview me in one message (questions below), read the plan back with the element list and a cost estimate, then keep going until everything in deliverables is done. </brief> <interview> ask only what the brief left open, all in one message: - what should someone feel in the first three seconds? three words - what should it look like it was made in: oil painting, fashion editorial, product cgi, claymation, risograph print, chrome and glass, film still, something else? - one site, film or artwork whose look you love, and one you'd hate to be mistaken for - the palette, or "pick for me" - how loud should the motion be: calm editorial, cinematic or maximal? - the one moment people should screen-record. what happens on screen? - what does the brand sell or say, and what should the visitor do at the end? then render three style frames (the hero moment in three different directions) with reference crops as input images, show them side by side with one line each, and let me pick before building anything. the pick becomes the art bible. </interview> <setup> - three.js only: vendored, es modules with an importmap, no build step, no frameworks - replicate for every image (gpt image 2.5 with input_images), playwright for captures and films, ffmpeg for frames, contact sheets and encodes, opencv for motion checks - a threaded local server that answers byte-range requests. video seeking breaks without them, and the stock python server drops connections under parallel captures - api keys live in environment variables only, never in a file or printed - one project folder: the site, tools/, and workbench/ (reference frames, every round, scores and the live progress page) </setup> <reference> - read every frame of the reference recording (record the live site yourself only if i say so). extract frames, make a contact sheet per section and name the states that matter: intro, hero settled, each transition beat, each pinned chapter - those named frames are the bar. every element is judged against its own crop of them - the reference is for measuring, never copying: no logos, wordmarks, product photos or code from it. my brand name goes everywhere - every image generation gets reference crops as input_images plus a stated twist. text-only prompts come out generic, and copies come out as copies - cut each image into the layers the motion needs (background plate, each figure, each prop as its own cutout) so parallax and transitions can move them separately </reference> <build> - one smooth scroll value drives everything. native scroll sets a target and a damped value follows it. the dom is translated by that value and every webgl scene reads the same one, so text and pictures never drift apart - a fixed full-screen canvas sits behind the dom text. each chapter renders into its own render target, and one composite pass does the transitions in hdr (half-float targets, a bloom pyramid, a filmic shoulder, dither) - every scroll-driven number lives in one timeline file in viewport heights, keyed to the reference frames, so pacing is tuned in one place - pins get soft corners, easing in and out over at least 0.1 viewport heights. a hard clamp stops dead then launches at full speed, and that reads as a jump - camera paths are splines with keys far enough apart that acceleration stays gentle. check pitch, position and screen speed numerically before rendering, and never stack two direction changes within a few hundredths of a viewport height - heavy chapters build ahead of need in idle time, never inside a frame: compileAsync, one texture upload per frame, images decoded off-thread, procedural textures baked once - each chapter is isolated, so a crash disables that chapter, not the page. debug hooks only respond to url flags - expose window.__app (ready, layout, named states, goto) so the capture tools can drive the page - in glsl, never call smoothstep with edges that can cross, and never divide by a value that can reach zero. on metal either one blanks a whole layer for a frame - respect prefers-reduced-motion with an instant scroll and still frames </build> <the_loop> every piece of work goes through the same loop, one element at a time, never the whole page at once: - set a bar you can point at: the reference crops for that element. never "make it amazing" - split the page into the smallest pieces a critic can judge alone: each image, each effect, each transition, each section, the chrome - each element gets a builder and a critic, always separate agents. the critic starts with fresh context every round, so it judges what is on screen, not what the builder meant - the critic never reads the builder's summary. it captures the real page at the named states from a frozen snapshot (so a builder editing mid-review can't skew it), puts its frames beside the reference crops, scores 1 to 10 against the bar and names the single biggest remaining gap - the builder fixes that gap and nothing else, backs up the previous round and hands back - no fixed round count and no deadlines. stop when the element meets or beats the bar, when two rounds in a row gain less than half a point, when i say stop, or when the budget is spent - if an element is stuck for two rounds, don't push the same approach harder. start a new builder on a new architecture (in the run this prompt comes from, the hardest transition sat at 4/10 until a rebuild around hdr light and bloom) - keep a live progress page in workbench/ with every round's frames, scores and named gap, so i can watch it evolve and anyone (or any agent after a crash or usage limit) can pick up from disk - once the builders are done, run one fresh smoothing agent over the whole page for consistency across the seams between elements </the_loop> <motion_qa> record a frame-perfect film of the full scroll and measure it, because a page that feels fine live can still hitch: - playwright with the fake clock installed and paused (pause_at), so time only moves when the recorder says: exactly one 16 ms animation frame per video frame. left running, the clock drifts with real time and doubles animation speed - seek every waapi/css animation and every video element to the same virtual time each frame, and force preserveDrawingBuffer on webgl - feed the scroll as an exact fractional value with a synthetic scroll event, only on frames where it moves. constant scroll events keep smooth-scroll libraries in their "scrolling" state and can freeze intros - record at the device pixel ratio the site is viewed at (3072x1728 for a 2x laptop screen, 1920x1080 at minimum) at 60fps: png frames piped into x264 at crf 12-14, yuv420p, faststart. hold 6 seconds on the intro, scroll at about 0.75 viewport heights a second, slow to about 0.4 through the signature moments, with speed ramps at least half a viewport long - then run an optical-flow jump scan: flag any frame whose motion changes by more than 3x the local median, look at each one, and fix the cause (hard pins, camera whips, one-frame shader blanks) or write down why it's intended - do a fast low-res pass first to find problems, and render at full quality only once it's clean </motion_qa> <compare> if i asked for the side-by-side: - record the reference with the same recorder, warm its cache first, and map its scroll to ours through matched story beats on a monotone curve, so the same beat lands on the same frame in both films - where the reference has sections we didn't build, cut across them with a hidden warm-up so nothing loads on camera - build a player: two videos side by side with a small logo and name over each, on one simple background. keep them in sync by nudging playback rate (seeking during playback stalls), run every animation on a steady clock rather than on video frames, and animate with transforms and opacity only - when the comparison ends, slide the reference out as a held frame and grow ours to full screen in one continuous move - serve the player and a full-screen page of our film alone on their own local servers, each with a clean link </compare> <honesty> - only state scores, frame rates and timings you measured, and mark anything you estimated - say what failed and show the output when something breaks - check image credit before queueing a batch, and stop to ask if it runs out - never record or scrape the live reference site, or publish anything, without my ok </honesty> <deliverables> - the site, runnable with one command - the art bible: the chosen style frame, plus every generated asset with its prompt - workbench/ with every element's rounds, scores and final verdict - the 60fps film at full resolution, plus the side-by-side player if asked for - a short note: what beats the reference, what's still below it and which builder should fix it, and the total spend </deliverables>frozen15d ago4.3K17200481.55%
higgsfield is giving back 100% of what you spend on their api, up to $100k per business so you can build an ai video product and run their models for free until the end of the month - seedance 2.5 with face references in the us - genjutsu and cinema studio both included - every api model counts toward the cashback - $20m pool, first come first served you have to earn and use it by september 30, insane opportunityfrozen28d ago3.9K16150201.07%
this is where we were a year ago btw (same prompt) https://t.co/y4H46qmkXI1d ago3.9K1400090.59%
higgsfield computer use powered by gpt-6.1 sol is f*ckin insane it opens your files and uses higgsfield itself, so it does the whole job start to finish what that means in practice: - find jobs people are posting publicly right now - read them and work out which ones actually fit - send a proposal with a free sample attached - generate the whole thing inside higgsfield - cut it, export it and send the finished file you literally just set the goal and it runs the rest all inside chatgptfrozen21d ago3.4K5111120.58%
this is how i'd make money this christmas with ai agents it's fully automated, ai agents run every account from the research to the sales. - scrape what's already working first - pick niches from what people buy - remake the top videos in your style - sell merch that ships on its own - sell a product you make once - post gift guides that pay per sale - review and improve every single week just wrote a whole guide on how you can set this up:frozen18d ago3.2K25320402.19%
hermes + grok bot + dots = a christmas business on autopilot we just entered the 2 months before christmas, and ai agents can get paid from every part of it - scrapes christmas content that's working - picks niches by what people buy - remakes the top videos with your own content - sells merch that ships on its own - sells a digital product you make once - posts gift guides that pay on every sale - runs ads on facebook and instagram just wrote a whole guide on how you can set this up:frozen18d ago2.9K18230291.77%
these are the only skill files you need to make money with ai you can use them on a new idea or your own business. the agent studies your customer first, then builds and sells from that - finds what people already pay for - profiles the exact customer buying it - proves the demand before building anything - builds the product around that customer - writes it in the customer's words - tests everything and keeps what works you can get them here for FREE: https://t.co/kuSd8z7xm1frozen14d ago2.6K22150372.46%
grok bot put a real animal's brain wiring into a 3d sim and it's swimming around on its own idk man...at what point do we start asking if these things are conscious a lab mapped every connection in a tiny marine larva, 2,675 cells and 14,066 connections. grok bot took that wiring and built it a body, eyes, cilia and an ocean in three.js nothing is steering it btw, it's just reacting to its surroundings. the fly brain got mapped in 2024 too. the more of these get mapped, the more we can literally build our own little worlds with these things living in them2d ago2.6K1611170.99%
here's the easiest way to make $10k/mo every brand needs ads constantly, so you take an ad that already works and drop their product into it you can do this manually in genjutsu, but with the api you can automate the whole process with an agent: > take one product video that already converts > run it through the higgsfield genjutsu api > swap in a client's product each time > send them a variation before you pitch > charge monthly for a new batch weekly give this prompt to your agent to get started: "here's a product video that's already converting. for every product image in this folder, run it through the higgsfield genjutsu api and swap the product in the video for that one, keeping the shots and the pacing the same. save each variation against the product name and tell me any that came back wrong."frozen9d ago2.6K14020231.49%
your agent can pay anyone right now, but it has no way to check who they are baselayer just raised $35m because that's about to be everyone's problem > verifies the business before the money moves > checks it against a trusted registry > flags shell companies and fake sites > runs through an mcp your agent can call agents spending money is where all of this is going, and none of it works without a layer like thisfrozen24d ago2.6K925040.76%
opus 5.5 > gemini 4 argon, and it’s not even close i told them both to make a commercial for apple’s new homeview (same brief) here’s where argon messed up: > no motion blur or depth of field anywhere > every scene rendered alone then glued together > its cuts flash for a single frame, five times > six critic rounds against sixty on opus argon burned its limits and ran hours longer than opus the difference is night and day, opus is still undisputedfrozen7d ago2.2K10021121.12%
they just dropped a coding model that runs on a macbook at 125 tokens/second you can literally have an agent building all day on it for free without an internet connection (fun fact, this model was built by their own ai in under 4 months)1d ago1.9K11030111.31%
ex gemini and apple researchers just launched a model that thinks visually it reasons on the image or video itself, the same way you'd look at it here are a few businesses you can build on it: > restaurants run a photo of every order before it goes out and it catches a missing side or a wrong dish > set it up for a corner shop so every morning it checks a photo of the shelves and texts the owner what’s running low > landlords send the move in/out photos and it lists exactly what changed > cleaning companies have staff take a photo of each room when they’re done and it flags anything they missed > an ecom brand gets a photo of each return and it says whether the product is actually broken or if they’re being played there are so many services you could build on top of this for diff industriesfrozen6d ago1.8K9200101.20%
slideshows are still one of the highest roi format on any platform. arcads can now make them for you - paste your app name into agent mode - mark builds the whole carousel around it - same character holding it across every slide - sized for tiktok, instagram or linkedin - run it again for a new angle every week the format barely changes and it keeps working, so all you need is volumefrozen28d ago1.7K11020111.37%
this is kind of insane, it plans, writes and produces a brand's content off what's already working for them here's how you turn that into a business: - find a brand posting content with no pattern to it - point it at their tiktok and instagram to analyse - it reads which of their posts actually worked - it writes the next concepts and scripts off that - you ship a new batch every week and repeat it runs the whole loop, so you're actually never starting from a promptfrozen21d ago1.7K422040.70%
here are 13 businesses you could start with higgsfield's computer use: - launch films for products that just got funded - redesign pitches for rundown storefronts - relisting videos for homes that won't sell - remade ads for brands with stale creative - seasonal promos when the forecast turns - walkthroughs for listings with no video - menu reels for restaurants that stopped posting - launch films for saas that shipped this week - before and afters for contractors with no portfolio - affiliate channels off trending products - event recaps sold to venues after the event - clips for gyms with nothing to post - teasers for artists dropping with no visual it finds the work and makes it and sends it back which means you get paid by the business and by the vendor you referfrozen21d ago1.6K5120131.31%
this is the first home robot i’d actually want in my house you can ask it to bring you stuff, find what you lost, and reset your whole house when it’s a mess etc., it makes sense cus the founder spent 4 years at boston dynamics working on how their robots handle objects2d ago1.4K815031.23%
in bangkok for a bit, if you’re founder here and wanna meet, dm mefrozen27d ago1.3K601000.52%
claude opus 5.5 one-shotted this iphone duo commercial it's kind of insane that every frame of this video is just code. i open-sourced the whole skill so you can make videos like this for any product repo link: https://t.co/D5XfkwubAP https://t.co/PBt0cbnpjT24d ago1.3K300090.92%
you can now turn a product into a story instead of an ad arcads writes and makes it, you pick the kind of story: - a relationship the product ends up saving - a disaster the product quietly fixes - a secret the product accidentally caused - someone's life changing right after it - a cliffhanger they keep coming back for pixar style, talking animals, claymation, whatever you wantfrozen14d ago1.3K402040.78%
this is a way bigger deal than it looks they just put out a model that takes a sketch of a physical product and gives you back the full engineering system and it's ready to run in CAD biz owners in manufacturing, furniture, product brands, still pay engineers for this. you can now basically taker their sketch, run it through, deliver the finished design and charge per productfrozen3d ago1.2K11110122.02%
this is actually super useful if you're starting a saas or any startup you can now form the company + the bank account in one go btw, stripe atlas charges you $500 just to form the LLC and you still have to go open the biz bank account, this company does both for $400frozen6d ago1.2K900091.48%
brands are sick of their ads looking ai generated here’s how you sell ad creatives as a monthly service: works for ecom brands, restaurants, gyms, salons, real estate, anything that needs photos and can’t afford shoots basically. > find a real photo that fits their product > change the background to match their market > relight it so it sits in the new scene > expand it into every ad size they run > animate the best one into a video ad > send them a fresh batch every week you basically just type what you want changed, couple examples: “put the product on the bonnet of a vintage convertible on a desert highway at dusk, keep the lighting on the product the same” “move this office shot into a brutalist lobby, swap the fluorescent lighting for flash photography, and reframe it vertically” “keep the person exactly as they are and put them on a rooftop in tokyo at night, with the light on their face matching the new scene”frozen7d ago1.2K802071.42%
there's an interesting opportunity here brands in niches like skincare, supplements, drinks etc. get talked about in hundreds of videos but usually never get tagged. so let’s say someone in the comments asks where to buy it and nobody answers, that means the brand missed a sale there. you can just set this up for them and charge a monthly fee. give this prompt to claude and it'll find brands worth reaching out to: ------------------------------ find me 50 dtc brands in [niche] worth pitching a social growth service to. start by picking 3 brands i'd obviously want as the bar, ones with real volume on tiktok and instagram, people posting about them without tagging them, and no agency running their socials. then build the list. for each brand pull their follower counts, how often people mention them without tagging, how long their comments sit unanswered, and whether an agency is visibly running their account. run a separate critic over every brand that hasn't seen your notes. it compares each one blind against the 3 bar brands and names the single biggest reason it's weaker. fix that, rerun the critic, keep going until the critic can't tell the list from the bar. drop anything with under 10k followers or an agency already on it. if you can't verify a brand is real and active, say so instead of listing it.6h ago91610110112.51%
people are doing 9 figures selling company data to ai labs right now you can sell your old github repos the same way, you just connect your account and labs pay you for a license (it's literally free money lol)4h ago889821051.80%
if you've ever felt like your agents are slow, it's because gpus are bad at generating tokens, they spend most of that time waiting on memory this company is now running a chip built only for tokens. really excited to see agents run on it2d ago879410000.57%
here's how to build a passive income stream with claude opus 5.5: this is one of the easiest ways to make money with ai right now. - prompt a whole ai video studio into existence - higgsfield's in-house models run underneath it - genjutsu, cinema studio, soul each get a tab - seedance 2.5 with face inputs handles the video - one-click templates for the formats going viral - people pay monthly, you pay per render they spent $1m+ building these models, you just rent them out.1mo ago828400051.09%
the next few years are going to be wild6d ago682200000.29%
canva just launched their own image model and they’re already beating google 😭 https://t.co/yvbe4AE7sK2h ago274201001.09%