Henry Daubrez 🌸💀

THE LIGHT WITHIN / Screen Test #2 More screen tests as I push deeper into development. Still figuring out direction, how scenes feel, and how the character holds in motion. Everything is evolving, including her design and overall aesthetic. The pipeline and workflow will be shaped through this phase. The script is already in a few good hands, and the early feedback has been really positive. Keep moving forward.

@bstuartTI @runwayml Thanks man! Good luck

@henrydaubrez @runwayml Thanks Henry. Your work has def been a big inspiration. Time to lock in and finish :)

3 days until the @runwayml AIF deadline. Lot's left to do. Final shots, polish, edit, sound. Energy drink weekend ahead. Huge thanks to Runway for including me in the CPP. This short wouldn’t be possible without it. NULL Coming soon.

@vr_tonio Gotcha! Sorry for the misunderstanding then! But pro AI folks are also paid to say so

@henrydaubrez I'm saying you're right. VFX influencers have flipped to Ai toolset sponsorships. Problem is they are paid to promote Ai. Very few are flipping honestly and using sustainably sourced Ai tools. x.com/i/status/20325…

For all my friends and comrades who’ve been in the AI trenches for years, getting berated, insulted, or threatened just for using a piece of technology… you’ve probably started noticing something. Some of the same people who were hating on you are now, almost overnight, turning into advocates. Here’s my honest, unsolicited take: 1/ Whatever your dream is, make a concrete and strategic plan to make it happen. 25-second random clips won’t be enough to stand out. 2/ If you don’t have a dream or a plan yet, that’s fine, but take the time to think about it. 3/ The noise is only increasing. Aim to create something truly meaningful. A piece of storytelling that is honest, raw, and personal. Give people at least one film they remember. (For me, that was Kitsune or Electric Pink.) 4/ Understand how unique this moment is. This window is short, and it will close faster than you think. The advantage of “being early” is already fading. Models are becoming commodities. Tools too. The only unique thing left is you. 5/ Force your luck. Don’t take no for an answer. Build your network. As much as we’d like it to be otherwise, it’s still a mix of what you can do and who you know. Every choice I’ve made in my career has been intentional, part of a larger plan. I’ve always preferred working on 3 highly intentional projects a year over 30 meaningless ones. It goes a long way.

@vr_tonio Don’t have time for that shit man :) I think I am pretty educated on this. Let’s agree to disagree

@henrydaubrez Deny deflect do no work. Pew research. Go find it. It's trending

@vr_tonio What is the sample, what age, coming from where, what was the question, in which context Polls man :)

If you go by actual statistical polling.. even ICE immigration raids poll better then AI. Sandra Bullock and Reese Witherspoon are managed by CAA. All A-list members get talking points prior to awards season. VFX Software influencer are being made to pivot due to SaaS-pocolypse

@JoeDotAverage I start to see a lot of anti AI CGI artists finally discovering it could help them

@henrydaubrez Great advice! I haven't personally seen the critic turn to advocate thing yet, but it's probably because your network is at the bleeding edge.

@billywoodward Definitely, especially now

@henrydaubrez Great advice and I think number 4 is really key..."The only unique thing left is you" 👏

@billywoodward I think issue is that when you do it too many times it degrades your output

Extend video in Seedance is outrageously good ⚡️ Paired with consistent prompting and a project bible, you can direct scenes quickly Export short clips → alternative coverage → screenshot to lock performances

@KNGMKRlabs @FlowbyGoogle I think the issue is that those are two different teams working on different projects with no direct causality. Tagging @ummerrr just in case but.

The silence is deafening. I have been looking hard to find one actual slop farm they took down. But it increasingly just appears to be some of the most thoughtful and unique storytellers in the medium. I hope the team at @FlowbyGoogle understands how demoralizing this is for people trying to actually make quality work with their tools. Not engagement farms. Not fake ads. Films. And it’s happening to some of the most talented artists trying to actually make meaning with these tools. We’re making a list if you ever care to see it.

@juliewdesign_ 🤘

@henrydaubrez yesss, can't thank you enough! onto many more meetings ✨🤞🏼

Congrats Julie! It was fun to see the process and to finally meet you in person!

@scottbelsky “How come nobody talks about”

@SoribeStella No, it’s still ongoing :)

@henrydaubrez My goodness! So you made it hyper realistic? Oh noooo

THE LIGHT WITHIN / Screen Test #3 Leaving no stone unturned right now, experimenting with very different aesthetics and pairing them with different workflows. Reworking the same scene over and over. Some approaches are more cost-effective, some more visually interesting, and some sit somewhere in between. Given how challenging it is to maintain perfect consistency in animation, I’ve started exploring alternative approaches.

@Flvmingo The story and the public

@henrydaubrez what made you defer from the original claymation style idea for this?

@mark_k @OpenAI YES, thank you

Because some of you asked, I've put together a collection of images showing the image quality issues with GPT-Image-2. The artefacts appear as a distinct noise pattern, a grid of specks or dots. Hoping this is just a bug and gets fixed soon by @OpenAI. GPT Images 2 artefacts:

@infiniteyay @blac_ai Saaaaame. Good to see you guys

@blac_ai Grok's like: alright someone's finally onto the BS the teams at X have been up to, send it! 🚀 miss ya! hope to see more of you on my timeline!

I sent an AI agent swarm to read the X algo source code. What they found shocks and confuses me. First, I want to be clear about why I'm posting this. Four years on this platform. 60,000+ followers. I've shown up every day since I started. And over the last three months, I've watched my reach drop 40%+, off a cliff, and I haven't changed ANYTHING; I am extremely consistent, disciplined, and focused on what I do and how I do it. What bothers me in addition to my own numbers is that Artists I used to see constantly, I never see anymore. People that I look forward to seeing what they're creating... one day they disappear from my feed. I assume they left. Nope, still here. Still posting. Multiple times a day. Just completely invisible to me now. And presumably me to them. This is happening to a lot of us. I've tried to figure out why and how to fix it. Post more. Post less. Different times. Everything has hurt my account. I'm frustrated, tired, and tbh, straight up losing interest. So... I had my AI agent, Mai, spin up a research swarm last night; a multitude of specialized sub-agents pointed at every line of X's open-source algorithm. Every file. Every filter. Every module they've made public. Literally. I wanted to know exactly how to see this from the perspective of a creative here, from an artist, and not from a content consumer which is what literally every other post about the algo is focused on. What follows is what they found. ///// ⭕️ TLDR; 5 things we all should be aware of: 1. Our follower count does nothing for our reach anymore. 2. The algorithm decides how many people see our posts based on a PREDICTION, before anyone has seen it. 3. Posting too much hurts us. Posting too little also hurts us. (Really) 4. Every time we repost another artist's work, the algorithm buries it. 5. Our posts are gone from the system after 48 hours. Nothing from 3 days ago is being shown to anyone. You start from zero every 48 hours. ///// ⏬ Going deeper on those 5... 1. Your Follower Count is just a Display Number Buried in the codebase: "author_followers_count" is pulled through a service called "Gizmoduck" and passed to the tweet entity service for display only. Not fed into any scorer. Anywhere in the system. 100,000 followers. 1000 followers. Same starting point in "Phoenix", the new system. Years building an audience on this platform? That audience, as a signal to the algorithm, is worth nothing now apparently. What travels with your posts is PREDICTED engagement, a score based on your content and historical signals, regardless of how many people chose to follow you. _ 2. "The Prediction Trap" This is the one that actually broke my brain. Before your post reaches anyone, "Phoenix" scores it across 19 "prediction heads"; 19 different things it's trying to predict about how people will behave. Let me repeat. ❗️THE ALGO IS PREDICTING HOW MUCH ENGAGEMENT YOU WILL GET, AND ASSIGNS REACH BASED ON IT.❗️ WHICH IS A SELF-FULFILLING PROPHECY! Some of the 19 metrics: favorite_score — will someone like this reply_score — will someone reply dwell_score — will someone pause on it (binary) dwell_time — how long will they pause (continuous, two separate signals) photo_expand_score — will someone expand the image not_interested / report — negative signals The prediction determines reach... It actually decides if the post will get reach, by predicting... reach? how does this make any sense. It's not determined by merit of the post. It's determined by wether or not the algo thinks it will get reach, thus giving it reach. Phoenix PREDICTS low engagement. Shows the post to fewer people. Fewer people means fewer chances for engagement. Prediction validates itself. Post gets suppressed. + Phoenix PREDICTS high engagement. Bigger distribution. More chances. Prediction validates itself. Post gets pushed further. The prediction drives distribution. Content quality is secondary. And the prediction is built on your account's recent historical signals. If your reach has been declining, Phoenix is PREDICTING it will keep declining, AND actively making that happen by restricting your distribution. ie; A great piece posted on an account with declining engagement gets a small test group, underperforms in that group, gets confirmed as low-value. Even if it's the best thing they've ever made. The algorithm creates the outcome it predicted. And for anyone who's been in a decline, getting out requires overcoming a system that's actively betting against you. _ 3. "The Volume Trap" "AuthorDiversityScorer" applies exponential decay every time you appear in the same follower's feed session. Each additional post from you in a single session scores lower than the last. - Post at 9am, noon, 7pm. - A follower opens X at noon. - They see your midday post. - Your 9am post, still alive, is now decayed because you already appeared in their session. - Your 7pm post decays further. ❗️The more you post, the less each post reaches. So you post less... Impressions drop anyway, because low activity reads as a dormant account. The "per-author" caps governing this are redacted from the public code. Post too much = decay. Post too little = dormancy. The band where things work is narrow, undisclosed, and different for every account. This is absolutely absurd. And impossible for people to navigate. _ 4. The New Repost Penalty April 12, 2026. X announced a crackdown on aggregators. Reposts of other people's work: up to 90% impression deduction. On that specific repost. To be clear: NOT on your account. On each individual original post. Lots of mis-info out about this. Every time you share another artist's work because you believed in it, because community means showing up for each other... The algorithm buried it. 90% visibility cut. Gone. BUT Self-reposting your own work is different. X uses a "Bloom filter" that resets at the end of each session. "RetweetDeduplicationFilter" only drops self-reposts for followers who already saw the original in that same session. A follower opening the app at midnight hasn't seen your morning post in their current session. It reaches them fresh. The rule: sharing someone else's work = buried. Sharing your own = viable. _ 5. 48 Hours and... It's GONE. "Thunder" is X's in-memory post store. It auto-trims every 2 minutes. Retention window: 48 hours. After 48 hours your post is gone from the candidate pool. The algorithm can't serve it to anyone. The idea that consistent posting lets your older content keep circulating is wrong at the architecture level. You're starting from zero every two days. Thunder also maintains per-author caps on how many of your posts can be in the candidate pool at once. Those values are redacted. ///// 🫠 How our habits are hurting us: For years the advice was: show up every day, post on a schedule, build the habit. The accounts that did that built audiences. That consistency was proof of commitment. The "AuthorDiversityScorer" punishes it. The daily schedule that built your following now means your posts are competing with each other instead of adding value. The disciplined consistency the old platform rewarded is now what triggers exponential decay under the new one. Let that sink in❗️ The platform changed the rules. The habits we built under the old rules are working against us under the new ones. And no one said anything about it. /// 📤 A Note about/to Nikita & the X Team: Nikita Bier and the algo team at X are building for consumers. The changes make sense from that angle: algorithmic feeds, crackdowns on low-quality reposts, pushing formats that generate comments and replies. If your goal is to show the people scrolling a better experience, this logic tracks. That might even be the right goal. I could argue that with a certain perspective. However... there's a side of the equation they're seemingly not accounting for: the creators who supply the content that makes the platform worth scrolling in the first place. For artists specifically, this has been a demolition job. The art was always supposed to be the value. That's what we spent years building. That's what the audiences came for. The current algorithm doesn't reward that natively anymore. It rewards high comment probability. The result is people like me spinning up AI agent swarms to read source code just to understand why our reach is gone. Creators running diagnostics on a platform they used to just create on... is ridiculous. I don't think this is the intent. But it's the outcome regardless. You can optimize the consumption experience all you want. If the people making things stop showing up because the game is too rigged, there's nothing left to consume. The creator side of the algorithm needs a voice in these decisions. Right now it doesn't have one. //// I sent agents to read the code because I was tired of not knowing the rules. Tired of watching reach disappear. Tired of looking for accounts I used to see every day and finding out they're still there, still creating, just invisible. Understanding all this doesn't fix anything, ironically. But at least now I know what I'm working with. They built the algo well. Just not for us. It's built for the masses, engagement farming, rage baiting, fear baiting, and overall 2026 end-of-days pvp slop and brain rotted doom scrollers. I don't know what else to tell you, or how to operate with any of this, and trust me, I get how insane and confusing a lot of this is. It numbing. Tiring.. and just.. Idk. Regardless, I hope this helps in whatever way it can. -BLAC _ Attached: 1 - screenshot of my death spiral analytics 2 - Summary report on agent swarm findings 3 - the prediction trap, visualized 4 - snippets from the public X algo repo with notes

@KNGMKRlabs Alright so. I don't know EXACTLY but I think I read someone saying it might be the scraper is doing this because it's seeing standard voices from Eleven Labs which might trigger the "oh it's mass produced AI stuff" Maybe you don't but look into that already

YouTube demonetized my channel today for “inauthentic content — mass-produced or repetitive.” A policy written for content farms, applied to work I’ve spent years making. If you've seen any of the 30 or so videos on my page, it's pretty clear they are not "mass-produced." Films. Scored, storyboarded, edited, argued over. I don’t think I was singled out. I think a classifier saw “AI” and stopped reading. That’s going to keep happening to filmmakers like me until platforms learn the difference between a person using new tools and a farm using no tools at all. Right now they can’t tell, and the cost of that falls on the people actually trying to make something. Appeal filed. Work continues. That part isn’t up to YouTube.

@Uncanny_Harry Looking good!

I wanted to make something heartfelt and hopeful. Made this with just one Midjourney image (see in replies) and everything else was done inside Seedance, (apart from the Suno music track). Really pleased that model was able to maintain the animation style and give such solid character performances. Seedance is not the cheapest model but bang for buck it's produces the best quality results. The 1080p is virtually Broadcast quality IMHO. Seedance 2.0 is now available via @BytePlusGlobal API