🎬 Film concept artist and illustrator. 🎞️ Alien: Earth, Matrix, Marvel, DC, Transformers, Woman King, Jupiter Ascending, 1923, Hunger Games.
Michigan, US
Joined January 2009
- Tweets32.8K
- Following2.6K
- Followers19.8K
- Likes42.8K
Pinned Tweet
I figured I'd post a little bit of my Matrix Resurrections work here.
These were done under the production design of Hugh Bateup and Peter Walpole, and the direction of Lana Wachowski.
These are some designs from IO, including Niobe's keep and the Morpheus shrine.
Hope you enjoy!
Reid Southen retweeted
If you want to know why animators are up in arms when someone respected says they “did it the old way” but then it has all the hallmarks of generative AI funkiness, ask them how work has been the last 18 months.
If you’re lucky to find work right now, guess what a lot of it is - cleaning up those AI errors to make it look like it wasn’t used in the first place.
There’s a lot of discussion to be had on where the line is between tools that assist versus tools that generate, but purposely obfuscating what was used and then doubling down on it all isn’t going to move the conversation forward.
Reid Southen retweeted
BREAKING: Wisconsin sues Kalshi, Polymarket, Robinhood, Coinbase on the same day for running illegal sports betting
"This was made 100% with local models."
And in the same tweet:
"Opus 5.5 came up with the story, wrote the narration, generated every shot on the Spark, rejected the bad takes, mixed the sound and cut it together."
This was made 100% with local models. Every frame and every sound in this cartoon came from AI models running on an NVIDIA DGX Spark on my desk. No cloud generation, no subscriptions.
"Santa and the Little Lost Star"
All I typed was "make a Christmas short under a minute" (plus "Santa" and "1930s cartoon style"). I didn't write the story, plan the shots or edit it. Opus 5.5 came up with the story, wrote the narration, generated every shot on the Spark, rejected the bad takes, mixed the sound and cut it together.
It took about 4 and a half hours today. The first full cut was done in an hour. The rest was agent directed polishing: 28 video renders, about 3 hours of GPU time, for 22 seconds of finished film.
It was all made in Imagination Studio, a free, open-source local film studio built by @SamJWasserman. This thing is ridiculous. One installer downloads every model you need, and an AI agent can drive the whole thing.
What made what (all running locally):
Video: MiniMax H3 (FastH3) with the Studio 1939 LoRA by @OdinLovis for the golden-age hand-painted look
Title card: MOSS-Image
End card: FLUX3-K
Keyframe fixes: Qwen-Image 2.1
Narrator and Santa's voice: Fish Audio Drama 3
Score: MiniMax Music 3
The "Merry Christmas everyone" song: YuE2 Sound effects: Stable Audio Open
github.com/drowzeys/Imaginat…
Reid Southen retweeted
Today I paid a human being to voice a character in an indie game
That's it. That's the post
I can't afford baked goods, so I pay a subscription service to rob bakeries around me to get things a lot cheaper. I can't believe how much bakers are whining about this, they should adapt, this is progress. The entitlement is off the charts.
"I need my artists to work for sub-minimum wage, I need them to ask themselves if it would be better to work in fast food or at a car wash every time they deliver me a commission. Can't have them getting too cocky, I deserve nearly free labor."
My house burned down when I was a kid and when I ended up in the ER at 8am, a chipper nurse walks past and goes, "Smells like somebody had a bonfire!"
What does this remind me of...
Oh! The narcissist's prayer:
"That didn't happen.
And if it did, it wasn't that bad.
And if it was, that's not a big deal.
And if it is, that's not my fault.
And if it was, I didn't mean it.
And if I did, you deserved it."
the biggest lie I see here is that AI is replacing talented artists' jobs.
it's not.
if it is, you're not good.
skill-wise or for utility.
we have one of the BEST distribution tools ever made, and anyone who can leverage it to drive business is invaluable.
the development of AI is a net positive for anybody doing creative work.
we're witnessing one of the biggest increases in creative production capacity EVER.
there's more money involved today because it's increasingly valuable knowing what you should create and why.
just look at the number of creative roles paying > $100,000. this wasn't the case 4 years ago.
artists can focus on creative and cool things instead of time consuming technical problems.
if you’re an artist struggling to find work while taking an anti-AI stance, drop your ego. companies hire you for the value you deliver, not the tools you use.
you were never hired solely by your ability to use after effects or photoshop.
but rather for your artistic talent, which doesn't lie solely in tools.
SO BE CREATIVE, AND MAKE YOURSELF VALUABLE!!!
Reid Southen retweeted
The amount of non-artists upset by this is unreal. The arts community has taken a massive hit from AI.
My husband had a 20 year career in animation for Disney/Nickelodeon and just like that, poof.
This is a bid to make sure human artists don't give up and disappear.
So just remember this when your 'real job' businesses turn to ChatGPT for a new logo, or ad, or sign... instead of hiring a graphic designer/creative to save money.
If you didn't already think the CEO of Anthropic was an evil lunatic, here you go.
Readers added context they thought people might want to know
The excerpt is from Dario Amodei's 2010 GiveWell guest post as a Princeton physics grad student; he donated the $10k to VillageReach (child vaccines) and described the critical analysis as emotionally taxing.
blog.givewell.org/2010/06/03/my-…
nytimes.com/2026/11/05/tec…
Tesla to axe Cybertruck as Musk shifts focus to robotics and AI ft.trib.al/9UnuyMh
They hung a "fuck AI" banner 🔥
Protesters break into Microsoft data center site in Amsterdam. Around 100 people made it into the construction site, with some scaling a crane to place a “fuck AI” banner. Details 👇 theverge.com/news/1028549/pr…
Reid Southen retweeted
"But can't AI just be used to complete unimportant backgrounds or clean up animation?" No. Those are entry level positions that turn into long careers. Bg painters become art directors. Clean up artists become animation leads. Stop trying to cheat.
Lol, Halo guns and X-wings, please sell this, I dare you.
I quit my 11-year corporate career to make games with AI. I built the world’s first AAA-quality sci-fi FPS game with AI in 24h. On my laptop. While traveling.
A giant company in the game industry contacted me after my last AI game went viral with 3M+ Views. They want to feature a game i make with AI in their million-dollar booth at Gamescom and help me release it worldwide across platforms.
So here I present my own original IP: SOL: The Last Imperium.
→ Fast first-person combat with epic guns, grenades, and melee
→ Drive, fly, and fight across massive battlefields
→ Giant boss battles against walkers, titans, and a Leviathan
Graphics, gameplay, concept art, music, sound effects and animation. All made with AI, entirely vibe coded. Built on Three.js.
This would not have been possible without @tripoai. I create world class 3D models of characters, vehicles and monuments in Tripo, then let Opus 5.5 jam with Blender to bring AAA-quality to the 3D models. Absolute game changer.
Now it feels like I have an entire $100M game studio on my laptop.
The future is here. Go after your dreams and start creating, now is the time!
Dropping some AI game dev sauce in the comments!
Readers added context they thought people might want to know
The "world’s first AAA-quality sci-fi FPS game with AI in 24h" refers to a rapid AI-assisted browser prototype on Three.js via tools like Tesana, not actual AAA production. No evidence supports the giant company/Gamescom claims.
docs.tesana.ai
pcgamer.com/software/ai/th…
innovecsgames.com/blog/what-are-…
eurogamer.net/heres-the-worl…
Reid Southen retweeted
Friendly reminder that if there is no such thing as a faithful AI upscale. AI will hallucinate details that do not reflect reality and it will put your integrity at risk to present an AI image as reality
Hello my name is Olivia Reingold and I used ChatGPT to brighten and sharpen an image of a woman in Valentino shoes and a Chanel bag.
After processing, it still shows these same things: a woman wearing Valentino shoes and a Chanel bag.
She is a real (and chic!) woman, really wearing those items. The observation holds.
Here’s the photo I took:
