New research project: Lluminate - an evolutionary algorithm that helps LLMs break free from generating predictable, similar outputs. Combining evolutionary principles with creative thinking strategies can illuminate the space of possibilities.
https://t.co/lNdFtvjlcm
Research News! Announcing the 1st release of fundamental AI research from the Open-Endedness Team @LilaSciences: a vision-focused blog + 4 preprints. The blog details a broad research agenda for achieving open-endedness while each paper unveils its own novel research direction.
The ideas covered in the papers include:
• a novel approach to training for creativity designed to sidestep a newly-identified problem called the “creative paradox,” which means that directly reinforcing creative outputs can sometimes limit reaching full creative potential;
• an investigation of the advantages of seeing the world through fresh eyes by training an LLM that is intentionally naïve in a certain area (in effect presenting less data as a potential advantage);
• a new kind of training regularization technique for SGD called unified factored organizers (UFOs), which is designed to achieve unified factored representation (UFR) as seen in Picbreeder CPPNs;
• and finally a unique study of catastrophic forgetting that shows that networks with UFR (like those from Picbreeder) are intrinsically resistant to catastrophic forgetting. The inset video on this post is a visualization from that catastrophic forgetting work.
The blog post also includes an interactive “wheel of science” demo.
The implications of these ideas are broad and diverse, but the fun part is that each one opens up its own new research playground - there is a lot of room for further research here!
Moreover, we hope this release also highlights one other important point about AI today: while it may seem that the road ahead is already paved and all that’s left is to drive mindlessly forward, there actually remains a lot of room for new directions and insights in the pursuit of open-endedness and creativity.
This research was possible because @LilaSciences appreciates the critical role of open-ended innovation in the pursuit of scientific superintelligence. The advances you see here are part of this much larger company-wide ambition, which includes AI Science Factories and many other unprecedented components. When this engine is fueled by open-endedness, the result will be much more than a step change.
More advances in open-endedness are coming!
Blog link below 👇
@GregariousWC Thanks :) All code is emergent but is arguably combinations within llms vast space of its known concepts... It's a quality-diversity evolutionary algo with vlm scoring. I've been pretty impressed it's still exploring new spaces after a month!
New sculpture - LIFEFORM
It endlessly evolves artificial life adapted to its own glazed screen. it watches itself through a camera, so the screen becomes its living environment 📽️ 🧫
So proud of our new open-endedness team @LilaSciences! We'll be sharing work with the world soon. In the meantime, you can learn more about us in this team profile Lila just posted. Our bet is that open-
endedness is mission-critical to real scientific discovery. More👇
Introducing https://t.co/KHomcdZZDF!
Hundreds of thousands of particles self organize into a stunning variety of structures. Explore a world of possibilities with mutation and artificial selection!
This is my personal tool for exploring Fluoddity, rebuilt for the web by Opus 5
spent the evening at tiat arguing about whether an ai video can feel homemade. not good, homemade.
best line tonight: creativity starts with a vague intuition. you don’t know what you’re making until you’re partway in.
a prompt is a decision made up front. a craft is a process.
New essay: Beyond Slop
Reflections on 6 years making creative AI tools and why the field feels stuck on content production rather than personal expression.
We're building molds with dials rather than new clay.
On embracing craft, process, and open-ended mediums (with some new demos!)
https://t.co/V2ArsgV59y
MC0001 Artist Focus: @_joelsimon
Joel Simon is a resident of Stochastic Labs and the founder of @Artbreeder and @StudioMorphogen.
Bridging computer science, biology, and art, his multidisciplinary practice explores emergent systems in nature and creativity.
May 29–31, 2026
Lighthaven, Berkeley
Conference program and ticketing: https://t.co/ndTF6QYsco
also deadline to apply is the 31!
"Residencies include work space, housing (for those traveling from outside the bay area), and shop access."
https://t.co/lqfrMejSfJ
Stochastic Labs is running their summer residency again!
This year's theme is Liveness + Agency — subgroups on artificial life, realtime AI interfaces, theater + code, experimental narrative interfaces, and more.
Wonderful mix of artists / scientists / technical dreamers. Highly recommend.
Apply ↓
https://t.co/W620m4z9nT
Incredibly impressive what @asciidiego and @viccpoes have created with @krea_ai !
It was great working together back then, and it’s been exciting to see their vision and focus continue taking gen AI tools to the next level.
even though i’m super proud of the team having done a foundation model and the company having a research team
there’s no biggest achievement than helping your best friend achieve their dream!
bro, i’m so happy you made this happen!
i still remember you telling me about all your generative AI work from 2022 - and people always forget or don’t know you’ve been working on this since 2017!!!
I've been playing with @_joelsimon 's CollageNet and added an img2img mode and also Party Mode to explore random settings. Code & screenshots below in 🧵