https://xitter.gq/t.co/qg9KTMCQDU
California, USA
Joined May 2026
- Tweets31
- Following97
- Followers65
- Likes1K
Jesse retweeted
This is an interesting milestone, showing RL can actively control self-organizing patterns like Lenia to achieve goals.
Together with NCA+IMGEP (@hamongautier et al) & perceptual occlution (@jessescool_ et al) providing passive controls, we now have a variety of control methods.
Jesse retweeted
🧵 New paper: RL for discovering and controlling self-organizing phenomena.
We introduce CARL, a closed-loop agent that learns to create self-organizing patterns in Lenia, steer their behavior, and let humans guide them in real time.
Project website + interactive demos below ↓
Jesse retweeted
Here it is - the official, revised, peer-reviewed version of my Platonic Space paper. mdpi.com/2409-9287/11/5/161 Of all the many unpopular positions I’ve taken over the decades - bitter controversies around the origin of left-right asymmetry in embryogenesis, bioelectricity and genetics, diverse intelligence, etc., this one has by far generated the most pushback: serious (grateful for those!) and energetic attempts to move me to other views, pleas to just drop it and not talk about it (for several different reasons), nasty emails and accusations, impacts on reviews of papers that have nothing to do with this, etc. Kind of amazing to me how incendiary this is. What can I say... Our job is to call it as we see it, and right now for me, this is it. Apologies to collaborators and colleagues for any shrapnel! Time will tell if this pans out or not; I've placed my bets. And btw, if you think this stuff is weird and uncomfortable, just wait… There’s much more on the way. The knob turns slowly but as long as the data keep coming, I'm going to say what I think it all means and follow it to the next steps it enables. Buckle up!
Jesse retweeted
humans do not understand math by reasoning forward through a sequence of intermediate lemmas and theorems with an error rate. we do it by shaping our insides into a sensor for peering directly into the platonic realm. the theorems and lemmas and stuff are a writing convention
Jesse retweeted
Last week @ALifeConf happened and James did an amazing job presenting our paper! 🎉
How do you know what an NCA has actually learnt? Observation only gets you so far, so we visualise the attractor landscape instead. 🧵
direct.mit.edu/isal/proceedi…
Jesse retweeted
Intriguing paper on the physiology of Lenia patterns by @jessescool_ @drmichaellevin et al, especailly love this figure 4. The chaotic zone in the head of K4s is very surprising, I mean how on earth can such a neat "control box" exist?
What are the preferences of novel in silico and in vivo agents that aren't directly engineered toward a specific set of behaviors? Here is an example, from the world of Lenia (en.wikipedia.org/wiki/Lenia) - our new #preprint on agnosiophobia (avoidance of the unknown): arxiv.org/abs/2605.30708
@jessescool_
Jesse retweeted
New ALife late-breaking abstract with @drmichaellevin!
We find that lifelike beings with species-specific reactions to perturbations emerge from Gifbreeder despite the absence of explicit agents, environments, or local interactions.
I welcome any feedback on these early ideas.
Jesse retweeted
The exceptional @drmichaellevin is all over the place today! I listened to him on @BBCRadio4 #Sideways this morning (bbc.co.uk/sounds/play/m002zg…) & then here he is in this rich portrait in @NYMag by @lizweil nymag.com/intelligencer/arti…
Jesse retweeted
Check this out: @jessescool_ made this:
A minimal Umwelt in Lenia
jessescool.github.io/lenia-u…
fun!
(more story: xitter.gq/drmichaellevin/status/…)
What are the preferences of novel in silico and in vivo agents that aren't directly engineered toward a specific set of behaviors? Here is an example, from the world of Lenia (en.wikipedia.org/wiki/Lenia) - our new #preprint on agnosiophobia (avoidance of the unknown): arxiv.org/abs/2605.30708
@jessescool_
Jesse retweeted
FRACTALS IN NEURAL NETWORKS
Hyperparameter tuning feels like navigating a coastline. Turns out that's literally true: the boundary between learning rates that train and ones that diverge is a fractal.
Why? Gradient descent is an iterated map, θ → θ − η∇L(θ), exactly like z → z² + c, the law that draws the Mandelbrot set. Iterate a nonlinear function, ask "does it stay bounded?", and you get a fractal.
So I made it interactive: drag to zoom, and each dive recomputes 65,536 full training runs on the GPU in ~1s. New inlets and peninsulas surface at every depth. The coast never resolves.
Same story with real data (MNIST-1D), the fractal survives. The best learning rates live right up against this shore. That's part of why tuning is so hard.
The fun part: I built this like a story pairing with Claude Code inside the running notebook via marimo-pair. It ran code in the same GPU kernel I did, read live state, and edited cells while the fractal recomputed in front of us.
Molab link below 👇
An interactive, story-driven notebook — built with @marimo_io + JAX + marimo-pair + Claude Code in molab. All credit to Jascha Sohl-Dickstein's paper "The boundary of neural network trainability is fractal"
#MachineLearning #JAX #DeepLearning #builtWithMarimo
Jesse retweeted
"Intelligence from Learnable Novelty "
This paper suggests that intelligence is not surprise itself, but the ability to turn surprise into understanding.
Since novelty search gets trapped by noise, and surprise minimization gets trapped by stasis, it splits surprise into learnable and unlearnable parts, then optimizes only the learnable part.
With a cheap differentiable estimator, it finds rule 110, grows solitons, clusters MNIST without labels, and improves RL exploration.
Jesse retweeted
You can get LLMs to write good non-AI-slop-sounding technical documentation by requiring them to adhere to ADS-STE100 Simplified Technical English
Jesse retweeted
A hopefully significantly clearer, better version of my initial Platonic Space paper (a much modified version of the original 2025 preprint) is here:
osf.io/preprints/psyarxiv/5g…
"Ingressing Minds: Causal Patterns Beyond Genetics and Environment in Natural, Synthetic, and Hybrid Embodiments"
More new papers on this topic coming, but I wanted to update the kickoff manifesto now that we're a year in since I first wrote it. It's submitted to a journal now so there will be a peer-reviewed version available eventually, but the updated preprint is already up.
Jesse retweeted
Can biology teach us new ways to compute? 🧠
Decoding the bioelectric 'software' that builds biological bodies, @drmichaellevin 's work on developmental #intelligence and synthetic organisms challenges the boundaries of #cognition and #selforganization!
#GSO2026 #BioComputing
Jesse retweeted
every city name in California has three ways to pronounce it:
(1) the Spanish way
(2) the way an English speaker would pronounce it if they hadn't heard the name before
(3) the way locals actually pronounce it, which is neither of the previous two. like San Rafell and Beneesha
Jesse retweeted
In this SFI Seminar, Eric Goles of the University of Adolfo Ibáñez explores fungal automata, a cellular automaton model in which information flows only horizontally or vertically. He shows that despite these directional constraints, fungal sandpile automata can simulate arbitrary Boolean circuits and are computationally universal.
Watch Goles’s SFI seminar: youtube.com/watch?v=N_HmfSz8…
Jesse retweeted
We are truly standing on the shoulders of Giants today!
@drmichaellevin together with @MillerLabMIT
"Physicalism has been dead since the time of Pythagoras, and probably long before that."
"The basement of all this, I don't think, is math. I think this is behavioral science. I think math is a behavioural science of a certain kind of pattern."
"It's a bioelectric code, because the network instructs the patterns of gene expression and cell behaviour and morphogenesis. If you want the system to make an eye on a tadpole's tail, or a flatworm that has two heads… you have a chance to do that."
Scientists working at the bleeding edge of bioelectricity at very different scales. They agree stuff, they disagree on stuff. Watch now ⬇️