Fernando Rosas 🦋
@_fernando_rosas
Followers
5K
Following
13K
Media
174
Statuses
7K
All posts on the blue sky | Emergence, synergy, brains, AI safety, and mental health
London, England
Joined October 2017
Preprint time: “Software in the natural world: A computational approach to emergence in complex multi-level systems” https://t.co/iKMJ4mpSG0 A rigorous framework that not only identifies *when* emergence takes place, but explains *how* this happens computationally
arxiv.org
Understanding the functional architecture of complex systems is crucial to illuminate their inner workings and enable effective methods for their prediction and control. Recent advances have...
20
89
368
A series of recordings from the second rendition of the best conference on theoretical AI alignment (ILIAD) just dropped! https://t.co/3I54qR4Bbe
youtube.com
0
2
7
Are systems capable of “real feelings” somehow selected by natural evolution (i.e., does this has behavioural consequences?) Or did it arise as a side effect / spandrel?
3
0
5
It makes sense that evolution selected neural circuits that make us to “want” certain things, as that ensures robust proactive behaviour… But why that wanting has to be experienced at all, instead of acting simply as unconscious compulsion? (a “little hard problem”)
11
2
14
Nice short reading: "What Is Geometry?" 1) Axioms (Euclid) 2) Coordinates (Descartes, Fermat) 3) Calculus (Newton, Leibniz) 4) Groups (Klein, Lie) 5) Manifolds (Riemann) 6) Fiber bundles (E. Cartan, Whitney) "A property is geometric, if it does not deal directly with numbers"
17
157
985
Thrilled to share our latest preprint with @D_Sekizawa and @ito_sosuke! https://t.co/wHJGzVU52l We merge Koopman operator analysis with stochastic thermodynamics to uncover the oscillatory origins of thermodynamic dissipation in nonlinear systems. This framework pinpoints
arxiv.org
Nonlinear oscillations are commonly observed in complex systems far from equilibrium, such as living organisms. These oscillations are essential for sustaining vital processes, like neuronal...
How do nonlinear oscillations generate thermodynamic dissipation? Our new arXiv preprint with @ito_sosuke and @oizumim introduces a Koopman-based framework that breaks down dissipation in nonlinear dynamics into contributions from oscillatory modes. https://t.co/XVBWFXMF6Z
0
15
50
BIG ANNOUNCEMENT📣: I haven’t been this excited to be part of something new in 15 years… Thrilled to reveal the passion project I’ve been working on for the past year and a half!🙀🥳 It started from my frustration with the depressing effect that the current publishing system has
108
486
2K
About to start, join online if interested! ✨
This is tomorrow, 3pm JST. https://t.co/myw9BtxPzo
0
0
2
I was so excited when I saw that Neural Cellular Automata had been applied to the @arcprize - do you remember the famous self-repairing Gecko from @zzznah in 2020? I think ALIFE methods are an exciting path forward in AI research! This is @stenichele and Etienne Guichard at
5
12
87
In this SFI Seminar, Scott Aaronson (University of Texas at Austin) explores the limits of mathematical knowability — from Gödel’s Incompleteness Theorem and Turing’s uncomputability to the astonishing growth of the Busy Beaver function and the future possibilities of quantum
2
21
117
For PhD/Postdoc/Prof theoretician (math/physics/CS) 6-week AI alignment mentored program in London (remote option) $6-15k stipend, Jan 5-Feb 13, 2026. develop a research proposal, & get help securing 6-24mo follow-on funding. Deadline Nov 2, rolling so apply soon! Link in Thread
1
1
5
If you love theory and want to make a difference for AI alignment, please apply to this and join us! https://t.co/Qz8GTAOdnb (Please RT and share around!)
0
5
16
Recently, we had a pleasure of hosting Max Hodak @maxhodak_ at our CC Tokyo. I’m truly impressed by his deep insights into consciousness. Everyone interested in consciousness must watch his talk. Towards Consciousness Engineering
1
20
60
If you think animal brains are more interesting than LLMs, and that current approaches to AI are missing something, please come and work with me and the team at Sakana AI 🧠✨
We are excited to share that “Continuous Thought Machines” has been accepted as a Spotlight at #NeurIPS2025! 🧠✨ The CTM is an AI that mimics biological brains by using neural dynamics & synchronization to think over time. It can solve complex mazes by building internal maps,
16
18
293
Poll time, just out of curiosity. ( This is in the context of our symposium, new talks and content updated every week: https://t.co/O6sQzMF4Jc . . ) How many of the professional mathematicians and physicists here think that the properties of mathematical objects are
thoughtforms.life
Host page for the first Symposium on the Platonic Space
28
22
126
Calling all mathematicians, physicists, computer scientists, statisticians, learning theorists, engineers, neuroscientists, developmental biologists, etc.... If you want to solve deep scientific problems in AI safety, apply to our MATS stream 1/3
1/ AI is accelerating. But can we ensure that AIs truly share our values and follow our goals? We argue that aligning advanced AI systems requires cracking a core scientific challenge: how data shapes AI's internal structure, and how that structure determines behavior.
2
26
236
On Wednesday this week, I’ll be giving a talk on the mathematics of qualia at the Models of Consciousness at Hokkaido University. I’m preparing for it now, and I feel most blissful when I’m immersed in thinking about qualia. https://t.co/5m8sPVN5WU
1
5
15
Super excited to be visiting Japan during the next weeks! ✨
We will have Fernando Rosas @_fernando_rosas at CHAIN seminar in 14 October. Online registration is available as well → https://t.co/45lCZLPIhF
2
1
15