Manuel Baltieri
@manuelbaltieri.bsky.social
Chief Researcher at Araya, Tokyo. #ALife, #AI, embodied and enactive #cognition. Information, control and applied category theory for cognitive science.
https://manuelbaltieri.com/
https://manuelbaltieri.com/
Pinned
After a multi-year collaboration with Martin Biehl, @mattecapu.bsky.social and @nathanielvirgo.bsky.social, I’m stoked to share the first of (hopefully) many outputs:
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
Reposted by Manuel Baltieri
My comment on Fillipo Torresan & @manuelbaltieri.bsky.social's "Disentangled representations for causal cognition" in Physics of Life Reviews:
www.sciencedirect.com/science/arti...
I argue that there is little meaningful analogy between learning from "pixels" vs "experience," but I praise
www.sciencedirect.com/science/arti...
I argue that there is little meaningful analogy between learning from "pixels" vs "experience," but I praise
Disanalogies between causal learning in animals vs. machines: Comment on “disentangled representations for causal cognition” by F. Torresan & M. Baltieri
None.
www.sciencedirect.com
July 11, 2025 at 6:15 AM
My comment on Fillipo Torresan & @manuelbaltieri.bsky.social's "Disentangled representations for causal cognition" in Physics of Life Reviews:
www.sciencedirect.com/science/arti...
I argue that there is little meaningful analogy between learning from "pixels" vs "experience," but I praise
www.sciencedirect.com/science/arti...
I argue that there is little meaningful analogy between learning from "pixels" vs "experience," but I praise
Shocking
So, your favorite/fancy/rich AI provider most likely cheats most of the time to score high in LLMs leaderboards.
Shocking, but totally expected, isn't it?
arxiv.org/abs/2504.20879
Where are the AGI Bros? 👌
#AI #LLM
Shocking, but totally expected, isn't it?
arxiv.org/abs/2504.20879
Where are the AGI Bros? 👌
#AI #LLM
May 2, 2025 at 11:43 AM
Shocking
Reposted by Manuel Baltieri
Igor, you legend. Don't stop being you.
There are ten more of these unreadable hypercube diagrams on the following pages....
Souce: https://arxiv.org/abs/2505.00682
There are ten more of these unreadable hypercube diagrams on the following pages....
Souce: https://arxiv.org/abs/2505.00682
May 2, 2025 at 7:37 AM
Igor, you legend. Don't stop being you.
There are ten more of these unreadable hypercube diagrams on the following pages....
Souce: https://arxiv.org/abs/2505.00682
There are ten more of these unreadable hypercube diagrams on the following pages....
Souce: https://arxiv.org/abs/2505.00682
Reposted by Manuel Baltieri
My experience applying for retractions at Elsevier.
I've looked at paper mills since 2019 and drafted a preprint on a paper mill from an international publisher in 2021. I started contacting journals or research integrity teams to raise concerns about papers. Publishers react differently. 1/n
I've looked at paper mills since 2019 and drafted a preprint on a paper mill from an international publisher in 2021. I started contacting journals or research integrity teams to raise concerns about papers. Publishers react differently. 1/n
April 25, 2025 at 1:48 PM
My experience applying for retractions at Elsevier.
I've looked at paper mills since 2019 and drafted a preprint on a paper mill from an international publisher in 2021. I started contacting journals or research integrity teams to raise concerns about papers. Publishers react differently. 1/n
I've looked at paper mills since 2019 and drafted a preprint on a paper mill from an international publisher in 2021. I started contacting journals or research integrity teams to raise concerns about papers. Publishers react differently. 1/n
Reposted by Manuel Baltieri
Great talk by @manuelbaltieri.bsky.social!
April 23, 2025 at 11:04 AM
Great talk by @manuelbaltieri.bsky.social!
Reposted by Manuel Baltieri
"We discuss the problem of running today’s software decades, centuries, or even millennia into the future" tinlizzie.org/VPRIPapers/t...
tinlizzie.org
April 10, 2025 at 9:19 PM
"We discuss the problem of running today’s software decades, centuries, or even millennia into the future" tinlizzie.org/VPRIPapers/t...
Reposted by Manuel Baltieri
Preprint time:
“AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability”
arxiv.org/abs/2504.04608
Exploring the fundamental limits that shape the design space of world modelling for agent sandboxing and interpretability
“AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability”
arxiv.org/abs/2504.04608
Exploring the fundamental limits that shape the design space of world modelling for agent sandboxing and interpretability
AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability
Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment to ensure their reliability and safety. However, accurate world m...
arxiv.org
April 8, 2025 at 3:22 PM
Preprint time:
“AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability”
arxiv.org/abs/2504.04608
Exploring the fundamental limits that shape the design space of world modelling for agent sandboxing and interpretability
“AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability”
arxiv.org/abs/2504.04608
Exploring the fundamental limits that shape the design space of world modelling for agent sandboxing and interpretability
Reposted by Manuel Baltieri
GOL in GOL in HOL: Verified circuits in Conway's game of life. ~ Magnus O. Myreen, Mario Carneiro. arxiv.org/abs/2504.00263 #ITP #HOL4
GOL in GOL in HOL: Verified Circuits in Conway's Game of Life
Conway's Game of Life (GOL) is a cellular automaton that has captured the interest of hobbyists and mathematicians alike for more than 50 years. The Game of Life is Turing complete, and people have be...
arxiv.org
April 2, 2025 at 9:00 AM
GOL in GOL in HOL: Verified circuits in Conway's game of life. ~ Magnus O. Myreen, Mario Carneiro. arxiv.org/abs/2504.00263 #ITP #HOL4
Great to see a colleague speaking up, sad to think about the state of affairs.
March 26, 2025 at 8:14 AM
Great to see a colleague speaking up, sad to think about the state of affairs.
Reposted by Manuel Baltieri
I don't want to delete anything. I simply agree with Barbieri's distinction and claim that for a successful syntactic relationship, there is no need for anticipation or computation.
On that level, the cell is a simple reliable #state machine (transducer) with no place for interpretation of meaning.
On that level, the cell is a simple reliable #state machine (transducer) with no place for interpretation of meaning.
March 23, 2025 at 1:53 AM
I don't want to delete anything. I simply agree with Barbieri's distinction and claim that for a successful syntactic relationship, there is no need for anticipation or computation.
On that level, the cell is a simple reliable #state machine (transducer) with no place for interpretation of meaning.
On that level, the cell is a simple reliable #state machine (transducer) with no place for interpretation of meaning.
Reposted by Manuel Baltieri
One of the most controversial corollaries of relational biology is the impossibility of simulating life. But what if I tell you that this claim is simply the result of misinterpreting Robert Rosen's ideas?
#complexitycat 🐈⬛👇🧵1/3
amahury.github.io/posts/trilog...
#complexitycat 🐈⬛👇🧵1/3
amahury.github.io/posts/trilog...
Relational Biology I: Is it possible to simulate life?
The first part of this trilogy is devoted to discussing the difference between model and simulation, one of the cornerstones for understanding relational biology. How true is it that Robert Rosen deni...
amahury.github.io
March 14, 2025 at 1:57 PM
One of the most controversial corollaries of relational biology is the impossibility of simulating life. But what if I tell you that this claim is simply the result of misinterpreting Robert Rosen's ideas?
#complexitycat 🐈⬛👇🧵1/3
amahury.github.io/posts/trilog...
#complexitycat 🐈⬛👇🧵1/3
amahury.github.io/posts/trilog...
Reposted by Manuel Baltieri
Re the Tononi paper: Both Tononi’s IIT (phi) and Friston’s FEP start from fundamental, axiomatic, and debatable assumptions. These assumptions are generally made without any humility. This logic allows them to make exceptionally broad claims. Which contributes to my unease about them.
March 12, 2025 at 4:01 PM
Re the Tononi paper: Both Tononi’s IIT (phi) and Friston’s FEP start from fundamental, axiomatic, and debatable assumptions. These assumptions are generally made without any humility. This logic allows them to make exceptionally broad claims. Which contributes to my unease about them.
Directed wiring diagrams for Mealy machines!
Keri D'Angelo, Sophie Libkind
Dependent Directed Wiring Diagrams for Composing Instantaneous Systems
https://arxiv.org/abs/2503.05457
Dependent Directed Wiring Diagrams for Composing Instantaneous Systems
https://arxiv.org/abs/2503.05457
March 10, 2025 at 5:31 AM
Directed wiring diagrams for Mealy machines!
Reposted by Manuel Baltieri
Only just learning about this now -- I guess for a while people have predicted that the AI doomer rationalist crowd would go violent, so its not surprising in some sense. Still though, odd times!
www.theguardian.com/global/ng-in...
www.theguardian.com/global/ng-in...
They wanted to save us from a dark AI future. Then six people were killed
How a group of Silicon Valley math prodigies, AI researchers and internet burnouts descended into an alleged violent cult
www.theguardian.com
March 8, 2025 at 7:50 AM
Only just learning about this now -- I guess for a while people have predicted that the AI doomer rationalist crowd would go violent, so its not surprising in some sense. Still though, odd times!
www.theguardian.com/global/ng-in...
www.theguardian.com/global/ng-in...
After a multi-year collaboration with Martin Biehl, @mattecapu.bsky.social and @nathanielvirgo.bsky.social, I’m stoked to share the first of (hopefully) many outputs:
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
March 5, 2025 at 2:31 AM
After a multi-year collaboration with Martin Biehl, @mattecapu.bsky.social and @nathanielvirgo.bsky.social, I’m stoked to share the first of (hopefully) many outputs:
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
“A Bayesian Interpretation of the Internal Model Principle”
arxiv.org/abs/2503.00511.
1/
This looks fantastic, and goes to the must read pile for 2025
February 25, 2025 at 11:43 PM
This looks fantastic, and goes to the must read pile for 2025
This looks really interesting!
Matthew Pugh, Jo Grundy, Corina Cirstea, Nick Harris: Learning Is a Kan Extension https://arxiv.org/abs/2502.13810 https://arxiv.org/pdf/2502.13810 https://arxiv.org/html/2502.13810
February 20, 2025 at 2:54 PM
This looks really interesting!
Reposted by Manuel Baltieri
Elon Musk is making wild claims that #DOGE has found evidence of massive Social Security fraud....
The reality is that Musk's young engineers don't seem to be able to understand COBOL databases while Musk is misrepresenting the Social Security data
www.wired.com/story/elon-m...
The reality is that Musk's young engineers don't seem to be able to understand COBOL databases while Musk is misrepresenting the Social Security data
www.wired.com/story/elon-m...
No, 150-Year-Olds Aren't Collecting Social Security Benefits
Elon Musk claims to have found rampant fraud in the Social Security Administration. There's a much simpler explanation.
www.wired.com
February 17, 2025 at 8:30 PM
Elon Musk is making wild claims that #DOGE has found evidence of massive Social Security fraud....
The reality is that Musk's young engineers don't seem to be able to understand COBOL databases while Musk is misrepresenting the Social Security data
www.wired.com/story/elon-m...
The reality is that Musk's young engineers don't seem to be able to understand COBOL databases while Musk is misrepresenting the Social Security data
www.wired.com/story/elon-m...
More on process theories arxiv.org/abs/2502.10368
Generalised Process Theories
Process theories provide a powerful framework for describing compositional structures across diverse fields, from quantum mechanics to computational linguistics. Traditionally, they have been formaliz...
arxiv.org
February 17, 2025 at 10:36 PM
More on process theories arxiv.org/abs/2502.10368
Generalising Laplacians in a categorical setup
Robert Ghrist, Miguel Lopez, Paige Randall North, Hans Riess
Categorical Diffusion of Weighted Lattices
https://arxiv.org/abs/2501.03890
Categorical Diffusion of Weighted Lattices
https://arxiv.org/abs/2501.03890
February 9, 2025 at 12:50 AM
Generalising Laplacians in a categorical setup
Too many things to read already for this year arxiv.org/abs/2404.14423
A Mereological Approach to Higher-Order Structure in Complex Systems: from Macro to Micro with Möbius
Relating microscopic interactions to macroscopic observables is a central challenge in the study of complex systems. Addressing this question requires understanding both pairwise and higher-order inte...
arxiv.org
February 8, 2025 at 11:03 AM
Too many things to read already for this year arxiv.org/abs/2404.14423
Reposted by Manuel Baltieri
Review of "Haskell in depth" by Vitaly Bragilevsky. ~ Brent Yorgey. www.cambridge.org/core/service... #Haskell #FunctionalProgramming
February 8, 2025 at 9:12 AM
Review of "Haskell in depth" by Vitaly Bragilevsky. ~ Brent Yorgey. www.cambridge.org/core/service... #Haskell #FunctionalProgramming
Reposted by Manuel Baltieri
This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235
January 29, 2025 at 4:15 PM
This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235