Empowerment Gain and Causal Model Construction: Children and adults are sensitive to controllability and variability in their causal interventions Learning about the causal structure of the world is a fundamental problem for human cognition. Causal models and especially causal learning have proved to be difficult for large pretrained models usin...

New preprint of a paper with Eunice Yiu to appear in Philosophical Transactions A, Special issue: World models, 2026. The theoretical link between empowerment in RL and Bayesian causal models with cool new data. arxiv.org/abs/2512.08230

Hello @neuromorphicboki.bsky.social.

As requested, here’s a new preprint proposing a testable framework for when artificial systems might become conscious, grounded in viability and uncertainty.

Would value your thoughts.

zenodo.org/records/1949...

Hello dreamers, I would like to crowdsource how we test for consciousness(?)

Do you know of any papers exploring these topics. Feel free to link anything, even if you think I'm aware of the paper (i.e., Bayne et al.'s paper, etc.).

#consciousness #neuroscience #sentience

What would it take for artificial systems to become conscious?

This article (now available on Google Scholar) suggests a testable pathway.

scholar.google.com/scholar?hl=e...

a man is standing in front of a crowd of people and looking at the camera with a surprised look on his face . ALT: a man is standing in front of a crowd of people and looking at the camera with a surprised look on his face .

Is ‘The Boys’ the best show currently on TV & is Homelander the best (worst?) villain?

This preprint is about this! THIS!! Mindblowing.

What if an AI could genuinely need to survive, not just optimise a goal?

New preprint proposes a testable framework for viability-grounded control in artificial systems.

Serious implications for AI welfare and alignment.

zenodo.org/records/1949...

Affective Control under Uncertainty: Constitutive Viability and Self-Model Recruitment in Artificial Systems Most AI systems pursue goals assigned to them from the outside. Change the objective, adjust the reward signal, and the system simply optimises for something else; nothing about its own functioning is at stake. This paper asks whether a different kind of architecture is possible: one where the conditions for remaining in control are built into the system itself, rather than specified from outside. Affective Control under Uncertainty (ACU) formalises what this would require: a continuous viability-monitoring signal that globally shapes how the system selects actions, and a conditional self-modelling process that activates only when uncertainty, stakes, and time pressure converge. The paper specifies the architecture, proposes a discrimination experiment, and remains deliberately neutral on consciousness. The goal is to make a genuinely architectural question more precise and testable.

I just wrote a paper on how AI might become conscious.

I’d be very interested in constructive feedback.

What are the positives? Where are the holes?

zenodo.org/records/1949...

I know this sounds like the start of a sci-fi dystopia (I do know, I do) but: I wonder whether anyone is aware of any work on trying to make an LLM feel shame? I know they can't feel. I'm using it as a shorthand for all the things that happen to a human when we feel ashamed. Intrusive memories...

osf.io/vyrnt/files/...

What does it mean for a machine to feel its own survival?

New preprint:

philpapers.org/rec/MCFACU-2

Can we build an artificial system where survival isn’t just some preprogrammed objective, but a physical necessity for the AI to function?

(PDF) Affective Control under Uncertainty: Constitutive Viability and Self-Model Recruitment in Artificial Systems PDF | Conventional artificial agents optimize externally assigned objectives, leaving unclear whether architectures can support control processes... | Find, read and cite all the research you need on ResearchGate

www.researchgate.net/publication/...

Instead of adding feelings to artificial systems, what if models build themselves around their feelings?

zenodo.org/records/1949...

What does it mean for a machine to feel its own survival?

Affective Control under Uncertainty (ACU) proposes a testable architecture for AI systems whose control is grounded in their own continued viability, not just assigned goals

Survival is the constraint, not the objective.

Is Consciousness Physical? YouTube video by Philip Goff Philosophy

Philip Goff against Physicalism

youtu.be/eV9ClkSyHDk?...

Consciousness: Philosophers & Neuroscientists Defend Physicalism YouTube video by Phil Halper (aka Skydivephil)

Phil Halper in favour of Physicalism

youtu.be/QYAdtfRFI3M?...

It’s a ‘Battle of the Phils’!

Phil Halper (AKA Skydive Phil) defends physicalism while Philip Goff goes on the attack.

YouTube links in the replies👇

A lot of AI experts imply that ordinary people will have the power to create businesses quicker & easier than before.

But in reality, is building a working iPhone app as hard as it’s ever been? You can’t vibe code it.

I'm a Materialist, but Consciousness is Foundational - Galen Strawson YouTube video by Alex O'Connor

Alex pushed a little more but Galen says it’s complicated electrochemistry and “I don’t have much more to say than that.”

youtu.be/O_duZtFwfKM?...

Galen Strawson tries to explain panpsychism to @cosmicskeptic.bsky.social.

Alex asks why some collections of conscious particles give rise to a conscious brain while others lead to unconscious chairs & tables.

GS: It takes very complicated electrochemical interactions.

So why panpsychism?

New preprint with @alexlepauvre.bsky.social, @standehaene.bsky.social and Lucia Melloni (@predictivebrainlab.bsky.social) on the temporal dynamics of conscious access:

Discrete episodes of conscious access revealed by the psychological refractory period

osf.io/preprints/ps...

In theory, the brain is a prediction computation representation information machine.

In reality, the brain is an anticipatory collective of dynamic living cells.

Do our metaphors matter for understanding brains?
Romain @romainbrette.bsky.social says yes...

braininspired.co/podcast/235/

Consciousness: Philosophers & Neuroscientists Defend Physicalism YouTube video by Phil Halper (aka Skydivephil)

www.youtube.com/watch?v=QYAd...

I've created a list for Bluesky users who were part of philosophy Twitter back in the day. Help me populate it! Also happy to add people who wish they had been part of the old community. I've added a few names already. (Ask if you'd like to be removed.) bsky.app/profile/did:...

I’m not very prestigious, but I’m certainly one of those people who wish they had been part of the old community.

Discussions of machine versus living intelligence need more clarity - Nature Machine Intelligence Sharp distinctions often drawn between machine and biological intelligences have not tracked advances in the fields of developmental biology and hybrid robotics. We call for conceptual clarity driven ...

Nic Rouleau & I: checklist to go through when settling on opinions about AI, diverse intelligence, unconventional cognition, consciousness, mind/machine issues, etc. When you read (or write) about these topics, run the perspective through this, to kick the tires. 🧪
www.nature.com/articles/s42...

New preprint with Nic Rouleau (allencenter.tufts.edu/nicolas-roul...) : what do the major theories of #consciousness say as to why it's specifically associated with brains?
osf.io/preprints/ps...
"Brains and Where Else? Mapping Theories of Consciousness to Unconventional Embodiments"
🧪