banner
dynamicaspects.org
Roly Perera
@dynamicaspects.org
220 followers 470 following 98 posts
Making software more open, explorable and self-explanatory https://dynamicaspects.org/research Also: subjectivity, agency, active inference, niche construction, enactivism @plrg-bristol.bsky.social @iccscambridge.bsky.social @f.luid.org
dynamicaspects.org
Posts Media Videos Starter Packs
Pinned
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 21
My AGI 2025 talk on “Subjectivity Via Self-Simulation” is online at youtu.be/WtWfmBujxxU?.... I had a blast, thanks to all the organisers (esp. Hikari Sorensen, @mitibennett.bsky.social and Leonard Eberding) for pulling off a great event.
Machine Consciousness: Philosophy and Implementation
YouTube video by SingularityNET
youtu.be
1 3
dynamicaspects.org
Roly Perera @dynamicaspects.org · 2h
But evolution has already demonstrated it. It built a conscious machine without relying on any resources (other than a lot of time) that an engineer wouldn't also have access to.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · 4h
Consciousness isn't something special happening *to* us, it's something special that we can *do*, and so any account has to be functional in nature and any role for the "substrate" can only be in delivering functionality. Difficult to make progress without agreeing on the explandum first.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · 4h
The problem is that these stories are all a bit mysterian about consciousness itself, i.e. as an explanatory target it is itself mysterious and so it remains an open question whether there is some (correspondingly mysterious) role for biological "substrates" to play.
1 1
dynamicaspects.org
Roly Perera @dynamicaspects.org · 10h
Evolving a machine (meat or otherwise) is just a one way of engineering one, so conscious organisms provide an existence proof that consciousness can be engineered.
1 2
dynamicaspects.org
Roly Perera @dynamicaspects.org · 19h
“Biological realisers” are also computational mechanisms, though, so not sure I understand your premise.

And a conscious machine is “just” a machine that thinks it's conscious -- perhaps not something easy to engineer but certainly not a notion that depends on any particular substrate.
1 1
dynamicaspects.org
Roly Perera @dynamicaspects.org · 3d
Realising that “as Immanuel Kant would say” is quite triggering for me
dynamicaspects.org
Roly Perera @dynamicaspects.org · 3d
Super-excited for *two* ALIFE workshops on goal-directed behaviour tomorrow: 2025.alife.org/program#WORK... and 2025.alife.org/program#WORK...
ALife 2025 Program
Experience the full ALife 2025 Program: Special Sessions, Workshops, Tutorials, Art & Demos, an Industry Expo and more.
2025.alife.org
2
dynamicaspects.org
Roly Perera @dynamicaspects.org · 4d
The bits i managed to catch of LIVE 2025 were great - an impressive and subversive set of submissions! Looking forward to more LIVE (recorded earlier) antics next year 🌟🌟
Reposted by Roly Perera
joshuahhh.com
Josh Horowitz @joshuahhh.com · 5d
Less than 24 hours till the LIVE 2025 Q & A / Discussion session!

Watch the presentations: www.youtube.com/playlist?lis...

Join us to chat about them: links at liveprog.org

Hope to see ya there!
1 2 9
dynamicaspects.org
Roly Perera @dynamicaspects.org · 21d
Companion (Workshop) Proceedings for ‹Programming› 2025 are now available! Co-edited with @jonathoda.bsky.social and @tomasp.net. Thanks to the awesome OASIcs publishing team for getting this over the line.
drops.dagstuhl.de/entities/vol...
Companion Proceedings of the 9th International Conference on the Art, Science, and Engineering of Programming (Programming 2025)
drops.dagstuhl.de
3 7
dynamicaspects.org
Roly Perera @dynamicaspects.org · 25d
pseudonymous double-barrelled dipshit
dynamicaspects.org
Roly Perera @dynamicaspects.org · Sep 3
Excited for three Fluid presentations coming up:

Fluid: Towards Transparent, Explorable Research Outputs
rsecon25.society-rse.org

Language-Based Dependency Tracking for Explorables
liveprog.org

Authoring Tools for Transparent Climate Reporting
conf.researchr.org/home/icfp-sp...
Workshop on Live Programming (LIVE)
The 11th Workshop on Live Programming (LIVE 2025) will take place online. LIVE invites submissions of ideas for improving the immediacy, usability, and learnability of programming.
liveprog.org
1 3
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 29
A person is vastly more capable in this regard -- almost every kind of behavioural “prompt” will reveal rich, broadly consistent information about a subjective life.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 29
There's no reason at all for thinking Gemini or similar systems have a self-model. We can prompt them to generate plausible-sounding claims about being conscious, but we can also prompt them to spout gibberish, or to deny that an AI could ever be conscious.
1 1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 29
Then as far as you are concerned (you being the subject matter of the self-model), it is information about *your* first-personal vantage point — how things look to you. I think of it as the body schema enriched to a full agent-in-the-world schema.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 29
Ok, nice. It's not enough just to have access to perspectival information about appearances. You also need a self-model that takes that information about a first-personal vantage point and interprets it as yours.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 26
(And if you have the patience to sit through a 20-min video, I have a talk on this very topic here: youtu.be/WtWfmBujxxU?...)
2
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 26
6/ In fact it's other way around: the images are the content of self-interpretative acts by which the agent comes to a rich appreciation of itself *as* an agent with a perceptual vantage point.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 26
5/ These are internal subpersonal actions that serve to build up a self-narrative whose subject matter is “how the world looks”. A conscious agent thus delivers phenomenal content primarily to itself. This doesn't threaten a Rylean regress because we don't use these images to explain perception.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 26
4/ The other crucial step to flesh out the story a bit is recognising that the organism is able to (and routinely does) deliver that imagistic information *to itself* (not, say, only when pressed for a verbal report). This is an example of what @metzinger.bsky.social calls “epistemic agency”.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 26
3/ The vehicle is the organism, which can deliver all kinds of fine-grained imagistic information about appearances: for example how apparent shape transforms in response to movement. The totality of this perspectival subpersonal knowledge *is* the content of visual consciousness, on this view.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 26
2/ So the usual enactivist adage that “the world is its own representation” is tempting but too quick. Vehicle vs. content is one of the crucial ingredients need to resolve this conundrum. Then the claim is that the *content* is a dynamic egocentric image, not the vehicle.
1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 26
It takes some unpacking. We can't think of these images as living in our heads (Cartesian Materialism), given what we know about eyes and brains. But they can't live in the world either. The world is allocentric, and these images are characteristically egocentric. Let me try to summarise my take:
1 1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 25
If I'm talking *about my consciousness* (as I take myself to be doing now, for example), then that consciousness that I'm talking about has to at least have the function of generating that consciousness-talk. Something superficially resembling consciousness talk might come about in other ways.
1 1
dynamicaspects.org
Roly Perera @dynamicaspects.org · Aug 25
If it didn't have a functional role, we wouldn't be talking about it now -- there wouldn't be any mechanism for doing so.
1