[FRIAM] absurd
steve smith
sasmyth at swcp.com
Thu May 1 16:24:12 EDT 2025
glen wrote:
> This is what I imagine y'all are doing when you chat with LLMs:
>
> Confusing ChatGPT With an Impossible Paradox
> https://youtu.be/1qbiCKrbbYc?si=V8U_mioTmlaDpynM
>
> At times, it smacks of a Monty Python skit.
>
Loved the skit... and/but it made me think about the broader
implications which made me "look in the horse's mouth" for an answer (to
mix a parable or a metaphor):
The point was to take GPT beyond trying to relate it's own "gathered
rumours" about how "a human claps hands" and consider what a (more
broadly capable) AI system might need to do to get one step closer to
actually "understanding" the clapping of hands. Many here may
discount Hawkin's 1K brains model so this may be an(other) empty gesture
but I find it a compelling model for thinking about how spatio-temporal
(esp. tactile to visual) (functional) understanding of the physical
world that brains with neocortices do. And maybe how that translates
into understanding abstract concepts (a bit more of a stretch).
that's all (y'all)!
------------------------------------------------------------------------
“What would it take for an AI to have an internal model, much like Jeff
Hawkins' 1,000 Brains and Cortical Columns, to emulate the clapping of
hands?”
00:14
ChatGPT said:
To emulate something like the clapping of hands using an internal model
inspired by Jeff Hawkins' "Thousand Brains" theory and cortical columns,
an AI would need a few key components.
First, it would require a distributed representation of the environment
and the concept of hands, allowing it to form a model of how hands move
and interact. This involves creating multiple parallel models (like
cortical columns) that each predict and update their understanding of
the hand's position, shape, and movement.
Second, the AI would need a sensorimotor integration mechanism, enabling
it to predict and adjust its model based on sensory feedback—just as
humans constantly refine their understanding of their hand's position
through touch and proprioception.
Third, it would need a timing and sequence prediction capability to
anticipate the sequence of events that constitute a hand clap: bringing
the hands together, the moment of impact, and the resulting sound and feel.
Finally, it would need a way to compare its predictions to the actual
outcome and refine its internal models accordingly, improving its
understanding and emulation of the action over time.
In essence, it would involve a complex, layered network of predictive
models working in tandem to generate and refine a coherent and dynamic
representation of the action.
You said:
“How practical would it be to create such a thing?”
00:03
ChatGPT said:
Creating such a system is theoretically possible, but it's a massive
challenge in practice. Mimicking the "Thousand Brains" approach would
require a highly advanced architecture capable of running many parallel
models, each constantly predicting and updating in real time. This would
necessitate significant computational resources, advanced algorithms for
sensorimotor integration, and a robust feedback mechanism.
While some aspects of this are already being explored in
neuroscience-inspired AI and robotics, achieving the full complexity of
human-like sensorimotor predictions and adaptability is still at the
frontier of research. Over time, as our understanding of brain-like
computation and hardware capabilities improve, building something close
to this concept could become more practical. For now, though, it's more
of a long-term goal rather than an immediate reality.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20250501/5e11ac9d/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: OpenPGP_0xD5BAF94F88AFFA63.asc
Type: application/pgp-keys
Size: 3118 bytes
Desc: OpenPGP public key
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20250501/5e11ac9d/attachment.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: OpenPGP_signature.asc
Type: application/pgp-signature
Size: 840 bytes
Desc: OpenPGP digital signature
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20250501/5e11ac9d/attachment.sig>
More information about the Friam
mailing list