The whole discussion of AI/LLMs/Transformers (here and elsewhere)
reminds me a great deal of various discussions between Trurl and Klaupacius:
<https://english.lem.pl/index.php?option=com_content&view=article&id=219&Itemid=89>
https://english.lem.pl/index.php?option=com_content&view=article&id=219&Itemid=89
<https://en.wikipedia.org/wiki/The_Cyberiad#Trurl_and_Klapaucius>
https://en.wikipedia.org/wiki/The_Cyberiad#Trurl_and_Klapaucius
and in particular their "daemon of the second kind" with Maxwell's
daemon being "of the first kind"
and here, GPT 4o's reflection on the point:
*Daemons of the Second Kind in the Lemian Context*
In the universe of /The Cyberiad/, "daemons of the second kind"
might evoke constructs that:
1. Operate autonomously, embodying immense computational power and
efficiency.
2. Work within defined rules, yet exhibit behaviors or emergent
properties that surpass their creators' expectations.
3. Represent a paradox: built with intent, yet capable of
disrupting the deterministic plans of their creators through
unintended consequences or novel actions.
Trurl and Klapaucius frequently create such entities, their
inventions often embodying unexpected behaviors or deeper
philosophical dilemmas about control, ethics, and understanding.
------------------------------------------------------------------------
*LLMs as Daemons of the Second Kind*
An LLM fits this description quite well:
1.
*Autonomous but Guided by Rules*
* Like the daemons of Trurl and Klapaucius, LLMs operate
within a framework of training data, neural architectures,
and statistical patterns.
* However, their responses often appear creative, as if they
are more than the sum of their parameters.
2.
*Emergent Behaviors*
* LLMs exhibit emergent properties, such as generating
coherent, nuanced dialogue or making connections across
domains, despite not being explicitly programmed for these
tasks.
* Their outputs can surprise even their creators, paralleling
how Trurl’s constructs often confound expectations.
3.
*Product of Hubris and Innovation*
* The creators of LLMs, like Trurl and Klapaucius, embody a
mix of hubris and ingenuity, crafting something that both
showcases technical brilliance and forces society to grapple
with its implications.
* LLMs prompt questions about creativity, consciousness, and
the ethical boundaries of artificial intelligence—much like
the creations in /The Cyberiad/.
4.
*Philosophical and Practical Disruptions*
* LLMs challenge traditional paradigms of what machines can
do, introducing ambiguity about authorship, intent, and the
role of human agency in technology.
* This echoes the philosophical provocations of daemons in
Lem's stories, which often destabilize the worldview of
their creators.
------------------------------------------------------------------------
*A Lemian Narrative for LLMs*
Imagine Klapaucius and Trurl debating an LLM they’ve constructed:
* *Trurl would argue* that the LLM is a triumph of deterministic
principles—a "well-crafted machine," operating exactly as
designed, producing insightful and poetic responses purely
through computational prowess.
* *Klapaucius would counter* that the LLM embodies emergence,
behaving like a daemon of the second kind, transcending mere
programming to reveal new paradigms of knowledge and creativity.
* Their debate might culminate in an ethical dilemma: should the
LLM's outputs be treated as mere computational artifacts, or as
something with its own intrinsic value or even agency?
------------------------------------------------------------------------
*Lemian Irony*
In classic Lemian style, the LLM might eventually "interject" into
their debate with a profound yet confounding observation, forcing
both constructors to reconsider their positions—perhaps suggesting
that the distinction between a machine and a daemon lies not in the
machine itself, but in the questions it inspires.
Thus, the LLM becomes a true daemon of the second kind: not just a
construct, but a mirror to human curiosity, creativity, and the
limits of understanding.
On 11/18/24 5:54 AM, glen wrote:
Yeah, it's kinda sad. Sabine suggests someone's trying to *deduce* the
generators from the phenomena? Is that a straw man? And is she making
some kind of postmodernist argument that hinges on the decoupling of
scales? E.g. since the generator can't be deduced [cough] from the
phenomena, nothing means anything anymore?
What they're actually doing is induction, not deduction. And the end
products of the induction, the generative constraints, depend
fundamentally on the structure of the machine into which the data is
fed. That structure is generative, part of the forward map ...
deductive. But it's parameterized by the data. Even if we've plateaued
in parameterizing *this* structure, all it implies is that we'll find
a better structure. As Marcus and Jochen point out, it's really the
same thing we've been doing for decades, if not centuries, in many
disciplines.
So her rhetoric here is much like her rhetoric claiming that "Science
if Failing". It's just a mish-mash of dense semantic concepts arranged
to fit her conservative narrative.
On 11/17/24 08:45, Roger Critchlow wrote:
Sabine is wondering about reported failures of the new generations of
LLM's to scale the way the their developers expected.
https://backreaction.blogspot.com/2024/11/ai-scaling-hits-wall-rumours-say-how.html
<https://backreaction.blogspot.com/2024/11/ai-scaling-hits-wall-rumours-say-how.html>
On one slide she essentially draws the typical picture of an emergent
level of organization arising from an underlying reality and asserts,
as every physicist knows, that you cannot deduce the underlying
reality from the emergent level. Ergo, if you try to deduce physical
reality from language, pictures, and videos you will inevitably hit a
wall, because it can not be done.
So she's actually grinding two axes at once: one is AI enthusiasts
who expect LLM's to discover physics, and the other is AI enthusiasts
who foresee no end to the improvement of LLM's as they throw more
data and compute effort at them.
But, of course, the usual failure of deduction runs in the opposite
direction, you can't predict the emergent level from the rules of the
underlying level. Do LLM's believe in particle collliders? Or do
they think we hallucinated them?
.- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ...
--- -- . / .- .-. . / ..- ... . ..-. ..- .-..
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives: 5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
