<div dir="ltr"><div dir="ltr"><br></div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Wed, Feb 26, 2025 at 2:05 AM Stuart LaForge via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org">extropy-chat@lists.extropy.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">On 2025-02-24 21:54, Jason Resch via extropy-chat wrote:<br>[snip]<br>
> I agree with this paper in that the notion of causality in the brain<br>
> cannot be explained entirely reductively, rather there are many<br>
> independently operating levels of causality simultaneously working<br>
> within our skulls.<br>
> <br>
> This idea is summed up by Roger Sperry's "Who pushes whom around<br>
> inside the cranium?" Is it the atoms and molecules that tell neutrons<br>
> and thought patterns what to do, or is it the thought patterns and<br>
> neurons that tell molecules and atoms what to do?<br>
> <br>
> It's also captured by Hofstadter's notion of a strange loop, or a<br>
> tangled hierarchy. Where causes bubble up from lower layers and then<br>
> the top layer reaches back down to affect something at a lower layer:<br>
> like a neuron firing leading to like a thought pattern leading to a<br>
> neuron firing.<br>
<br>
Yes, it is like Hofstadter's Strange Loop. People have called it <br>
downward causality where a supposed epiphenomenal consciousness can <br>
cause changes in the underlying substrate. But that just goes to show <br>
that epiphenomenalism is false. Information can be causal. That is the <br>
whole premise behind programming robots and other machines. So yes, our <br>
mental states can directly affect our brain states and the state of our <br>
entire body. How else would we get be able to get out of bed in the <br>
morning?<br></blockquote><div><br></div><div>Agreed.</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
Moreover, you could even potentially think of it as it retro-causal in <br>
the sense that when it comes to intent and intentionality, one could <br>
argue that desired future states are backwardly causing present states.<br></blockquote><div><br></div><div>Hmm, I've never thought of it in those terms before. An interesting thought.</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
> But I disagree completely with the paper's assessment that computer<br>
> programs are incapable of inductive reasoning. I think the paper's<br>
> author is guilty of the same kind of reductive thinking he complains<br>
> about for how others talk about brain.<br>
> <br>
> If you look at the bottom layer of a Turing machine you will see<br>
> everything following deductively, but this doesn't preclude a higher<br>
> level program at play, collecting and categorizing evidence, and<br>
> running algorithms to generalize that data.<br>
> <br>
> Indeed there have already been programs that given a set of physical<br>
> observations, can derive physical laws to explain them. I think these<br>
> were recent AI experiments performed by Max Tegmark.<br>
<br>
Yes, I agree with this. Even his definition of inductive reasoning is <br>
strained. He equates with choice which doesn't make sense to me. So <br>
while I agree with him about the relationship between choice, agency, <br>
and living systems, I don't think that has anything at all to do with <br>
inductive reasoning. Here is a quick two query experiment with ChatGPT <br>
that proves LLMs are capable of inductive reasoning:<br>
-----------------------------<br>
Here is a made up word being used in a sentence: Because the child was <br>
obsking, his friends could not find him. Use obsking in a sentence of <br>
your own.<br>
ChatGPT said:<br>
The cat was so skilled at obsking that no one could spot her hiding in <br>
the shadows of the attic.<br>
<br>
You said:<br>
The cave was so screwmious, that no one who entered ever returned. What <br>
do you think screwmious means?<br>
ChatGPT said:<br>
Based on the sentence, screwmious seems to describe something ominous, <br>
dangerous, or possibly supernatural—maybe a mix of eerie, treacherous, <br>
and mysterious. It could imply that the cave is so perplexing or <br>
perilous that it ensnares those who enter, never letting them leave.<br>
<br>
You said:<br>
Use it in three different sentences.<br>
ChatGPT said:<br>
The old mansion at the end of the street had a screwmious aura, making <br>
even the bravest kids hesitate to approach.<br>
<br>
As the storm raged on, the sea grew screwmious, swallowing entire ships <br>
without a trace.<br>
<br>
There was something screwmious about the professor’s smile, as if he <br>
knew a terrible secret no one else did.<br>
----------------------------------<br></blockquote><div><br></div><div>Nice experiment!</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
While I was playing to the strengths of an LLM in word prediction, it is <br>
clear that it was understanding the meaning of words that I was making <br>
up on the spot based on a specific context, generalizing them, and then <br>
correctly using them in sentences. In any case, I think the question of <br>
computer programs are capable of inductive reasoning is actually <br>
irrelevant to the question of agency, choice, intention, and the origin <br>
of life or information processing for that matter.<br></blockquote><div><br></div><div>I wonder how the paper author would explain your result.</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
<br>
> <br>
>> Biology since Virchow and Pasteur says all cells come from other<br>
>> cells.<br>
>> Where did the first cell come from? Where did the genetic code come<br>
>> from? Where did information come from? Walker and Davies (2016)<br>
>> called<br>
>> these questions the "hard problem of life”, which is “the<br>
>> identification<br>
>> of the actual physical mechanism that permits information to gain<br>
>> causal<br>
>> purchase over matter”.<br>
> <br>
> On its own, information has no causal powers. Rather, there must be a<br>
> system to proces and acts on that information. He may be making them<br>
> problem more difficult by framing it this way, rather than asking:<br>
> "How do information processing systems arise?" The simplest<br>
> abstraction of such a system is a finite state machine.<br>
<br>
Information definitely has causal powers because causal power is what <br>
distinguishes it from entropy or noise that has no causal power.</blockquote><div><br></div><div><div>To clarify, I do think information states can sit within, and make a difference to some causal chain.</div><div><br></div><div>When I think of information (by itself), however, I think of bits sitting on a hard drive or a CD-ROM, not able to do anything. It is then, only (in my view): information + an information processing system, that the information acquires meaning, or causal power. It is like DNA + ribosomes, a camera feed + a robot brain and body, a nerve signal + a brain to process it.</div><div><br></div><div>Even entropy/noise (like snow on TV screen) can have causal power to a brain who sees it, causing someone to get up and smack the TV or fiddle with the antenna. Or to the cryptanalyst who wracks his brain trying to decipher an apparently encrypted message (but was just random bits meant to frustrate the enemy).</div></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"> Your <br>
statement only even makes sense if you assume that information can exist <br>
on its own, which is in keeping with your Neoplatonism, but not <br>
necessarily an obvious fact.<br></blockquote><div><br></div><div>Don't physicists also think in terms of the entropy of a system, as existing independently (entropy being a measure of how much information is required to describe the system)? Blackholes, for example, have equations defining their information content.</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
Yes, I do think that "How do information processing systems arise?" is a <br>
relevant question because information processing systems only seem to <br>
come from other information processing systems. Conway came from DNA and <br>
the Game of Life came from Conway. Did that chain of intentional <br>
causation of information processing systems have a beginning at all, and <br>
if so, then when and how?<br></blockquote><div><br></div><div>I don't know if this paper will provide any satisfaction to you in that question, but he provides a constructive proof of how assuming (at the start) only information processing systems (what the author calls "graph machines") he works out why most will perceive themselves to exist in a universe with properties similar to our own: <a href="https://arxiv.org/abs/1712.01826">https://arxiv.org/abs/1712.01826</a></div><div><br></div><div>The author is, however, silent on the question of what the ultimate source of these graph machines might be. But this does help offer a solution to the emergence of information out of nowhere (though it could be argued, that within the totality of reality, the information content of everything is still zero), as argued by Standish's "Theory of Nothing": <a href="https://www.hpcoders.com.au/nothing.html">https://www.hpcoders.com.au/nothing.html</a> or as I summarize here: <a href="https://alwaysasking.com/why-does-anything-exist/#Less_Information_More_Reality">https://alwaysasking.com/why-does-anything-exist/#Less_Information_More_Reality</a></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
> Also note they thermodynamically, storing information requires an<br>
> expenditure of energy (the Landauer Limit). So before there could be<br>
> systems that store (or process) information, requires that there be<br>
> machines that store and/or expend energy. Metabolism, in some<br>
> primitive form then, must predate genetic codes, or any other<br>
> information recording mechanism.<br>
<br>
Yes. In this regard it is seems very informative that adenosine <br>
triphosphate or ATP, the energy currency of metabolism, is also a <br>
constituent of RNA molecules that can store and process information in <br>
cells.<br></blockquote><div><br></div><div>I was not aware of that, but I think you are right in that it is perhaps not a coincidence.</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
>> These questions are made all the juicier by there being a $10<br>
>> million<br>
>> USD prize offered by investors affiliated with the Royal Society of<br>
>> Great Britain for demonstrating how any sort of genetic code could<br>
>> evolve stochastically from chemicals in vitro.<br>
>> <br>
>> <a href="https://evo2.org/theprize/" rel="noreferrer" target="_blank">https://evo2.org/theprize/</a><br>
> <br>
> John von Neumann demonstrated how to make life in the "simplified<br>
> universe" of a cellular automata (<br>
> <a href="https://en.wikipedia.org/wiki/Von_Neumann_universal_constructor" rel="noreferrer" target="_blank">https://en.wikipedia.org/wiki/Von_Neumann_universal_constructor</a> ).<br>
> <br>
> One thing that could make this problem more difficult than it might<br>
> seem (for our universe), is that fine-tuning could apply not just to<br>
> the supportability and sustainability of life, but also to it's origin<br>
> and development.<br>
<br>
Yes. In fact the universe could have been fine-tuned for the origination <br>
of life in a previous epoch and since evolved to be fine-tuned for the <br>
sustainment of life and not abiogenesis. The current laws of physics <br>
might no longer allow the creation of biological life from scratch. The <br>
universe is a cold and hostile place now, but at one time it was 37 <br>
degrees centigrade which is body temperature. It was also once much <br>
lower entropy than it is now. There are theories that the fine structure <br>
constant could vary in time and space. That is bound to significantly <br>
affect chemistry in different times and places.<br>
<br>
<a href="https://arxiv.org/abs/1608.04593" rel="noreferrer" target="_blank">https://arxiv.org/abs/1608.04593</a><br>
<br>
The fine structure constant might have been conducive for the creation <br>
of carbon-based life in the distant past but no longer so in this <br>
neighborhood.<br></blockquote><div><br></div><div>What an interesting idea!</div><div><br></div><div>It also has some strong implications for exobiology (we shouldn't find life on any younger worlds). It also might mean Earth required life to arise earlier, perhaps on Mars, and pass the baton via panspermia, for life to have enough time to evolve as far as it has here. This would mean intelligent life is much more rare than we would otherwise conclude.<br></div><div><br></div><div>I know that we have used spectrometry to detect precursors of organic chemistry from the light of distant gas clouds ( e.g. <a href="https://physicsworld.com/a/amino-acid-detected-in-space/">https://physicsworld.com/a/amino-acid-detected-in-space/</a> ). I wonder if with sufficiently sensitive telescopes we could ever do the same for more distant (and older) galaxies, or if, in finding similar molecules (and spectral bands of elements) it would rule out changes in the fine structure constant.</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<br>
> That is, there could be an extremely specific, improbable, kludgy path<br>
> that just so happens to work in this universe because the chemistry is<br>
> just right to support this specific sequence of steps, involving just<br>
> the right sequence of molecular interactions. Anthropic fine-tuning<br>
> means there's no reason we should expect there to be more than one way<br>
> to get to life (there could be only a single sequence of reactions<br>
> that get there). If this thinking is right, the winner will we need to<br>
> discover this one one exact sequence (which would necessarily be the<br>
> same one they led to us).<br>
<br>
That too is a possibility. I wonder if there have been any serious <br>
entries for the prize?<br><br></blockquote><div><br></div><div>Met too.</div><div><br></div><div>Jason </div></div></div>