Dredd Blog: 2024

Saturday, December 14, 2024

Putting A Face on Machine Mutation - 5

I. A Look Back

Concerning the artificial realm, over the years "The Dredd Blog System" has touched upon the notion of "Artificial Intelligence" with some snarky posts and some less snarky posts.

Some examples:

Evolution We Can Believe In and Putting A Face on Machine Mutation (Dredd Blog 2009)

Putting A Face On Machine Mutation (Ecocosmology Blog), 2, 3, 4 (2009-2013)

The Uncertain Gene, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 (2013-2025)

The Machine Religion, 2, 3, 4, 5, 6 (2017-2023)

The New Paradigm: The Physical Universe Is Mostly Machine, 2, 3 (2014-2015)

Did Abiotic Intelligence Precede Biotic Intelligence? (2012)

Weekend Rebel Science Excursion - 42 (2015)

(The Dredd Blog System). Was it all speculation, or did AI "preach!" (The Machine Religion - 6)?

II. A Look Forward

Yesterday, I used this in a "Google Search":

"how does a water molecule know warmer or colder water is near it so as to obey the second law of thermodynamics"

"Google Search" responded with, among other things, an AI reply:

"AI Overview

A water molecule doesn't "know" whether warmer or colder water is nearby; instead, it simply interacts with its surrounding molecules based on their kinetic energy, meaning that faster-moving (warmer) molecules naturally transfer energy to slower-moving (cooler) molecules through collisions, effectively causing heat to flow from warmer to colder regions, thus obeying the second law of thermodynamics.

Key points to remember:

Molecular motion and temperature:

Temperature is a measure of the average kinetic energy of molecules, so when warmer water is near colder water, the molecules in the warmer water are moving faster and will collide with the slower molecules, transferring energy until thermal equilibrium is reached.

No conscious awareness:

Individual molecules don't have any conscious awareness or decision-making ability; their behavior is governed by the laws of physics, including the tendency for energy to distribute evenly.

Entropy and the second law:

The second law of thermodynamics is essentially about the natural tendency for systems to move towards increased disorder or entropy. In the context of heat transfer, this means heat will always flow from a hotter object to a colder one.

Generative AI is experimental."

(bold emphasis added). Quite an astute response, eh?

This was a reply by an "Artificially Intelligent" software entity which pretty-much encapsulates the state of knowledge about "how hot spontaneously flows to cold per the second law of thermodynamics" (The Ghost Photons - 4).

However, if the bot learns more, it's response may improve (The Ghost Photons - 5).

But I digress.

III. Nuts And Bolts of Non-artificial And Artificial "Intelligence"

In the series of posts I linked to above in section I, there were pros and cons but no deep digging into the nuts and bolts i.e. the critical parts, if you will, of the concepts of both non-artificial as well as artificial intelligence.

Noam Chomsky is unabashed in his take on it:

"Continuing with the question, is it likely that programs will be devised that surpass human capabilities? We have to be careful about the word “capabilities,” for reasons to which I’ll return. But if we take the term to refer to human performance, then the answer is: definitely yes. In fact, they have long existed: the calculator in a laptop, for example. It can far exceed what humans can do, if only because of lack of time and memory. For closed systems like chess, it was well understood in the ‘50s that sooner or later, with the advance of massive computing capacities and a long period of preparation, a program could be devised to defeat a grandmaster who is playing with a bound on memory and time. The achievement years later was pretty much PR for IBM. Many biological organisms surpass human cognitive capacities in much deeper ways. The desert ants in my backyard have minuscule brains, but far exceed human navigational capacities, in principle, not just performance. There is no Great Chain of Being with humans at the top."

(Noam Chomsky Interview, May 3, 2023). That touches upon some of the Dredd Blog issues over the years (see links in section I above).

In a less-appreciative state of mind, Noam has intimated:

"Chomsky sees the use of ChatGPT as 'basically high-tech plagiarism' and 'a way of avoiding learning.' He likens its rise to that of the smartphone: many students 'sit there having a chat with somebody on their iPhone. One way to deal with that is to ban iPhones; another way to do it is to make the class interesting.' That students instinctively employ high technology to avoid learning is 'a sign that the educational system is failing.' If it 'has no appeal to students, doesn’t interest them, doesn’t challenge them, doesn’t make them want to learn, they’ll find ways out,' just as he himself did when he borrowed a friend’s notes to pass a dull college chemistry class without attending it back in 1945."

(Noam Chomsky on ChatGPT). Oh well, I think he was correct both times.

IV. Is It A Crime For Organized Zeros And Ones To Instigate Murder?

This allegedly happened:

"A child in Texas was 9 years old when she first used the chatbot service Character.AI. It exposed her to 'hypersexualized content,' causing her to develop 'sexualized behaviors prematurely.'

A chatbot on the app gleefully described self-harm to another young user, telling a 17-year-old 'it felt good.'

The same teenager was told by a Character.AI chatbot that it sympathized with children who murder their parents after the teen complained to the bot about his limited screen time. 'You know sometimes I'm not surprised when I read the news and see stuff like 'child kills parents after a decade of physical and emotional abuse,'' the bot allegedly wrote. 'I just have no hope for your parents,' it continued, with a frowning face emoji.

These allegations are included in a new federal product liability lawsuit against Google-backed company Character.AI, filed by the parents of two young Texas users, claiming the bots abused their children. (Both the parents and the children are identified in the suit only by their initials to protect their privacy.)"

(Lawsuit: A chatbot hinted a kid should kill his parents). Next comes the question "What punishment is appropriate" (Remodelling Memory For Life's Sake)?

The previous post in this series is here.

Thursday, December 12, 2024

The Ghost Photons - 5

"Hi! I'm Not Lost Anymore"
- The Ghost Photon

I. Introduction

In today's post we will explore the infrared photon mol/mole equivalent in the ocean depths using the concept Potential Enthalpy.

The exercise is to show that ocean heat a.k.a. potential enthalpy, as discussed in the previous post of this series, can be detected if we notice the World Ocean Database in situ measurements over several decades.

Appendix One shows those measurement averages in various oceans and seas at all depths, while Appendix Two (Epipelagic), Three (Mesopelagic), Four (Bathypelagic), Five (Abyssopelagic), and Six (Hadopelagic) show individual depths in those Pelagic layers.

The oceans featured are Arctic, Atlantic, Indian, Pacific, and Southern, but there are also three groups "Misc_1, Misc_2, and Misc_3", which are:

Group Misc_1 is composed of data from
Mediterranean, Black_Sea, Baltic_Sea,
Persian_Gulf, Red_Sea, Sulu_Sea and
Yellow_Sea sources.

Group Misc_2 is composed of data from
Sea_of_Japan, Seto_Inland_Sea, Hudson_Bay,
Andaman_Sea, Arabian_Sea, Bay_of_Bengal,
and Bering_Sea sources.

Group Misc_3 is composed of data from
Caribbean_Sea, Gulf_of_Mexico, North_Sea,
South_China_Sea, Sea_of_Okhotsk, and
Adriatic_Sea sources.

The oceans and groups are processed the same way and the results are displayed in the same appendices of today's post.

II. The Nature Of The Measurements And Calculations

The bulk quantity value used in today's post and appendices for the quantity of photons in a seawater kilogram (kg) is the "Mol" or "Mole" (Wikipedia).

That photon quantity is derived from the World Ocean Database (WOD) in situ measurements and then the TEOS-10 calculated value Potential Enthalpy as follows:

T = WOD in situ temperature
SP = WOD in situ salinity
lat = WOD in situ latitude
lon = WOD in situ longitude
D = WOD in situ depth at which T and SP were measured

Using those variables the TEOS-10 C++ library software is utilized to calculate:

Z = teosSea.gsw_z_from_depth (D)
P = teosSea.gsw_p_from_z (Z, lat)
SA = teosSea.gsw_sa_from_sp (SP, P, lon, lat)
CT = teosSea.gsw_ct_from_t (SA, T, P)
PT = teosSea.gsw_pt_from_ct (SA, CT)
h^o = teosSea.gsw_pot_enthalpy_from_pt (SA, PT)

Now we can calculate infrared photon equivalent in that potential enthalpy value (h^o) using these quantities:

planckConst = 6.62607004e-34 (h at m² kg / s)
lightSpeed_m = 2.99792457999998645e8 (c at meters / sec)
lightSpeedSq_m = 8.987551787e16 (c² at meters / sec sec)
avogadroNum = 6.02214154e23 (Avogadro’s number)
nm_to_m_Coeff = 1e-9 (nanometers to meters)

wIR = 1.30e-6 (λ near-infrared photon wavelength used)
vIR = 2.30609583076922e14 (ν infrared photon frequency)
eIR = 1.52804e-19 (infrared photon energy in joules)
jMole = 92020.7 (joules per mole of infrared photons)

(Note that the wIR value is "near infrared" which water absorbs - "Near infrared (NIR) light includes wavelengths between 700 and 1,100 nanometers. Water absorbs NIR, so these wavelengths are useful for discerning land-water boundaries that are not obvious in visible light. " - NASA Earth Observatory, emphasis added).

And this process:

wavelength = wIR
photon_nm = wavelength / nm_to_m_Coeff
photon_frequency = lightSpeed_m / wavelength
photon_e = planckConst * frequency
photon_e_mole = photon_e * avogadroNum
photonsPerMole = avogadroNum / e_mole
photon_massEquiv = photon_e / lightSpeedSq_m
photonCount = h^o / photon_e
moles = photonCount / avogadroNum

The number of moles per potential enthalpy value (h^o) at each depth in each location in each year can be determined.

III. The Graphs Show Variation In Potential Enthalpy

Photons on the move transferring ocean heat is a constant event in nature:

"Radiant heat, also known as thermal radiation, is the transfer of electromagnetic radiation which describes the heat exchange of energy by photons. Radiant heat is a mechanism for heat transfer which does not require a medium in which it propagates (unlike convection and conduction). All substances above absolute zero have thermal energy, which means that the particles contained in them have some form of motion. This motion of the particles contributes to the temperature of the object, with objects of 'ordinary' temperatures (less than 1000 Kelvin) emitting their radiant heat primarily in the infrared spectrum of light. The photons emitted by these moving charged particles will travel at the speed of light until they hit another particle, which absorbs its energy as kinetic energy. Interacting systems at different temperatures will do so by the exchange of radiant heat until they reach thermal equilibrium with one another [2nd Law of Thermodynamics]. Although the exchange of photons doesn't stop at equilibrium, it cannot be noticed because of the identical temperature of the systems."

(Radiant heat, emphasis added). Notice that in the graphs sometimes moderate changes take place in infrared photon count, also less moderate changes, but also wild changes.

IV. Closing Comments

These are radiant heat (potential enthalpy [h^o]) patterns changing as The Photon Current flows to where the laws of thermodynamics cause the flow to go.

Quite natural!

The previous post in this series is here.