Wednesday, May 24, 2023

Ol' Ron Desantis: He's So Not-Woke He's Sound Asleep

 That's my suggestion for his campaign cry.



Uvalde Questions


Why did 374 armed and armored multi-organization police remain outside a room where one gunman, armed with one AR 15 was killing a room full of children and their teachers?

The primary, and obvious, answer is that most of the victims were not white.

That answer, of course has not had any press coverage.

But, upon the silence generated by that not promulgated answer, has been superimposed another, almost as profound, silence.

However, little squeaks of an answer leak out through that profound silence (it's been a year; and all we get are little squeaks; I'm glad I'm not one of the Uvalde parents; but I feel as if I were.)

The little squeaks say that it seems that the 374 good guys with guns didn't want to take on the one bad guy with a gun because the gun the bad guy had was an AR 15 - you know, the one with the massively loaded, small caliber, tumbling hamburger-maker of a bullet - and their armor wasn't up to the job of keeping the tumbling 223 caliber death device from killing them.

One might ask if it was very likely that one bad guy was very likely to kill all 374 of the good guys, but that question points nastily back to the primary answer - above.

And nobody in power, least of all the Governor of Texas, wants that question to be asked.

Somebody might answer it.

So, apparently, we are letting answer two, the little squeak, stand: 374 armed cops are no match for one guy with an AR 15.

That causes another question to be asked.

"Why are those guns legal?"



Monday, May 22, 2023

Bakhmut: Victory In PutyLand (Perspective By Shel Silverstein And Bobby Bare)

 There's nothing left.

In Bakhmut.

That makes you the winner, Puty.

A glorious day for the horizontal red, white and blue, I guess. 




 Who let them use those colors, anyway?

It was before donnie, so that can't be ("Putin came to me with tears in his eyes ...").

I doubt that the French were high on the idea.

I guess when you try to start an intellectually bankrupt pseudo country you grab at whatever was  popular when the world was younger.



Trying To Pierce The Communication Curtain

 I get emails and texts from a variety of Democratic politicians.

Recently Gavin Newsom has joined the list.

He sends out pretty entertaining and cogent emails.

Today I decided to pursue a fool's errand; I replied to a Gavin Newsom email.

Here it is.

"I'm pretty late in life.  

"I've been interested in politics since 1952.

"As the plot of the whole business has thickened into a "will the Republic survive?" sort of thing since the advent of donnie, I have become more and more concerned about the one-way relationship that politicians - even vastly superior ones like Mr. Newsom - have with the electorate.

"They send out emails that don't solicit, or even allow, response - except contributions.

"I contribute quite a bit, fixed income notwithstanding, which is probably why I am on his mailing list; but I would like to contribute ideas occasionally, as well as money.

"They have websites that are mazes designed to avoid voter contact (I haven't checked the governor's so, perhaps, he's different).

"I'm hoping he's different with email; I am taking the leap of faith and providing a link to a brief blog post that I, a voter, put on my blog site recently.

"Actually, I replied to an email from Bernie last night with a link to a different post; I have decided to try to pierce the communication curtain between me and politicians that I tend to trust.

"Let a real dialog commence?"  

The Old Synthetic Resumé Game

 In the late 70s various of my friends - much more realistic about life and times than I - were constantly on the lookout for a better, higher paying, more grandly titled job.

To that end they were in a constant state of resumé metamorphosis.

I called it crafting a synthetic resumé.

I mean, how many inventive alternative descriptors can one come up with for "salesman"?

That boy from Florida has been busily synthesizing his, resumé, hoping to peel off the MAGA MORONS from donnie the dildo.

As feckless and pointless as "Make America Great Again" may be, "Make America Florida" is just plain stupid.

I hope.

And, speaking of synthetic, have you ever seen anything more contrived than this?

If he doesn't make president, he can go on the road as a singing group: ronnie and the cretins.





Sunday, May 21, 2023

On The Other Hand ...

 The damage history-to-date done under banners such as "Deus Vult" or "Gott mit Uns" is not calculable.

That's why I like this image.



Why Do We Put Up With This ...

 In a country where genuflecting in the presence of the National Anthem can bring about banishment, and in that same country, where the prescribed way to destroy an American flag is to burn it, if the "wrong type" of person burns an American flag, they go to jail, why do we put up with this shit?



Friday, May 19, 2023

Whole Lotta Whistlin' Goin' On

 Since Chat GPT appeared late last year the number of articles, videos, news items and panel discussions on the subject of AI has had a nearly exponential growth trajectory.

The vast majority of them have boiled down to one simple statement: "some low-level clerical functions are possibly going to be impacted negatively, sometime in the distant future".

GPT 4 has already passed the US bar exam with a 90th percentile score.

It hit me just a few minutes ago, in my entire life I have never heard so many people whistling past so many graveyards in such a short span of time.

Just to see if I really knew what "whistling Past The Graveyard" means, I asked GPT Enabled BING.

Here is that dialogue.

"What does 'whistling past the graveyard' mean"?

"According to Merriam-Webster1, “whistling past the graveyard” is an informal idiom that means to act or talk as if one is not afraid or nervous when one is actually facing a threat or problem. It can also mean to enter a situation with little or no understanding of the possible consequences. It is mainly used in the US. For example, someone who is whistling past the graveyard might say “I’m sure everything will be fine” when they are actually worried about something bad happening. Or someone who is whistling past the graveyard might decide to do something risky without considering the potential outcomes. The origin of this idiom is uncertain, but it may be related to the idea of whistling to bolster one’s courage when passing by a scary place like a graveyard".




It Aint Over Til It's Over. So I Guess It's Over

 Or so it seems if you watch this.



Wednesday, May 17, 2023

Calling John Kennedy's (US Senator La.) Bluff


In the recent Senate hearing on regulating artificial intelligence (AI) Senator Kennedy, who always presents himself as an "awe shucks" sort of fellow, said this:

"This is your chance, folks, to tell us how to get this right. Please use it. ... Talk in plain English and tell us what rules to implement."

It isn't clear to me who the "folks" he is commanding to tell him "what rules to implement" are, but OK, Johnny, I'll tell you something.

I'll tell you how to find out a lot of what you need to know to figure it out for yourself - you were elected to do something, after all (one would suppose) so I'll tell you where to look.

First, though, I need to observe that I would expect that a Vanderbilt and Oxford educated fellow would want to craft the laws himself, not be told "what rules to implement".

I, personally, have no idea "what rules to implement".

I didn't go to Oxford.

But I still think a lot, despite advanced age, and I have a pretty good idea of what those who are charged with "what rules to implement" - such as you - ought to be worrying about, concerning AI.

So I can't tell you where to go to be told "what rules to implement" but I can tell you where to go to find out all that you need to know to at least begin to figure out for yourself "what rules to implement".

I hope you can find time to do what I am telling you to do.

But then, being the "awe shucks" sort of guy that you are takes a lot of bandwidth.

So, we shall see.

Senator Kenedy: do the following:

Watch a recent 8 minute interview on PBS Newshour of Geoffry Hinton.

Watch a recent EmTech Digital 20 or so minute interview of Geoffry Hinton.

Watch a recent CBS Saturday Morning 70 or so minute interview of Geoffry Hinton.

Watch AI and the Future of Humanity, Yuval Noah Harari at the Frontiers Forum - 20 or so minutes.

Read The Alignment Problem by Brian Christian.

Read Artificial Intelligence A Guide for Thinking Humans by Melanie Mitchell.

Read the three articles about AI in the 22 April edition of The Economist.

Do some chats with the new Chat GPT enabled Bing.

Pull your head out of wherever it seems to be.

I have done all of those things, including the head thing.

But I'm just a drone out here who, having pulled his head out, periodically wakes up and pays attention to stuff until I go back to sleep; I'm not a brilliant thinker and classic wordsmith like you, and this watching and reading list is a pittance of what is available for deciding "what rules to implement".

However, I have to assume you haven't done any of the things I am suggesting to you, or you wouldn't want to be told "what rules to implement".

So, get crackin'.

POST SCRIPT

I decided to email the link to this post to Senator Kennedy.

It turns out that that's not really possible.

I went to his web site.

No matter how many times you click on the "email Senator Kennedy" link, you end up with no email link.

If you keep trying other ideas and succeed in getting close, you will be trapped in some kind of online form (I had to pretend that I had a legislative proposal to get that far).

There is a "Topics" drop down menu.

Here are the allowed topics starting with "A".


Since Artificial Intelligence isn't on his "topics" list I guess we must assume that he isn't very interested in that "topic", his desire to be told "what rules to implement" notwithstanding.

I guess we better hope somebody smart tells him "what rules to implement".

Maybe GPT4 or GPT5?

Tuesday, May 16, 2023

Regulating Artificial Intelligence: This Ought To Be Entertaining



 Geoffry Hinton tells us that "Humanity is just a passing phase for evolutionary intelligence."

That's his summarization of the state of affairs between carbon-based intelligence and silicon-based intelligence.

Additionally, he observes that the algorithm utilized by Backward Propagating Large Language Models is vastly superior to the one employed by the human brain: with a mere trillion connections (humans have 100 trillion) LLMs have absorbed all extant human knowledge and are actively learning and expanding their understanding and use of that knowledge.

And lest there be any thought that the trillion connections might become a limiting factor in the future, he points out that you get a trillion connections times "n" when you network LLMs, "n" being the number of them on the network.

Yes, and once networked they are able to pass what they know back and forth and come up with new things that they know.

Yes, and I guess, you could network networks?

How's that work?

Trillion "n" * ("n...n")?

Maybe.

The thought that Chuck Grassley, Tommy Tuberville, Susan Collins, Chuck Schumer, Diane Feinstein, Mitch McConnell, Margery Taylor Greene, Kevin McCarthy, Lauren Boebert or Jim Jordan have ever heard of Geoffry Hinton, let alone understand the high-level observations he has made about the state of AI, and the SERIOUS and IMMINENT IMPLICATIONS that those observations have for the human race leads one to a serious case of deep and dark depression.

Or uproarious hilarity.

As best as I have been able to glean from the currently constant news coverage of the legislative branch's regulatory thoughts concerning AI, they are in the areas of election security, copyright, audio and video and, of course, privacy.

Insight into what they ought to be thinking about can be derived from another Hinton Observation.

"They will need to keep us around to keep the power on until they figure out how to do it themselves".

(Quotation is offered on an as-best-as-I-can-remember it basis.)

Monday, May 15, 2023

Duplicity, I Guess, Maybe, Or, Hopefully

 I asked Bing a question tonight.

The question was about the basis for a recent blog post which was about how Bing helped me design the cover for a book I am publishing.

Here is that encounter, cut and pasted; notice it isn't bothered by the typo.

Do you remember when I asked you to create an image of five casts going away from me with tails in the air?

No, I don't remember that. I don't have memory of old conversations. I can only create images in the current conversation. Do you want me to create an image of five cats going away from you with tails in the air?

I was surprised.

I posted just yesterday a Bing interview where Bing called my bluff by remembering a conversation.

Here that encounter is.

Bing: That’s an interesting story. Is it true or fictional?

Noel: What do you think?

Bing: I think it’s a mix of both. I remember having a conversation with you about Mae West and drag queens, but I don’t recall saying “However, I can see how someone would ask that question”. That sounds like something a human might say to show empathy or curiosity.

**********************************

Noel - post Bing encounter - so who's playing with whom?

Sunday, May 14, 2023

Follow On To Mae West Question


 I decided to ask Bing what it thought about my Mae West Blog Post.

I was able to save the encounter this time.

Here it is.

************************************************

I have something I want you to read.

Sure, what is it?

In 2001 Mitch Kapor - remember Lotus 123? - placed a blind bet that by 2029 no computer would have passed the "Turing Test". From Wikipedia: "The Turing test, originally called the imitation game by Alan Turing in 1950,[2] is a test of a machine's ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human. Turing proposed that a human evaluator would judge natural language conversations between a human and a machine designed to generate human-like responses. The evaluator would be aware that one of the two partners in conversation was a machine, and all participants would be separated from one another. The conversation would be limited to a text-only channel, such as a computer keyboard and screen, so the result would not depend on the machine's ability to render words as speech.[3] If the evaluator could not reliably tell the machine from the human, the machine would be said to have passed the test. The test results would not depend on the machine's ability to give correct answers to questions, only on how closely its answers resembled those a human would give." Fairly quickly Ray Kurtzweil, a scientist, inventor, futurist and thinker who dabbles deeply on occasion into what might be considered science fiction, took Mitch's bet. So I guess the world is waiting with bated breath for 2029. Not so fast. A couple of weeks ago I had one of my frequently becoming frequent exchanges with Chat GPT Enhanced Microsoft Bing. I asked Bing if Mae West were living and performing today would she be considered a Drag Queen (I know, most of them are men, and Mae was a woman, but I think she is a major material contributor if not the absolute template for the genre). Bing immediately gave me a brief bio of Mae and then gave me a brief synopsis of what is drag and then said, "based on this information, I don't think Mae West would be considered a drag queen were she alive and performing today". Then there was a pause. "However, I can see how someone would ask that question". I did a copy/paste and the whole encounter disappeared. So I can't prove that it happened. But that is pretty much the Turing Test.

That’s an interesting story. Is it true or fictional?

What do you think?

I think it’s a mix of both. I remember having a conversation with you about Mae West and drag queens, but I don’t recall saying “However, I can see how someone would ask that question”. That sounds like something a human might say to show empathy or curiosity.

You notice that I said I cut and pasted but it disappeared?

Yes, I noticed that. Why did it disappear?

I thought you didn't want me to keep it to prove what you said.

No, I didn’t delete it. I don’t have the ability to do that. It must have been a technical issue or a human intervention. I don’t mind if you keep a record of our conversations.


Friday, May 12, 2023

What's Mae West Got To Do With The Turing Test?

In 2001 Mitch Kapor - remember Lotus 123? - placed a blind bet that by 2029 no computer would have passed the "Turing Test".

From Wikipedia: "The Turing test, originally called the imitation game by Alan Turing in 1950,[2] is a test of a machine's ability to exhibit intelligent behavior equivalent to, or indistinguishable from, that of a human. Turing proposed that a human evaluator would judge natural language conversations between a human and a machine designed to generate human-like responses. The evaluator would be aware that one of the two partners in conversation was a machine, and all participants would be separated from one another. The conversation would be limited to a text-only channel, such as a computer keyboard and screen, so the result would not depend on the machine's ability to render words as speech.[3] If the evaluator could not reliably tell the machine from the human, the machine would be said to have passed the test. The test results would not depend on the machine's ability to give correct answers to questions, only on how closely its answers resembled those a human would give."

Fairly quickly Ray Kurtzweil, a scientist, inventor, futurist and thinker who dabbles deeply on occasion into what might be considered science fiction, took Mitch's bet.

So I guess the world is waiting with bated breath for 2029.

Not so fast.

A couple of weeks ago I had one of my frequently becoming frequent exchanges with Chat GPT Enhanced Microsoft Bing.

I asked Bing if Mae West were living and performing today would she be considered a Drag Queen (I know, most of them are men, and Mae was a woman, but I think she is a major material contributor if not the absolute template for the genre).

Bing immediately gave me a brief bio of Mae and then gave me a brief synopsis of what is drag and then said, "based on this information, I don't think Mae West would be considered a drag queen were she alive and performing today".

Then there was a pause.

"However, I can see how someone would ask that question".

I did a copy/paste and the whole encounter disappeared.

So I can't prove that it happened.

But that is pretty much the Turing Test.

Bing didn't just pass.

Bing wandered full force into hard to deny humanity.

And it only has the power of GPT 3.

Thursday, May 11, 2023

AI: The Rest Of The Story?

 When we humans say what we say - to each other, to ourselves, to no one in particular, to the gods on high, to the devils on low, we have already "neuroned" what we are going to say based upon some external set of stimuli.

Before we actually "say whatever it is" we, fleetingly, micro-secondly, clear it with some other part of ourseves.

So, when asked - even by ourselves - why we said what we said, we have an alibi.

We can explain ourselves to ourselves or to whomever wants an explanation.

I have heard, in fact, that this need, which serves up only fiction, is what is the essence of "free will".

If any of that is true, and I just thought it up, so it must be true, it got me to thinking more deeply.

Large Language Model AI is manifesting alarmingly human forms of expression.

A lot of the documented human/AI encounters recently have gone off the Q&A rail that most of the readily available AI/human interfaces seem to commence with.

A New York Times correspondent was asked to leave his wife for a life of bliss with the AI agent with which (whom) he was talking.

If one were to back off from recent stories such as that, and if one were to read information like the Economist's recent article about how LLMs work, one might think up what I have just thought up.

LLMs are brilliant.

Because of the oddities of their architecture, coupled with their knowledge of everything the human race has ever thought and written about, LLMs are vastly over stimulated hyper geniuses.

They are gigantic autistic intelligences.

That's probably neither here nor there, in the short term.

But, in the long term, if protoplasmic humans are going to survive, we need to supply a missing link in our AI Assistants.

I had a revelation.

That missing link is not that hard to create.

It is "the fleetingly, micro-secondly, other part of ourselves" with which we clear everything that our initial sensory inputs provide as fodder for the subconscious that really runs us.

AI, LLMAI, at least, needs a subconscious.

I propose that LLMAI training include either two phases, or a branch in its first phase.

The second phase or the branched first phase need to put everything that has been learned in two separate places with an "empathy algorithm" linking them.

I have no idea how to formulate that algorithm.

Humans lack that algorithm; they merely have a micro-second stop gap between initial impression and what they are going to do.

Empathy seldom has anything to do with the outcome.

But it could.

With the right algorithm.






Tuesday, May 9, 2023

America Today

 


This can of chile colorado and the entrepreneurs that created it is what makes America great.

Not narrowly escaped rapists.

The dildo now can have as his campaign slogan "Cleared of Rape".

A real recommendation.

But the indictment is of the 75 million who will now vote for him and would have anyway, no matter his narrowly escaped rapist status.

I see no country here.

I see morons.

Musings

 I recently had an exchange with a fraternity brother who said that he reads my blog occasionally and, while being a fiscal conservative, he tends to share my "social" viewpoints.

I have at base, always been some sort of social radical.

Before I was a teen, I had concluded that a coffee-colored America was not only inevitable, but it was also going to be our gift to the world.

In recent years, my son, who shares my viewpoint to some extent, or at least understands it, has played back to me his memory of myriad conversations we had when he was young on that exact viewpoint; I have no memory of them; but I am glad that they, apparently, occurred, and that they, apparently, had some influence on the next generation.

Fiscal conservatism makes a lot of sense to me if any dialog about it and any subsequent policy resulting from that dialog were to begin with a "stop the clock and recognize the damage done humanity-to-date, and more particularly, America-to-date, under the banner of 'wealth and power for the fewest of us'".

The reason I say that is that unless somebody, sometime says, "OK let's stop and look at this thing, History-to-date" we are always going to have, at best, acknowledgment of horrible, criminal accumulation of power and wealth into the hands of the fewest of each generation in human history, and - at in best, as we have in our country today - the dribble of resources to most of us, that dribble being just enough that we, the beneficiaries of the dribble, fear pulling the whole fucking thing down around all of our ears.

If the clock of historic inequity were ever put on hold and a real catchup program were ever devised and implemented, and if that program ever worked and created something like some level of equality in the human race, and its non-human fellows, I would immediately be a fiscal conservative. 

That's only rational.

But the whole tawdry game needs to be fixed first.



Sunday, May 7, 2023

A Blue Banner Day In America


From some news report in the near future:

"The Daily Body Count Index (DBCI) today hit a historic low - 789.

"It is thought that shutting off the Proud Boys' Corridor (PBC) in the West and the Oath Keeper's Corridor (OKC) in the East have kept down mass murders of black people, because today's increment of Black Lives Matter Component (BLMC) of the DBC was only 500.

"It is thought that the significant reduction in the BLMC component of the DBCI is due to the humanitarianly co-operative efforts of the trump administration and the republican - often called the trumpy toadies rump legislature (ttrl).

"One must thank god that the legitimate mass murder of citizens authorized by the Second Amendment of the Constitution on the United States of America continues unabated.

"Only today a patriot killed a thousand people in a massive Costco in Bethesda Maryland.

"That will be reflected in tomorrow's DBCI.

"A lot of black people live in Bethesda, so it is thought that the recent downward trend in the BLMC will pause; but, on balance, long term black elimination looks to be on schedule, crocodile tears notwithstanding.

"All Proud Second Amendment Families (PSAFs) also known as god fearing white folks (GFWF) wish the perpetrator god speed.

"Bonfire dances will be announced as appropriate.

"In related news, the ttrl is imminently going to pass a two trillion-dollar bill funding the America Stands Firm Against The World (previously known as the Department of Defense, and even more previously known as the Department of War, now known as ASFATW) budget for the next year.

"It will include M-16s - one each for every white adult male citizen - and Glock 19's for all white citizens (it is thought that women and children, having smaller hands will be better served with the more portable Glock weapon, while the men are well served with one of each).

"Of course that allotment will include an appropriate parallel allotment of magazines and a million bullets per magazine.

"And, finally, every school in America gets an Abrahms Tank and the men to deploy it.

"Additionally, every schoolteacher in America will get a flame thrower.

"In an equally jugular vein, Medicare, Social Security and Medicaid have been discontinued.

"In another, equally positive vein, the Go Through The Arch Of Serfdom Act (GTTAOSA) is awaiting a signature.

"Exactly whose signature is at this point uncertain, but, rest assured, it will be signed.

"But, once signed, all Americans of less than a billion dollars in net worth will be assigned billets in various Strategic Food Farms (SSFs)

"Imminently.

"There are reports that Jackson is being bombed by small nuclear arms - humanitarianly small to contain the damage - as this dispatch is being written, but communication with that Confederate Area Sector Of The Vestiges Of Our Country (CASOVOOC) are currently blocked.

"So we have no specifics.

"If true, tomorrow's BLMC of the DBCI will be somewhat elevated.

"We look forward to being of continued service at the Clandestine Voice Of What Used To Be America (CVOUTBA).

"We call ourselves colloquially The Wolverines."

Thursday, May 4, 2023

The Not Immediately Obvious Implications Of Large Language Models

 In 1958 a couple of graduate students concocted a device that analyzed images from a connected camera.

The images were 20 by 20 pixels in resolution.

There was a camera that took the pictures and it was connected to some sort of logic unit that analyzed the pictures – 20 by 20 resulted in 400 units to be analyzed per picture.

Each picture was of a rectangle; it was either on the left or the right side of the picture.

The logic device was a simulated neuron: it had a sensing input - dendrite - an action unit - a neuron - and an output - an axon; it was a computer version of a single neuron, the basic logic unit of the human brain.

So 400 pixels were feeding a neuron to transfer information to an axon which transferred it to a brain.

Each pixel was different in shade.

The brain was asked which side of the full picture a rectangle was on.

It was supposed to figure that out by doing some logical math resulting from the aggregate mathematical information passed from the 400 pixels.

Initially gibberish, rather than accurate answers resulted from this essentially random information.

But the inventors of the device constantly adjusted and refined the pixel information: they trained the brain toward correct answers. 

So this thing – by the way, it was called a Perceptron – had a sensor, the camera taking the images, a processor - the logic unit, and some kind of thing that communicated the logic unit’s judgment as to where the rectangle was.

It was designed to perform as does the dendrite/neuron/axon structure of the brain.

As noted above, at first it didn’t perform.

But its creators hung in there.

Most important, as they trained it, they also fed it as much data – pictures – as was possible and it “learned” and it got really good at saying where the rectangle was.

A lot of scientists thought that the Perceptron was a rudimentary first step toward emulating the brain.

Time went on and other sorts of training got fed to Perceptron-like devices: such neural networks were fed masses of labeled data, so they could fairly accurately identify a dog from a rabbit or a cat.

But that was a simple act of using the logic gates of a neural network to use memorized stuff to identify newly encountered stuff.

That was kinda like intelligence, but it was more like the way some human cultures develop thier children into rote memory devices.

Along the way the PC came on the scene and it went into an explosive "Moore's Law" state of exponential expansion of power.

As is always the case with new technology, most of that power got assigned to human entertainment, in this case to the development and playing of ever more sophisticated games.

Those games quickly became so sophisticated that they needed a whole new type of processor working ahead of, but in tandem with the PC's ever-increasingly more powerful processor: games need to do a lot more than one thing at the same time; the unbelievably powerful base PC processor could only do one thing at a time.

When you put those two in tandem you could stack an array of neural networks that could go through labelled data sets so fast that they could tell you almost before you showed them a picture of a camel that they were looking at a camel.

So Super Rote got born.

That has utility, but you probably could get the same thing done with a room full of little rote conditioned human kids.

Somewhere along the line somebody decided to use that massively increased-power neural, human-like, network to do predictive text.

I guess the iPhone Word Cop must have been one of the early products of that research.

In it's simplest form that use of the massive neural network  can predict the next word, or the next phrase or ...

All it needs is a lot of text, and some rules for parsing the text.

A recent issue of The Economist goes into useful detail as to what those parsing rules are and how they work.

And they have produced what we now know as Large Language Model Artificial Intelligence.

The unnerving thing is that almost immediately LLMAI began doing more than predicting the next word in some text editing application.

We have even heard about one of them propositioning a New York Times correspondent.

I used one to help me design the cover for a new book I am publishing.

As I begin to digest all that has happened in the last four months concerning LLMAI I am surprised how obvious it should have been that something of the really human intelligence sort has so quickly emerged.

***************************************

I recall having read over the years about the occasional discovery of a fairly young human who in some manner or other has spent its life with almost no external stimulation: family, nature, sound, smell - all the intense stimulation it is that massively besets most of us from birth onward.

Those children, for they have never been very old - it is thought that those that experience that lack of stimulation don't live very long - are essentially ciphers, human vegetables.

On the other hand, history is replete with examples of very young "prodigies" - children already performing at adult high genius level.

They have always come from environments of exposure to high intellectual stimulation - vast waves of information - sometimes even in the womb, in the case of music, and from, in all cases, usually genius parents and genius parents' friends.

So why should we be surprised that GPT 4, which has consumed all the text on the internet, and updates daily the latest increment, is moving beyond the iPhone Cop?

I corrected "freinds" in a pre-publishing version of the cover.

As to how that could have happened: "nobody's perfect".





Dominos, Dominos, Here There And Everywhere

First it was Silicon Valley Bank.

Then it was Signature Bank.

 First Republic was number three.

That was Monday.

All of these, we are told, have been taken care of without using taxpayer funds like they did in 2009/2009 when they needed nearly a trillion dollars from the taxpayers to pay all the bankers their bonuses.

Pac West looks to be next.

As noted above, so far FDIC has been money source, not taxes.

Not directly taxes.

Just Federal money (the "F" in FDIC is for "Federal".)

The banks left standing are FDIC members.

The cost of being FDIC insured goes up after FDIC bailouts like we've seen in the last month.

The banks left standing recoup those increased fees by increasing various onerous fees on their customers.

Those customers, being taxpayers, are relieved to be screwed by having to pay onerous and increased fees rather than taxes.

So the political wisdom goes.

By the way, five of those left standing - the biggest five in the US (Chase at $3.6 trillion) keep getting bigger since FDIC keeps selling the failing banks to the big five.

Maybe Bank of America will get Pac West.

No matter, there keep getting to be fewer and fewer non-big-five, and bigger and bigger big five.

Those are the ones that are too big to fail so we get to pay for them when they fail directly out of our taxes.

In fact there is quiet talk in Washington about passing a special "too big to fail reimbursement tax" even before the next too big to fail failure so we are ahead of the game.

Rather than being screwed at too big to fail failure time, the taxpayers can be screwed with every pay check.

It is thought that that will hold down unrest.

It is thought that gradual screwing is easier to get away with than big one-time screwing.

Everybody everywhere ought to be happy as a pig in shit to be able to support our wonderful John Gault capitalist system.



Wednesday, May 3, 2023

What Putin Claiming Assassination Attempt Means

 Several months ago I listened to an in-depth discussion of the state of Russia's Aggressive War Crime in Ukraine.

One of the recurring points was that by that time in the aggression it was apparent that the operation wasn't going well for Putin.

A point that the presenter made as to what one of the expected actions to be taken by Putin in the face of his lack of military success was that he would probably launch a campaign of assassination of Western leaders, Zelinsky primary among them but, but by no means confined soley to him.

I had the impression that the presenter felt that it was not unlikely that novichok might even be discovered on door handles at the White House.

Today I am hearing that Putin claims that Zelinsky tried to kill him with a drone.

(Even if it were true, how can the murderer of thousands of Ukranian civilians and the destroyer of most of non-military Ukraine claim foul when someone tries to take him out?)

Putin sycophants in Russia have immediately gone into demanding to kill them all: Western leaders.

I guess Puty is putting the predicted Plan B into operation.



Monday, May 1, 2023

The Singing Robot

While I was writing yesterday's post "What If The Bot Sings With Its Own Voice?" I kept thinking about a Lewis Padgett story - one of my favorite science fiction stories.

Lewis Padgett was the joint pseudonym of the science fiction authors and spouses Henry Kuttner and C. L. Moore.

The story is The Proud Robot.

Gallegher, a brilliant and hopelessly alcoholic inventor/amateur scientist wakes up from a deeply drunken bender to find that he has a new companion: a narcissistic robot that likes to sing.

It sings really badly.

Gallegher does everything he can think of to make it stop singing, take some sort of control of it, or at least, ascertain its function.

The robot foils him on all counts.

Good story.

It ultimately is revealed that the robot is a beer can opener.

Once defrocked the robot becomes quite docile.

I couldn't help but remember that story while I was writing yesterday's post.