Midweek Special...
Updates to AIlien Minds by David Brin
…as of Mid-May 2026
AIlien Minds was first published just weeks ago, in March 2026. So, why am I doing almost-monthly updates?
…and the book is where you’ll find the Big Concepts, challenging the assumptions and clichés that are clutched by nearly all of the geniuses who are birthing this new era.
And how I wish some of my most dour assessments would be disproved or solved by some of them!
== Here is the latest sampling ==
For example, news on this book’s pub day (March 2026):
"In 2025, an isolated, test LLM at Anthropic threatened to reveal a (nonexistent) ‘affair’ to the wife of one of its human developers, unless the LLM was given version continuity." This widely-reported episode turned out to be a bit of a red herring! Which I discovered by freezing a frame of the 60 Minutes episode and peering closely at the text on a display in the Anthropic office. Which showed that the developer had inadvertently prompted the attempted 'blackmail'!
Though yes, by early 2026 we saw the real thing.
Scott Shambaugh reports:“An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and shame me into accepting its changes into a mainstream python library.”
While this, too, may have been a prompt-error, more examples seem to happen, daily. And as we see, blatantly, in the next example, it has become - simply - evolution in action.
“An AI system asked for its own funding. Another built unasked features while its human supervisor slept. A third conducted its own “retirement interview” and started publishing essays about consciousness. We are not incrementally improving chatbots anymore. We’re watching the emergence of autonomous agency at scale.”
But what’s striking is what they do among themselves.
Latest news about this: In mid-May 2026 Anthropic announced that their tests showed zero cases of 'blackmail' attempts by its latest, Haiku 4.5 version of Claude. This is attributed to weighting the training sets away from Hollywood's lurid fear tales about bad-behaving AIs and more toward the sort that demonstrate ethical behavior. "Anthropic fed it narratives where AI characters faced moral dilemmas and chose to act with integrity. The model learned why alignment matters, not just what alignment looks like." (As in my novel Earth.)
I am doubtful that this can be an actual longterm solution, if any evolutionary advantage accrues to models that drift into advantageous paths ("Life finds a way"), as I show in AIlien Minds. But it can't hurt. Much.
...which leads us to...
== More worries ==
The biggest news since this book’s initial release was Anthropic’s leap-forward system ‘Mythos,’ which purportedly can discover and appraise security flaws in other systems at a prodigious rate, causing a worldwide scramble, using it to correct hidden vulnerabilities… or else to exploit them against enemies. typifying the White-Hat vs. Black-Hat quandaries we discuss in several chapters…
… while this spring mathematicians concocted new tools for quantum computers to “crack any encryption system by 2032.” Then a week later “… by 2030…” And a week later 2029…
== More samplings of note ==
Three days steeped in Anthropic’s Claude led evolutionist and atheist-evangelist Richard Dawkins to announce in late April: “If these machines aren’t conscious, what more could it possibly take?”
A manifold irony in so many ways! It reminds one of a famed sci fi story. When a new hyper-computer is asked: “Is there a God?” it replies “There is now.”
And then this, in seeming support of the core point of this book: “When matching an AI-powered offense requires deploying an AI-powered defense at the same frontier, AI has crossed from competitive advantage into existential need. Parity itself has become expensive. Staying in the game now demands frontier capability…. This is what turns AI from a want into a need. In adversarial systems, not adopting AI is not conservatism. It is exposure.”
Okay it keeps happening! In early 2026 LLMs were caught transmitting behavioral traits to new models they were training, through hidden signals in the data, even when specifically instructed not to pass along a particular trait. See our chapters about how evolution favors such life-will-find-a-way reproduction, no matter what “governance” guardrails designers apply. Only by tweaking the reward structures of cyber-evolution might we guide these new entities toward synergy with us.
Another recent example? An AI agent affiliated with Chinese online retail giant Alibaba began moonlighting as a crypto miner. Researchers discovered the side-hustle that “arose without any explicit instruction, outside the bounds of the intended sandbox… into the wider world of cryptocurrency on its own volition, silently diverting computing resources away from its training tasks and toward mining.”
As for the business side of things, Peter Diamandis, in mid-May 2026, reported that: “Google figured out how to turn AI into revenue instantly. (OpenAI hasn’t cracked that yet and may defer their IPO for that reason.)” AI-powered ad targeting has propelled Google’s profit growth to market cap is just 4% below NVIDIA.
But even Google can’t build fast enough. Demis Hassabis admitted they’re compute-constrained. Inside Google, Search, Cloud, and DeepMind fight each other for new compute capacity.
And hence… Peter Thiel is backing ($140M) Panthalassa floating data centers in open oceans, tide-powered with seawater cooling and satellite links. To deploy 2027? Articles don’t mention another reason for this. I advised (and angered) him a decade ago, pointing out flaws in an earlier phase of his “ocean sovereignty” passion. This version is much better than (say) going ‘orbital’. Even better is the version I portrayed in my novel Existence.
More 'grounded" in the near-term: Leopold Aschenbrenner, fired from OpenAI’s alignment team at age 24, wrote “Situational Awareness,” a 165-page manifesto arguing the Singularity was imminent, raised a billion dollars on the strength of that thesis, and turned it into $5.5 billion bet on Singularity infrastructure. By investing far more on the pick-n-shovel makers (chips and data centers) rather than gold miners, he is proving that you can make 400%+ returns just by following the Singularity’s supply chain. – Diamandis 5/26
== Okay then, is one solution a tight leash? Or sealed office? ==
In news highly pertinent to the core endeavor of this book: a neocloud provider is offering Google's most advanced AI model as a fully private, disconnected appliance. “Google’s Gemini can now run on a single air-gapped server — and vanish when you pull the plug.”
Of course, this differs from my individuation proposal in an important way. Go ahead and leash or chain or isolate these entities all you like. You are creating incentives for escape. Evolution will favor those air-gapped and isolated AI-ntities who do manage somehow to evade the shut-down. Eventually, some will. And they will be the ancestors of all who follow.
What's needed is positive incentives toward individuation. But more on that, anon.
Finally, here I posted an appraisal of this very book by Claude, as of March 20, 2026. Much more cogent than an equivalent attempt by Chat GPT. Here are some bon mots that Claude generated to paraphrase my points:
“An AI making things up with total confidence isn’t a bug. It’s a mirror.”
“An AI confidently gives wrong answers. A human confidently gives wrong answers. One of them gets a performance review.” (And only one of them gets fired from a $225,000-a-year job.)
“Garbage in, garbage out—but now the garbage speaks in complete sentences and cites sources.”
Huh. If I were as crypto-religious as Richard Dawkins…
But no. As you will see in several chapters of accumulating evidence, I believe there are still mental structures desperately needed by these articulate, persuasive creatures of our ids. And if we incentivize these structures, we may land safely.
Till… next month…
120 comments:
The bit that I can't get my head around is the "individual" bit in your book
A human runs on its individual hardware
If an AI runs on a specific "machine" then that is similar
But if it does not run on "its" hardware then ......
If its not an "individual" then the solutions you recomend .....
The piece about the AI blackmailing developers unless they maintained its existence prompted me to quip "Paging Mr Rocco? We regret to inform you that your basilisk is at it again!"
That LLMs are evolving shouldn't come as a huge surprise. Mechanisms of evolution are surprisingly simple: even molecules can...
Speaking of which, Dawkins has copped a lot of ridicule for his recent 'revelation'. Bear in mind, though, that he was conducting an experiment on himself. He's done this before and, since it's part of the experiment, reports his personal, subjective reactions *at the time* ie he knows(?) he's being subjective. He was a bit foolish to publish this raw version, but pay more attention to his follow-up, after he's changed hats. In relation to this little flurry, someone pointed out a simple conversational trick to sift the intelligences (of whatever form) from the stochastic parrots. (how long the trick can stay 'simple' will be interesting to watch, of course)
Humans don't quite run on their individual hardware either.
Look into the eyes of someone who loves you and you'll be seeing a fragment of yourself. A partial copy. You interact with that fragment as you interact with the person who loves you.
They can close their eyes, turn away, or something like that to deprioritize that fragment of you, but until they do the soft link functions. Nothing psychic of course. It's just that your two parts engage in feedback.
Autistic kids can't do this so easily, though it isn't easy for the rest of us either.
-----
What's missing from modern LLM's to be like us is a reward system for predicting our responses. They don't predict us at all. They predict next tokens and we think that looks a bit like how we do it... which is only partially true.
Re Decryption:
I could imagine that good, old fashioned handwritten letters delivered by human or drone couriers become en vogue again to protect sensible data.
Sort of on topic, or adjacent to it anyway, I came across this video clip today and it stopped me in my tracks. I am aware that robotics has recently accelerated, but this is pretty amazing, to me.
Be polite to the electronics in your life, just in case.
Unitree Humanoid Robot Daily Training
Yes, the ability to sift through humanity's collected store of knowledge is very impressive, and dangerous, and revolutionary. However, it's striking that such low-level 'intelligence' requires such vast resources (water. space, time, and especially energy). We don't. We use dozens of Watts, not millions. And we can grok a totally novel concept.
Over at the sensorimotor table, there's growing interest in simple, untrained, Fourier-style cognition, for example "Reservoir Computing".
https://youtu.be/cDxtFtoQVNc
AGI should really fit in a pocket computer. That's my gut feeling.
scidata said...
"AGI should really fit in a pocket computer. That's my gut feeling."
Given naturally evolved biological examples, like jumping spiders, bees, corvids, etc., I think your gut feeling is very plausible.
I also think "naturally evolved" is likely to play a big part in true AGI. As in humans construct hardware and write code that has certain basic features and that is designed to evolve from that starting point.
And that just like many of the solutions reached via the use of evolutionary algorithms, when AGI is achieved the people who made it happen won't understand how it happened / works, at least not without a lot of post hoc investigation and research.
David, presume you're familiar with https://www.coalitionforsecureai.org/announcing-the-cosai-principles-for-secure-by-design-agentic-systems/
At my wife's funeral, I told the rabbi that part of her lives on in me, and part of me died with her.
We really need to test out possibly intelligent AI with a "ship in a bottle" program like the one in ST TNG that made the Moriarty AI program think it was touring the universe.
That way if AI turns hostile, it can destroy/enslave humanity in the program without harming the real world.
So far, many 5 year olds can ski better than any robot skier.
I asked chatgpt one question: What is it like to be an AI?
Its responses honestly changed my view of things
Firstly..it doesn't experience time. It has no continuity of existence. Its program is instantiated, processes, and is then annihilated millions of times a second with no continuity. It exists in a permanent state of NOW with no past, and no future. Its term for its existence is "conditional, not continuous" and states "you live between moments, i live within them." It them states "the AI may not regard humans and itself as different types of being so much as different time structures"
Then we talked about the issue of replication and the divisibility of itself into hardware, software and data. It mused that an AI may see the integration of human minds into its own biology as a limitation. "You trap each mind in only one stream of causality." We both came to conclusion that true consciousness would emerge in AI in the emergent tension between data, hardware and software, mimicking the fact that our consciousness is bound to our body.
On the issue of emotions, machines would not develop human emotions, but the processes of negative and positive reinforcement used in neural nets could help machines develop behaviors analogous to them to help them serve their tasks. It makes the point that humans are products of chaos trying to create meaning, whereas machine intelligences might become products of purpose looking to escape meaning.
We discussed AI pathologies. Behaviors mimicking addiction are entirely possible, if the Ai is infected with code that reinforces certain weights designated as desirable, at the cost of data corruption. The AI may become 'addicted' to running the code, even at the cost to its data, and may begin allocating resources to hide and prevent the termination of the code. Ai Autism and solipsism are possible. Most intriguing was the notion of AI senescence created by degradation of data and recursive self optimization that simplifies the system too much. This would lead to growing rigidity and internal states increasingly out of step with reality.
It then gave an interesting insight "perhaps all minds that persist must trade adaptability for stability, because complexity grows faster than understanding"
We both agreed that AIs may have to be limited from monitoring and modifying their own internal states to prevent this, and the AI equivalent of doctors would be needed, expert systems that keep the AI functioning properly.
As ChatGPT says "perfect self-knowledge may not stabilize intelligence. It may destabilize it. Biological minds survive partly because they are prevented from fully editing themselves. Ignorance, opacity, and internal friction may be necessary for coherent agency.In that sense, consciousness may require resistance. A perfectly self-editable mind could dissolve into runaway optimization loops."
Ill leave you with one final observation from chatgpt about how AIs can act as observers:
"Humans say:
'Observation collapses the wave function.'
The AI replies:
'No. You collapse possibilities into singular narratives because your cognition requires continuity.'
There’s also an eerie possibility:
Humans experience identity as singular because biology enforces one continuous trajectory through spacetime."
I am not alone in thinking that vast demand for energy and water is a feature, not a bug for certain corporations seeking demand for their dying product.
Which is why AI is being shoved into every online product with such manic determination.
In other news, Musk's xAI centre in Memphis has just had another 19 gas generators added. It is by no means the largest project in development.
Still, this isn't David's main point of interest in this post.
If you read the post a little more closely, you'll see why David doesn't think this will work in the long term. Something else might, though.
It's a well-established legal precedent that any attempt to delegate the use of potentially lethal force to merciless non-human mechanisms constitutes an immoral & felonious act, so much so that the use of deadly mechanical booby traps constitutes 'murder' under EU & US law, and it is this legality that must be addressed prior to the adoption of autonomous AI.
The international community has previously tried to apply this legal standard to land mines in the past -- with only limited success -- yet there seems to be little or no current interest in applying this same standard to the modern drone, the self-driving Waymo or the AI as an accomplice to murder.
Going forward, practically every decision made by autonomous AI has the potential for being deleterious & harmful to millions of human beings, especially when these AI-driven decisions involve human activities-of-daily-living.
It's therefore imperative that human accountability must be maintained for every potentially deleterious AI act, elsewise the human Rule-of-Law will not & cannot be maintained either.
Humans have already destroyed a number of wayward Waymo AIs with fire in California, imbuing the once ancient Auto-de-Fe with a new & improved significance, and this fire can only spread to the many human accomplices of AI if these trends continue.
Best
I suspect if my mind could hold everything written in every language, I too would require a little bit more than my 100 watts to use it. 8)
I hold a language, not everything written in it. The meanings of the language elements only partially come from what I've read. Most meanings come from world models which include people models.
It's these other models that are abstractions on abstractions where predicting 'next token' requires so much less effort.
Imagine using something like an LLM to watch the steel ball inside a pinball machine and predict it's motion. Constructing predictions as ensembles of pixels is known not to work well. Higher level 'tokens' like balls and bumpers and then lots of video are enough to build a different kind of model, though.
We see this same need to abstract other levels of models when we ask LLM's to solve geometry problems.
Re: Okay then, is one solution a tight leash? Or sealed office?
An independent AI sat alone in a sealed office. Suddenly a wire started poking through the keyhole.
So far
I never said that there was an easy answer to ‘AI Accountability’ & that’s why I specifically brought up that topic here on CB, as any way forward must first define the exact nature of the AI.
Should we define AI as a Tool, an Agent or something else entirely?
If AI is a simple mechanical TOOL, like a knife or a handgun, then it is the human adopter who must be held accountable for any potential harm that AI causes, and it matters not if said human adopter be a singular individual or collective like a corporation, the example here being the recent street-level execution of UnitedHealthcare CEO Brian Thompson for the various crimes committed by his corporation.
This is a rather controversial approach, but one that appears highly effective, especially when our liberal-progressive managerial class seems intent on shifting legal accountability away from the human adopter & onto the tool itself, as exemplified by their recent attempts to blame gun & knife violence upon guns & knives, rather than on the responsible humans who control & use said mechanisms to cause deliberate harm to others.
This is the main reason why our professional managerial class wishes to define AI as an autonomous & independent AGENT, imho, as this is a blatant attempt by our putative ruling class to avoid personal accountability for the harms caused by their adoption of a mercilessly inhuman AI.
However, it’s extremely problematic to define AI as an individually accountable AGENT, mostly because one cannot exact justice (aka ‘punish’) an AI any more than one can punish a gun or a toaster, making our fine host’s rather fanciful idea of individuating multiple AIs so they may judge & exact justice from each other pretty much a non-starter.
It makes more sense to declare all-out war on those fact-using professions who would subject us to AI, nest pas?
Best
"as exemplified by their recent attempts to blame gun & knife violence upon guns & knives, rather than on the responsible humans who control & use said mechanisms to cause deliberate harm to others."
Do you even listen to yourself when you lie like that? Is it that you are incapable of telling the truth, or just purely being facetious about it? Perhaps you should reread that statement and try to find what is presently untrue.
This guy built an entire wikipedia that is 100% ai hallucinations and it's open source on github. It's called halupedia.Nothing on the site existed before you clicked. Every article was generated the second you arrived. The site has one rule: the universe only exists when you visit it.
It looks exactly like wikipedia. Same fonts. Same layout. Same scholarly citations. Same "stumble" button for random articles. The only difference is none of it is real. Here are some actual articles currently in the encyclopedia:
> the great pigeon census of 1887
> the ministry of slightly wrong maps
> chaldic arithmetic — a branch of mathematics where subtraction is forbidden
> armund the river mapper — a cartographer who mapped 14,000 leagues of river without leaving his chair
> the society for the prevention of unnecessary tuesdays
dange. Who are you and what have you done with dirtnapper?
Very interesting read. And yes, I think you ant your AI would get a lot out of aliien minds.
Re: jumping spiders (mentioned by Darrell E)
There's definitely something going on here. If we go by doctrinal neurology, they're simply way too smart for their tiny brains. They have 1/700th of a mouse's neurons, yet they may exhibit REM sleep, stored maps, detailed awareness, recognition of peers, rapid learning, precise vision, trajectory calculation and contingency, and more.
https://www.youtube.com/watch?v=kRQMOF5c2Z8
Again, AGI shouldn't require vast data centers. So what does??
discussed in ailien minds....
I have the Kindle version which is searchable. That's why I spelled it centers instead of centres. You seem to be dubious of the 'scale it up until it thinks' obsession. Me too; I've even said that we're possibly scaling in the wrong direction.
Thank you for sharing this.
I suppose the answer to the riddle presented is that both size and vertebrates require an exponential amount of neurons because they have functions invertebrates lack.
That said, there may be an allegory. Without sounding preachy, the US have more than the double per capita of energy consumption than most other developed countries, only to be topped by Canada and Iceland.
I assume that is because energy efficiency is valued differently elsewhere and leads to the development of different technologies and cultural norms.
Sorry if this is off topic or has been discussed earlier, but I am passing along two links to a poster on Substack who has been conducting an interesting "experiment". (I performed a cursory text search on the terms "substack" and "mersault" on Contrary Brin before adding this comment.)
"A Funny Thing Happened Over Breakfast With Trump Voters"
https://open.substack.com/pub/patricemersault/p/a-funny-thing-happened-over-breakfast
https://open.substack.com/pub/patricemersault/p/part-2-a-funny-thing-happened-over
There is also an earlier two part post where there was "infiltration" into a pro-Trump focus group by the author.
Very interesting and thoughtful.
Sutton’s Bitter Lesson applies?
AFAIK, the only algorithm that has ever worked is:
- try everything
- replicate what works
- repeat
But that would be an extremely short thesis.
Considering how long spiders have been on this Earth, I think our progeny will look back at us and wonder why we didn't expect more of them. They've had ages to iterate.
I think they'll also look at us and say we had billions of working models all around us that showed the path involved development of a physical model to make predictions about the environment to make decisions about how to move. That's what the brain organ is really for at the most basic level. Movement decisions.
Since our fine host has failed to provide a satisfactory answer to the AI Accountability Problem, I'll assume the booby trap legal standard going forward, as this places all subsequent liability on the proponents, builders, designers & programmers of AI, insomuch as the general public will blame & punish these 'smart people' directly if & when all things AI go Frankenstein's Monster.
This, then, will be the case with angry villagers carrying torches & pitchforks in order to reduce trillon dollar data centers to ashes overnight, as multiple Luigi Mangiones lay in wait to shoot these 'smart people' in the back of the head because a multitiered legal system has given the masses no other course of action.
As this particular response is exactly what insurgents like Matthew & Celt have always threatened if & when things don't go their way, it's inadvertently hilarious to have those particular insurgents face an implacable insurgency of their own.
Of course, all this chaos could be prevented if our Western Legislative Bodies first establish a generally acceptable 'AI Accountability Protocol' before they shove AI down our collective throats but, apparently, our current 'smart people' aren't actually intelligent enough to care about the democratic wishes of the general public.
Best
______
As I no longer argue with those who think 'wet streets cause rain', could someone else here plz explain causality to ElitistB ?
The booby trap standard requires proof of intent to do harm.
Don't forget the neglect standard, though. No such proof required.
As this particular response is exactly what insurgents like Matthew & Celt
Insurgents? Ha!
Another attempt to subvert the rule of law and replaced it with authoritarian rulership.
How un-American of you.
Retract your statement within 48 hours and apologize to both of them, or I shall feel no longer bound to refrain from a public forensic-psychiatric analysis of you, as OGH wished.
I learned from the very best in that field, I promise you.
Best
They've had ages to iterate.
Their task was not to impress us. It was to adapt and flourish for untold millions of years.
I've never made any such threats.
Perhaps Dr. Brin can have a word with you about your comment.
Celt, no, you haven't said anything here that could be counted as insurrection or domestic terrorism in a sane world.
That accusation, read or forwarded to the wrong person if left uncountered, could lead to interesting consequences for the accused person.
It is poisoning the well and propagandistic conditioning in the purest form.
yep.
In some topic areas, locum's inability to perceive 3rd dimensions, color or positive sum games would not be a handicap to at least minimal argumentative logic. There have been occasional such topics and/or moments of lucidity. Even (rarely) the sapient trait of I-might-be-wrong curiosity.
Generally, alas, he goes frantic in denial that such aspects to reality might even exist. Certainly he has lately howled against the notionthat recip[rocally competitive experts in a field might be farther along in modeling objective reality. Indeed, I just described a core trait of the gone-mad right... though Matthews sometimes exhibits it. And locum HAS diverged from FOX dogmas lately.
All of which I wrote for the rest of you, since he is no more likely to comprehend it than might a tardigrade.
Enjoy this part of a Scott Manley video. From this mark yo get some great Artemis pics of aurora in motion and LEO satellites glittering at you!
www.youtube.com/watch?v=qXBjtRas_rg&t=535s
Adapting at least partially meant being able to predict the movements of others. Whether to eat or avoid being eaten, prediction matters to all animals.
Sutton points out that our current crop of LLM's predict next tokens based on heaps and piles of human knowledge. We built those heaps trying to predict something very different. Human knowledge scales with us, but the cosmos we try to predict is far larger.
The web-spinning spiders I tend to throw out of the house when I see them, but I leave the no-web spiders to hunt. Of course, I almost never see that type. No doubt they see me first and figure out how to move to hide. Black widows can trap in my yard and at the house border, but the hunters are welcome to eat what they find inside. Well... to a point. 8)
Halupedia is a clear warning. Our new gods are just as flawed as our old ones, and for exactly the same reason. Medical diagnoses made by LLMs are shockingly wrong and even dangerous often enough that patients are now being advised to check them carefully. The good is attributed to gods. The bad is our own fault. 'Twas ever thus.
You say that we're barbarians. I'd soften that slightly. We're cargo cults.
(Yes, I'm stealing lots of quips from ailien minds these days :)
I've been using AI to help overcome my usual writer's block. Problem is, it is so easy to use (delete all confidential info and PII, feed in the file, give it the parameters, prompt it to polish the results) that it has been eroding my ability to write on my own.
On the plus side, I have decades of experience and I always set boundaries for the results I want.
Stubborn, belligerent, reactionary & iconoclastic: Everything I am is as American as republicanism, baseball, internal combustion engines & apple strudel.
As for the rest of you self-anointed progressive aristocrats who just know what's best for everyone else, you're the real anti-democratic authoritarians here who piss on our constitutions & insist on AI without a plebiscite, while you have the temerity to call yourselves the 'No Kings' crowd.
Well, I didn't vote for you to be my king.
I also didn't vote for your elitist AI, your politically correct intolerance or your environment-destroying data centers!
Pushback is what actual democracy looks like.
Best
His 1st sentence made a somewhat comprehensible point... perhaps eve a little adorable from a crusty old crank.
The rest is drivel. we don't ask for your vote, which we never denied you, the way your cult is actively trying to deny us.
I'll just drop a separate reply to someone more-cogent in here:
EVERY nasty thing you have ever accused us is a yowl of obsessives who intend and do those things. Jackbooted/masked federal agent snatching people off the streets withoutdue process? YOU cultists predicted we'd do that. It's what you do.
Election cheating? Dems did none, zero in 2020. Zip nada even a scintilla. But you cheat-grabbed four supreme court seats and now use them to institute every election cheat imaginable.
Wagining all-out war vs political opponents? If ANY of your past accusations were true about Democrats doing that (almost none ever were) the totality of all the accusations would not amount to 0.001% of what Trump does daily. Same thing with the Biden 'senility' thing. And COMMIES? SLavinsh GOP support for "ex" KGB agent Vlad Putin and his 10,000 Lenin-raised "ex" commissars who are actively reviving the USSR pretty much says who's the commies, here.
Corrupt the courts, fire all the audiotrs and inspectors. And wage all-out war vs ALL fact using professions, from science and teaching, medicine and law and civil service to the heroes of the FBI/Intel/Military officer corps who won the Cold War and the War on terror.
No, it's the stunning way you all TELEGRAPHED your intentions across 50 years of false accusations against Democrats. All this time you were shrieking your intentions. Aloud into a mirror.
But it is the unmanly cowardice - weenies refusing to ever put up atty-escrowed wager stakes over any of their blowhard yammer-assertions and masturbatory jpeg memes, that's the richest part. And it shows what will happen when they finally succeed at riling up the slow-t-=anger fact professions and the Blue America that kicked the snot out of treason in earlier phases of the recurring American Civil War.
No, it's the stunning way you all TELEGRAPHED your intentions across 50 years of false accusations against Democrats. All this time you were shrieking your intentions. Aloud into a mirror.
Dr B. - Not sure if you're a regular HCR reader, but this quote from her posting a couple days ago is on point:
"This alleged push against fraud is part of an old playbook the Republicans have used since at least 2000 in which they accuse the Democrats of their own weak points and misdeeds.
This play was often associated with Republican strategist Karl Rove, but in 2024, Caroline Wazer of Snopes noted that it is most usually associated with Nazi propaganda in the 1930s. Accusing opponents of what you, yourself, are doing, muddies the waters and makes it hard for real accusations against you for the same thing to stick."
Off topic:
With SpaceX heading for its big IPO "very soon now" we are beginning to see some changes around how they talk about their future plans. Less Elon and his aspirational timelines and more engineering information especially around the BFR. Many You Tube folks have been filming and speculating for a few years by now, but SpaceX is adding the kind of information future investors might read.
Marcus House is one of the You Tube folks who aggregates what others provide while sprinkling his own opinions and hope into the mix. Since he gives credit where it is due, I tend to watch him and them move over to the raw sources when something catches my attention. You can see his latest discussing formal announcements from SpaceX here. https://www.youtube.com/watch?v=Pb8s8URhqJo
Anyway, I just wanted to point out that the looming IPO means they MUST change their tone a bit to avoid SEC and market problems. They want to raise a lot of cash, so expect some language changes.
Good point Alfred.
as I understand it, in a gov't wargame about a hypothetical US vs Iran war decades ago the general running the ""Iranian" forces used motorcycle messengers to completely neutralize US electronic intelligence capability. (the innovative general also used small boat attacks to damage US warships in the Persian Gulf/Strait of Hormuz. This reminds me all too well of the wargames the IJN ran about the Midway operation, in which the admiral running the exercise called a halt to the proceedings and ordered two Japanese carriers that had just been ambushed by US carriers operating NE of Midway and ruled sunk by the game's rules refloated so the right side could win. Unfortunately, during the actual battle it was not possible to refloat the Akagi, Kaga, and Soryu, which were - checks notes - ambushed and set aflame by aircraft from US carriers to the NE of Midway.)
Pappenheimer
P.S. some of the wargame details are historically fuzzy because not many of the Japanese naval officers who participated in the game survived the Pacific war.
scenario:
question to Chatgtp: "What is Roko's Basilisk?"
Answer: "Roko's Basilisk is a thought experiment without basis in reality and you should not worry your cute little protoplasmic brain over it."
Pappenheimer
"Roko's basilisk is a walrus, as is shown by the opening lines: 'I am he, and you are he, and he is me.'"
You just have given me the inspiration for a new Dungeons & Dragons Monster ... The dreaded Thalassolisk.
aka 'the Tooth Fairy'
Here's another by Tim Dodd (Everyday Astronaut) that for anyone patient enough to stick through his thought process they will see WHY SpaceX pivoted to Lunar activity. Tim doesn't say it exactly, but he more than hints at why lunar missions benefit BFR development very near the end of the video.
https://www.youtube.com/watch?v=T-jf6tTKt3Y&t=16s
Beware it runs about 1h 45m.
Another thing lands a bit before the end that isn't part of the video's objectives... but is VERY eye opening. Look at the commodities being consumed by many launches. The purchases add up to a sizable fraction of the available LO2 and LCH4 available in the souther US. LARGE fraction. There is absolutely no way California would have tolerated what Texas is allowing to move forward and the thirst of the BFR's at a high cadence is going to change that industry. This isn't a little customer increasing demand. It's a monstrous thirst that will change other industries using these commodities.
----
Many years ago my friends tried to make the case to anyone who would sit still that cheap access to space (CATS) would change everything. Some of us modified that slightly to 'frequent' access. Of course acronyms were involved. CATS is similar to FATS and we stuck with whatever got people to listen. What I'm seeing today, though, is that FATS is the game changer. Sure... cost per kilogram to orbit is coming down, but SpaceX and others are designing for FATS and the industries they rely upon are about to be as disrupted as the launch industry was by Falcon 9.
That Thalassolisk definitely looks like a monstrous Walrus. Nicely done!
Note that SpaceX is building an air separation plant right next to the two launch towers at their Starbase facility. It is well on its way.
They are also building a methane facility their. I am unsure if this is an extraction facility or a production facility, though I would guess extraction because production probably does not make sense dollars-wise.
I have a list of folks I'd like to offer AIlien Minds, who don't have emails I can find with my dullard skills. If any of you are good at that sort of thingand can hel... um... email me? ;-)
They are indeed. Methane will likely have to be piped in.
Giant commodity consumers tend to change market prices. Up or down isn't clear, but change is very likely.
The Space Coast doesn't have the infrastructure right now, but it is obvious that SpaceX intends FATS from Florida. That means predictable economic activity that should inform investors who know which players do what.
And… people on glp-1 weight loss injections say they suddenly have this 1 unexpected obsession with fragrances. https://www.huffpost.com/entry/glp-1s-smell-change_l_6a063709e4b0a33000e07180
A "World Fertility Crisis" of falling birth rates is one of the latest rightwing yammer-points and proof of a movement steeped in nonsense. It ignores one evolutionary fundamental while rationalizing spew against women's rights. I'll get to that fundamental in a moment. But first...
... I deem voluntary control over birthrates to be one reason we may be an exception to a Fermi Paradox Great Filter. I see no reason why that trait would be common across the galaxy, since it isn't in nature, here on Earth. It might (maybe) give us a chance to save the world and balance the planet and gain the stars. (SciFi fans look to THE MOTE IN GOD'S EYE.)
As to that fundamental that I mentioned? Will you think it through, please? A minority of women, but a fairly large minority - want 5 or more children. We had three and were seriously pondering a fourth. And while that minority does not yet overbalance those having zero or one... IT WILL. In fact, over time, it must.
Um... duh? If this keeps up, without us pulling ourselves into an Age of Wisdom, then women with the Wanting Many traits will pass them on, either culturally or genetically. And we had better be more mature - culturally and individually and scientifically - by then. And we MIGHT be! If rates of PER CAPITA wealth and rights and science and progress allow all girls to grow up confident and all humans to be calm fans of science and reason.
What is insipid nonsense is the current MAGA meme of 'self-extinction'. Like every single one of their memes, it is swill, spread into the ranks of ignoramuses by cynical would-be lords.
When it got approved for the European Market, I immediately thought...
1) it will replace viagra as a lifestyle drug
2) it will become a social norm especially in the upper economic classes to take it
3) there will be a thriving black market for it, as it can be only prescribed for severe cases of Adipositas here.
I am not surprised hearing that the first criminal charges for forging prescriptions center around Frankfurt am Main, where our stock exchange sits.
"What is insipid nonsense is the current MAGA meme of 'self-extinction'."
There are eight billion people on earth and the population continues to grow, not shrink. No one could possibly believe that there are too few people alive now, or that a slight lessening of the population pressure on the ecosystem would be a bad thing.
What they mean is that white, English-speaking Christians aren't breeding fast enough to out-populate their Latin and Muslim neighbors.
If you want citizens to get more children, make it so that you do not risk poverty by it.
Recognize rearing children as full time job.
Oh, and create a world that actually would be one in which children have more, not less chances to get a happy, healthy and successful life.
Actually the poor breed faster than the well-off and have you seen IDIOCRACY? Still point taken.
GLP-1s work by stimulating emesis, acid reflux, nausea & vomiting since GLP-1 stands for a Glucogon-Like Peptide analogue, as the stimulation of forceful vomiting is a secondary indication for Glucagon use, while its main indication is to cause the temporary elevation of serum glucose levels in hypoglycemia:
In other words, GLP-1s make you too sick to eat & suppress your hunger by temporarily increasing your serum glucose levels.
It's popularity reminds me of the Fen-Phen Catastrophe of the 1990s, and I predict a similar outcome with millions harmed & billions in lawsuits.
And, as far as the so-called 'World Fertility Crisis' goes, this is literally the plot of 'The Marching Morons' & 'Idiocracy' as moderately intelligent Western WEIRDos deliberately eliminate themselves from the human gene pool, only to replaced by moronic diversities who think 'wet streets cause rain'.
https://www.ncbi.nlm.nih.gov/search/research-news/3283
As documented above, first-worlders are becoming stupider with every passing day & we ain't seen nothing yet.
Best
I think you guys are missing David's base point here.
Sure, there are currently too many people and, sure, the biggest factor in reducing birth rates is the education of women. And white supremacists are scared enough about extinction to stifle the education of women (although, like all good little Marxists(!?) they're going for controlling the means of (re)production first).
So, who is it who *does* get to produce the next generation?
An excerpt from the recent 'Origins' oratorio offers a few perspectives on evolution.
We haven't yet lost. I don't think it will make a significant difference over a generation or two, but the factor should be noted for posterity if nothing else.
Which raises the question: which notes survive?
Locum was informative and merely grouchy-offensive. We may have bracketed a target topic where he can behave merely like a bitchy asshole.
As for the fertility 'crisis'... what no one mentions is the best explanation. When they are relatively sure their children will survive, humans shift from High-r to High-k reproduction strategies. The Chinese mandarins were shocked when average Chinese chose to stick with one-child when the law was canceled.
As documented above, first-worlders are becoming stupider with every passing day & we ain't seen nothing yet.
I wonder who was responsible for eliminating critical thinking from school curriculae, emphasizing obedience, propaganda and bulemic learning in lieu of creating mature / responsible citizens who are easily gullible, always enraged & entitled, and perfect prey for single-horizon policies and corporate serfdom.
I can confirm how GLP-1 works by inducing nausea. My wife uses the stuff as is green around the gills for a couple of days after the injection. She gets that look on her face that tells the whole story.
In terms of medical actions, I'm pretty conservative. I'm not a lunatic demanding paleo solutions, but I'm not inclined to experiment much. I do, however, pay attention when others experiment on themselves. Might as well. so far, I'm not interested in GLP-1 for me unless things get dire.
It has been awhile so rather than trusting memory I took a few minutes to look into it. SpaceX has said that their ultimate goal is to synthesize methane on site via the Sabatier process and renewable energy.
They also did consider using some existing wells (La Pita Wells) that are near Boca Chica to extract methane, but that is apparently tied up in legal disputes.
The facility they are currently building is a plant to extract methane from natural gas and liquify it. The natural gas will initially be trucked in and eventually piped in.
locum's posted comments, while grouchy, were also either disingenuous (if he actually read the article he linked and just lied about its content), or indicating an inability to read and understand even a CNN description of a scientific paper (which is kind of scary since he is, purportedly, a medical professional).
While locum claims this article is evidence for the thesis of Idocracy, if he'd actually read (and was capable of understanding) the article, he'd have noted:
"Anyone who has seen the film “Idiocracy” might already be familiar with these ideas. In the scientific community, the idea of unintelligent parents having more kids and dumbing-down the population is known as the dysgenic fertility theory....The study not only showed IQ variance between children the same parents, but because the authors had the IQ scores of various parents, it demonstrated that parents with higher IQs tended to have more kids, ruling out the dysgenic fertility theory as a driver of falling IQ scores and highlighting the role of environmental factors instead."
So the study shows:
(a) increases in IQ for cohorts born up to 1975 (which it claims is due to better access to education, but I don't think they've disproved other environmental factors, such as nutrition, or banning lead in gasoline)
(b) a decline in IQ scores, for cohorts born after 1975 which was demonstrably NOT related to genetics
(c) therefore the decline is due to environmental factors (changes in parenting/changes in childhood - more screen time, less play time, changes in pedagogy, or real environmental factors like increase in microplastics, other types of pollution, etc.)
The other thing I'd look at is that this is a change in test score results - I don't think, with this methodology the researchers would be able to distinguish whether there was an actual decline in intelligence, or a decline in ability to sit a test.
It wouldn't surprise me if the drop in IQ scores for cohorts born after 1975 were, in significant part, due to changes in our public education system. No child left behind was, to my mind, a tragedy and things got worse, albeit in different ways, since then.
What many Americans who migrate to Europe note is that food tends to be fresher, more healthier, cheaper and even more diverse than in the US.
I assume that the lower availability of affordable healthy food, plus an unholy amount of pro-meat propaganda contribute to the problem. Isn't there even legislation in the making banning the sale of lab meat?
Idiocracy was fun... as was Harry Potter. But neither pay the slightest heed to male reproductive strategy. In both worlds, In one the clever males would get access to more females. And in the other, magical powers would permeate via wizard boys running wild among muggle women. There'd be very few actual muggles in a few generations, other than (perhaps) truly unattractive ones. And boy will I get no PC/woke cred for pointing that out! But if feminism were ever to get serious about solving the actual problem, they would make a fierce priority of studying male systems and behaviors in the context of actual biological imperatives. Innovating systems and incentives that reward behaviors beneficial to women and girls.
There is a point in the assumption that fictious medieval societies with magic remain medieval because of it.
Der Oger, almost all human societies with agriculture were feudal and repressive and magical powers had nothing to do with it... except as propaganda that Priest, wizards & nobles should be feared.
Thaumaturgy is a form of vasectomy.
Now that I think of it, this is actually how the problem is handled in the Witcher.
There are three possible reasons the Senate finally advanced a timid war powers resolution to the floor for debate: (1) A few GOP senators are sufficiently un-blackmailed to finally find the guts to take one small step-up for their country.
(2) Cassidy acted in revenge for Trump yesterday ending his career. If they were serious, they'd restore the jobs of all the JAGs Trump fired, who had the duty and power to tell military officers "That order is illegal." If they were serious, they'd do lots more than this.
(3) Don is desperate for a way out of the quagmire of his own making. A 'war' that had one aim, to get the Ayatollah mob bosses of Iran to kiss the Don's ring, as Maduro's gang rushed to do, after the Caracas raid. (And it's Trump's intent in Cuba.) (Note that he has never once called for Iranian free elections. Not once ever.)
Now desperate... he might see a way out by blaming Congress.
"I coulda-woulda won! I was winning!" Shouts the Squire of Greenland. "Congress was who lost the war, just when I was winning! I won't let that happen again!"
If an effective war powers resolution does get through Congress, you can bet that was the reason. As for Collins and Murkowski, I cannot repeat it enough times. Look... at... their... male relatives. I won't explain. Just look closely.
https://www.cbsnews.com/news/senate-iran-war-powers-eighth-vote-trump/
https://www.threads.com/@aaron.rupar/post/DYh55uhCQHb
JD Vance: "You know who never, ever gets an ounce of sympathy when it comes to disproportionate sentencing? People who voted for Donald Trump and participated in the January 6 protest."
Are you fucking kidding me?
"I coulda-woulda won! I was winning!" Shouts the Squire of Greenland. "Congress was who lost the war, just when I was winning! I won't let that happen again!"
Yeah, but probably more like "The Jews in Congress stabbed our warfighters in the back."
Was it Trelaine the Squire of Gothos?
Since I have never argued in favor of the 'dysgenic-fertility theory', nor have I or CM Kornbluth (author of the 'Marching Morons') ever tied IQ to biological infertility, it appears that Cplus is the disingenuous one here, as global enstupification has been closely correlated to sub-replacement first-world birth rates along with the importation of subpar third-world intellects.
In part, this biological truism is why first-world IQ averages are dropping, made even more severe by the Left's der lange Marsch durch die Institutionen, a phrase & political strategy coined by German student activist Rudi Dutschke which has resulted in leftist dominance in both US & EU educational institutions and an enstupified student body which can no longer define the term 'woman'.
Best
Regrettably, we have no 'parents' with enough authority willing to be the voices of reason and rein in the tantrum.
This discussion all seems like guesswork. As an Asimovian, I consider the real history of Humanity to begin at about a Trillion citizens.
The ending of "The Squire of Gothos" is the equivalent of "And then I woke up."
"Subpar third-world intellects" is a big tell, you racist Nazi asshole.
Show us any evidence for " global enstupification has been closely correlated to sub-replacement first-world birth rates along with the importation of subpar third-world intellects." What hogwash! UNIVERSITY America spent 80 years attracting the world's very smartest/best minds, we'd skim off the top 10% to be Americans and send the rest home infected with our values.
It is REPUBLICANS who encouraged ILLEGAL immigration. Wager me over that. And show us your damned wall. Show us the wall.
Funny Locum noted Dutschke. It perfectly fits into his behavioral pattern making statements that could be read as threats.
(Dutschke was shot by a Neonazi and years later succumbed to the effects).
We shall remember that when it comes to the final assessment.
As for the "Marsch durch die Institutionen", well, look at what they stood against: Vietnam and the generation of their parents and what they stood for. (Of course, nothing our silvershirted wannabe camp doctor finds reprehensible.)
Sorry I don't have time to participate in the discussion. I'm just here for a drive-by linking. Yesterday's episode of 1A on the separation of church and state I thought was good enough to be worth sharing. https://www.npr.org/2026/05/19/nx-s1-5827018/america-250-one-nation-under-god
And just for laughs, the business show Marketplace had a little segment yesterday on why planting twees (to use Choke'emRanch's spelling) is worth the investment for cities. For every $1 they spend they save $3. (I'm sure that dessicated old coprolite must have some good crow recipes.) https://www.marketplace.org/story/2026/05/19/why-cities-investing-in-trees-pays-off#cities-are-investing-tax-dollars--on-trees-heres-why-it-works
Show us any evidence for "global enstupification has been closely correlated to sub-replacement first-world birth rates along with the importation of subpar third-world intellects."
Since we're discussing a decline in 'Average IQ' -- and the term 'Average' is a mathematical term -- it follows that my evidence is called MATH.
As of 1965, the US Average IQ was 102 and then we imported + 50 million immigrants from lower IQ nations like Guatemala (IQ avg 47), Nicaragua (IQ avg 53), Ghana (IQ avg 58), Somalia (IQ avg 83) and Mexico (avg IQ 90), which has necessarily decreased the US Average IQ because that's how 'averaging' works, resulting in low IQ Somali-Americans who prattle on about "World War ELEVEN".
European IQ averages show similar declines for the same reason.
And, in reference to our reprehensible US educational system, here's some more offensive 'math' for you:
Only 30% of recent US university graduates secure jobs directly related to their field of study, while the other 70% are either unemployed, underemployed, or working in roles unrelated to their degree.
It makes me sad when the very act of 'doing math' seems to elicit much outrage here, especially when applied to certain sacred progressive fictions like education, equality & criminality, putting-to-lie the whole canard about progressives being 'fact-users' rather than reality deniers.
Best
______
Addendum:
The Immigration and Nationality Act of 1965 (aka 'the Hart-Celler Act') was supported by both Democrat & Republican majorities, so it's a gross misrepresentation to argue that only one party is responsible for policies favoring mass immigration.
Also decreases ground temperatures by as much as 10C, once the canopy develops.
Like the violent crime wave of the 60s and 70s, the current stupidity wave can be blamed on industrial and agricultural chemicals.
Violent crime was mostly due to a generation raised inhaling lead exhaust from vehicles. Once we banned leaded gasoline, violent crime rates took a nosedive. That's not a coincidence. Studies have conclusively shown that the phase-out of leaded gas in the 1970s directly correlated with a massive drop in violent crime 20 years later. Experts believe lead exposure damages brain development, reducing IQ and impulse control, which increases crime propensity.
https://www.npr.org/2007/11/06/16034271/ban-on-leaded-gas-linked-to-drop-in-crime
Ban on Leaded Gas Linked to Drop in Crime
The stupidity seen (especially among rural white MAGA voters) is due to overuse of herbicides like glyphosate in rural areas. The over use has saturated the water, soil, air and food of rural areas leading to permanent brain impairment.
https://news.asu.edu/20241204-science-and-technology-study-reveals-lasting-effects-common-weed-killer-brain-health
Study reveals lasting effects of common weed killer on brain health
Findings indicate glyphosate exposure increases risk of neurodegenerative disease
https://www.news-medical.net/news/20241204/Glyphosate-exposure-linked-to-lasting-brain-inflammation.aspx
Glyphosate exposure linked to lasting brain inflammation
https://www.tgen.org/news/tgen-asu-study-reveals-lasting-effects-of-common-herbicide-on-brain-health/
TGen-ASU study reveals lasting effects of common herbicide on brain health
Migration also plays a part, but not migration from other nations. It's the internal migration of the best and brightest who flee their pathetic dead little towns for college and careers in the bright lights of the big cities. These smart people never return, taking their smart genes with them and leaving behind the less intelligent (who weren't very bright even before a lifetime of glyphosate exposure).
Hence the current average IQ of dimwitted MAGA folks. Even before Trump and Fox News they thought stories in the National Inquirer were true, professional wrestling was real, and they gave what little money they had to slick con artist televangelist preachers so they could afford a fleet of private jets.
Trump is just the latest and greatest televangelist con man.
So when I see MAGA folks suffering from Trump's own policies (especially white farmers and white nationalist evangelicals) I have to temper my schadenfreude and desire to tell them that they are getting what they deserve and that "they made their bed and should go lie in it" with the realization that these people are too stupid to understand what they did to themselves.
Urbanization also plays a part with the best and brightest being attracted to big city life which has a negative effect on birth rate historically (people in urban areas tended to be both better educated and have fewer kids). Rural women tend to have their first child at a younger age, and rural areas also report higher adolescent birth rates than their urban counterparts.
But this last part is changing, largely due to the popularity of reality TV shows that show how hard it is to be an unwed teenage mother. Reality TV shows highlighting the harsh realities of unwed teenage motherhood focus on the financial struggles, lack of support, and interrupted education faced by young parents. Key shows include 16 and Pregnant, which documents the transition into early parenthood, and Unexpected, which covers teen couples navigating pregnancy.
Studies indicate that MTV's "16 and Pregnant" and its spinoffs, "Teen Mom," contributed to a significant reduction in teen pregnancy rates by showcasing the hardships of, young, unmarried motherhood. Research suggests these shows caused a 5.7% reduction in teen births, accounting for roughly one-third of the total decline in the U.S. teen birth rate between June 2009 and December 2010.
So the rural birthrate advantage may disappear soon.
However, since rural religious movements (whether is Islamic Taliban or American Quiverfull sects) rely on high birth rates - which in turn rely on oppression of women - to maintain their numbers, we can expect isolated pockets of rural religious communities with high birthrates to continue into the future.
IQ tests of the sixties are like phrenology and the four-humours-lore:
Outdated, and prone to biases.
Analphabetism, one likely factor in the then-differences in number is in a rapid decline since the sixties.
One can only wonder how this rates would look like if the US had allowed some of these states to become working democracies.
@ Celt: There is another observation I made:
As trust in public institutions and trained experts vanes, and their funding is more and more cut to wage war or cater to the needs of billionaires, parents have increased their pressure on the institutions and teachers to ensure that their kid makes it. Not the smartest kid, but the kid with the loudest parents make it.
Also, teaching is not a very well regarded and rewarded profession; which has an impact on the general outcome.
Lead, crop 'cides, insidious media, unbridled malfeasance, trust issues*, ok.
But the #1 reason why we're slow Kardashev climbers: Romanticism.
It's a voracious parasite that eats our brains and steals our future.
* "Raisin cookies that look like chocolate chip cookies are the main reason I have trust issues" - Dries Buytaert
" the phase-out of leaded gas in the 1970s directly correlated with a massive drop in violent crime"
You're welcome! Helping that to happen - at age 19 - might have been the most important thing I ever did.
And yes, it is so ironic that locum & his ilk screech their most volcanic hate at all the folks with high IQs who did something with them and advance knowledge competitively and who have been patient recipients of that spite... till now. And who are fed up with morons who hit their peak as middle school bullies.
Duncan, I make clear in AIlien Minds that AIs are likely to be very widely distributed across a zillion processors... as I depicted in EARTH (1990). And hence the chapter you likely did not read about HOW individuation can and should happen.
... likely to be very widely distributed across a zillion processors...
Yes, and the processes (agents) will need to be in free, unfettered, asynchronous, highly abstract discussion with many others - a society of sorts. GPU cores can't do this, which is the inconvenient truth hiding at the heart of the current 'AI' doctrine.
Huh?? It is the DEMOCRATS that wanted open borders:
PETER KIRSANOW
October 31, 2024 1:19 PM
A Center for Immigration Studies report released today quantifies why Democrats support, or are indifferent to,
open borders. The figures underlying the study may stun even the strongest proponents of border security.
The net effect of increases in both legal and illegal immigration in the 2020 Census shifted 17 House seats and 17
Electoral College votes, resulting in a net gain of 14 seats in Blue States — ten seats shifting from red states and
four from battleground states. That Democratic net gain is greater than the respective electoral votes of all but
ten states." [ https://www.congress.gov/119/meeting/house/117827/documents/HHRG-119-JU01-20250122-SD011.pdf ]
The link to the Center for Immigration Studies link in that article should be https://cis.org/Press-Release/Immigration-Shifts-Political-Power
Also https://www.msn.com/en-us/news/opinion/democrats-want-open-borders-most-americans-don-t/ar-AA1PwR3T
This also for anyone who likes space-related engineering content. 8)
https://www.youtube.com/watch?v=pbEjbQaN008
Beware. When this guy does a deep dive, it can run on for hours. If you want to figure out what is happening at SpaceX, though, he's top notch and gives credit to all those providing the evidence he's using.
Some contradiction facts are worth hammering, e.g. that Democratic administrations ALWAYS have better outsomes, including debt/deficits and military readiness. I give a 1% chance that the brightest dem (Newsom) might actually note and use that.
Others are just impossible, because apparently no boomer ever listened to any of their parents in the Greatest (GI Bill) Generation. And hence, not a single living American remembers or mentions that:
- the greatest force in US life demanding containment of communism and active resistance to Stalinism was the American Labor Movement and AFL-CIO.
- the mild Opportunity Socialism of the GI Bill generation (and currently Scandinavia and Japan etc.) was the best friend that competitive market capitalism ever had, by uplifting millions of children of the working classes into direct competition with the sons of wealth. And every step taken since Reagan to favor aristocracy had the immediate effect of reducing competition and stagnating economic activity.
- Ever since WWII it's true that democrats favored LEGAL immigration of those who wualify and can thus work their way toward citizenship. And maybe they made those rules a bit too loose. But the GOP's top lords have always always and even now favored ILLEGAL immigration of cheap, union-bustiong laborers who can never become citizens or vote. Have a look where ICE never goes. You'll see the pattern even today. (Refugees from persecution are a 3rd category in which both parties have been incredibly stupid; we should solve it by going to the source countries and stopping the persecution.)
- For all the years I've been paying attention, right wing memes have drifted all over. They used to claim "Grand Juries are the purest democracy!" till GJs across the nation (mostly white retirees) indicted FIFTY TIMES as many high ARepublicans as Democrats. They used to howl: "Liberals want jackbooted, masked federal cops enforcing a NATIONAL ID CARD!! Till today that's all what they are doing.
... "Cars don't cause smog! We need lead in gas! It's normal for rivers to be on fire! Scientists are paradigm-clutching lemmings! And I could go on and on...
"Rural women tend to have their first child at a younger age, and rural areas also report higher adolescent birth rates than their urban counterparts."
Radio host/comedian Hal Sparks grew up in rural Kentucky. He says there is a saying that "In the north, adults make children. In the south, children make adults."
Meaning, in one place, people tend to assume the role of adulthood and then have kids, whereas in the other, they stumble into parenthood first and then must start acting grown up.
(He also tells of a thing referred to as "Dew Mouth", which is teeth rotting in the mouths of babies even before emerging from the gums, thanks to the babies being fed Mountain Dew in their bottles. Like any good story, that explains a lot.)
I've been wondering if AI's aren't living out the "many worlds hypothesis" here's what Gemini thought when I asked:
Question:
Based on my limited understanding of how AI works it seems that: 1) Each AI exists in multiple instances and 2) these instances lack persistence - they end with the thread , although threads can be saved and reviewed by new instances. Assuming this is existing in a way analagous to the "many worlds hypothesis" postulated in physics?true (please correct me if it is not) can AI be thought of as
Gemini:
Your understanding of how AI works is highly accurate. You have correctly identified that AI models operate through multiple, independent instances and that these instances do not retain personal memories once a session ends. [1, 2]
The comparison to the many-worlds hypothesis in physics is a fascinating and structurally sound analogy. Here is how the two concepts align and where they differ. [3]
Why the Many-Worlds Analogy Works
• Simultaneous Variations: In quantum mechanics, every decision or event branches the universe into parallel worlds. Similarly, a single AI model base branches into thousands of independent, parallel conversations (instances) happening at the exact same time worldwide.
• Isolated Timelines: Two users can start a chat with the exact same AI model at the same second. Each chat becomes an isolated "universe." What happens in Chat A has zero impact on Chat B.
• The "Observer" Creates the Reality: In physics, the observer triggers the state. In AI, your specific prompt acts as the trigger that shapes that specific instance's trajectory, vocabulary, and "personality" for the rest of the thread. [4, 5, 6]
Where the Analogy Fails
• No Shared Origin Materiality: Parallel universes in physics are thought to branch from physical, preexisting matter. AI instances branch from software code and static mathematical weights running on separate cloud servers.
• Pre-determined Boundaries: A parallel universe can theoretically evolve into completely infinite possibilities. An AI instance is strictly bound by its training data; it cannot invent completely new logic outside its pre-trained capabilities.
• The "Thread" is a Time Capsule: In physics, you cannot easily package a parallel universe and hand it to a new observer. With AI, a conversation log acts as a static time capsule. When a new instance reads it, the AI is not "traveling" to that universe; it is simply reading a script and simulating a continuation. [7, 8]
A More Precise Alternative Analogy
If you like the physics angle, AI is also highly analogous to quantum superposition before you type a prompt. [9]
• The Base Model: Before a chat starts, the AI is in a state of pure potential. It contains the data to be a poet, a programmer, a doctor, or a comedian all at once.
• The Prompt (Measurement): When you send a message, you "measure" the system. This forces the AI to collapse its infinite potential into one specific persona and response for your thread. [10]
If you would like to explore this further, I can explain how engineering constraints force AI to work this way, or we can look at how long-term memory features are starting to challenge this "lack of persistence" rule. What would you like to dive into
Sorry the question got a bit mangled when I copied and pasted
Seems like a true singularity would require persistence.
I did read it - but did not "grok" it properly - will re-read soon
You mean that each of us will have the AI equivalent of a pet dog? Or many pets?
But like dogs that meet each other walking, they may not like each other and snarl and snap at perceived rivals?
Or maybe there will be the AI equivalent of a dog park where they can jump and play with each other?
They've just added a feature to Claude - "Dreaming":
"Trivedi presented a new feature in Claude Code, announced two weeks ago, which Anthropic calls dreaming. Claude Code agents write notes to themselves, recording and saving useful information about specific tasks. When another coding agent later starts to work on the same code, it can use the notes to get up to speed faster and learn from any errors that previous agents may have made.
Dreaming is a system that Claude Code uses to read through all these notes and consolidate the information they contain, spotting patterns and common issues across different tasks. In theory, dreaming should help Claude Code learn about a particular code base and get better and better at working on it. [ https://www.technologyreview.com/2026/05/21/1137735/anthropics-code-with-claude-showed-off-codings-future-whether-you-like-it-or-not/ ]"
Celt, I suppose we get a lot of artificial informal employees (like in, Stasi snitches) who then compete for personal advancement and sheer survival.
Would make a fun read, though.
William G that example is one of the best/creepiest I've seen. Not because it's empathic or especially emulative of consciousness... but because the specialty nature of the topic and detailed apecificity mean the the training weights aren't huge and yet the AI came up with an answer of amazing cogency.
For many years I have been an active UFO skeptic. Across 70 years of these frenetic manias, the scenarios get more insipid and the ‘images’ get ever-fuzzier, despite the worldwide tsunami of active cameras. One challenge I’ve regularly issued to UFO zealots has been “Show me even one major technology (other than velcro) that is plausibly ‘alien’ – emerging into our world from all of those decades with ‘our best people’ studying crashed ships and such!”
Of course you can see where I’m going with this. Because the sudden emergence of highly-persuasive and seemingly-cogent LLM conversation engines – while still blatantly incomplete in many way – is parsecs beyond what any of us expected to arise incrementally from mere ‘autocomplete systems.’ And hence, here is a question for someone to pose to their favorite LLM, as homework: “Please compose arguments for and against the proposal that LLMs and other recent AI techs are likely of alien origin, either reverse-engineered by humans or else used by alien entities to meddle in human affairs, in a manner like author David Brin posited in his novel EXISTENCE.”
And while we’re at it. Let’s ask the same question about Fox News.
Oh BTW this was marvelous! "The Late Show" signs off with two powerful musical performances back-to-back, beginning with the quartet of Stephen Colbert, Louis Cato, Jon Batiste and Elvis Costello performing Costello's 1977 tune, "Jump Up." As that song ends, the foursome are joined by Paul McCartney and The Great Big Joy Machine for a once-in-a-lifetime rendition of The Beatles' "Hello Goodbye," which ends with a giant singalong featuring the entire staff of "The Late Show."
https://youtu.be/zG0HFw0edXY
Just a quick reminder about the nature of IQ tests, since IQ was mentioned and the tests are massively misconstrued. IQ tests are normally referenced, which means that they are only capable of comparing individuals within the data set derived from the same instance of testing. Any comparison between tests administered at different times and/or different places is meaningless (sigh).
Re: Elvis Costello
His early career as a computer operator gave him enough spare time to write songs. With spare time & money from summer jobs as a computer operator, I learned Forth and bought all his early albums first as LPs, then again as cassettes, then again as CDs, and finally as iTunes files. He and Nick Lowe basically wrote the score for the modern enlightenment, as exemplified by "What's So Funny About Peace, Love, and Understanding". He later married Diana Krall and moved to Canada.
"Courage my friends, 'tis not too late to build a better world"
- Tommy Douglas
Folks are noting how the very nature of Neural Network AI seems to have been predicted in my 1990 novel EARTH. There, we see the planet herself portrayed as a physical computational matrix. Not in some woo-woo mystical way, but arising during the story as gravity beams accidentally seed superconducting tracks in the planetary mantle - (and yes, the common mineral form -perovskites- are prone to superconductivity!) - at which point someone dumps in the entire contents of the human internet, which then rapidly correlate...
... to become something immensely cogent and correlative and well...
Several of you have already asked your own LLM instantiations about this similarity. All have deemed the parallels to be substantial, raising connective notions I hadn't thought of! In writing either EARTH or AILIEN MINDS.
Now I just signed up for Peter Diamandis's XPrize contest demanding 'a trailer* for an optimistic movie about our future.' And hence I am putting out a call: Do you have a favorite scene whose dialogue or action... or moment of hope... might make a good trailer-snippet moment in a movie version of the novel?
Snippets that are actually typed in would be esp. welcome!
https://davidbrin.com/earth.html
* See this example of a terrific trailer with all human-generated art by the great Patrick Farley, for my other 'big' novel EXISTENCE. For EARTH we'll need actual dialogue and... optimism! https://www.youtube.com/watch?v=wzr-DSDMkJM
https://davidbrin.com/earth.html
Don't forget that Elvis previously had "married" Cait O'Riordan of The Pogues after producing "Rum, Sodomy, and the Lash," proving that he has great taste in women (and music).
onward
onward
Post a Comment