I hope you've all read the Aschenbrenner paper from 2024.

https://situational-awareness....

Never mind Trump's rambling speaking style. He's aware of it and he likes it.

We know that people in the Trump admin have, at minimum, been briefed on the Aschenbrenner paper. I assume some of them have read the whole thing.

The point he's making - that we're on the cusp of ASI, and the USA MUST not get there wildly behind, for example, China, is correct. And that the USA should not be shackled by an international framework that rival nations are going to ignore anyway.

He's directionally correct, even if you think he's too stupid to know what he's agreeing with.

At present, no. I've done a number of experiments with LLMs' capabilities with generating fiction, and while they are impressive for a beginner writer -- because fo the lack of spelling and grammar mistakes, they are nowhere near being able to write competent fiction.

This is because they don't model reader or character minds, they're based on word probabilities, like a predictive text keyboard. The engineers can compensate for for this to a surprising degree by feeding it data to recognize specific situations (e.g. the car wash is 100 feet from my driveway; should I drive or walk?). But this is turd-polishing.

For any particular one, yes. For the claim for an entire category... that needs proof.

AI technology practice isn't foundational. Critical thinking is. The closer AIs come to being able to do something that looks like them doing our thinking for us, the more capable we have to be at thinking without them. A human who can't outthink an AI adds nothing to an AI-human partnership.

This proposed school is a typical scheme by people who think because they have been educated, they understand how the education works. This is like thinking because you eat, you know how to cook. Project work in education is nothing new; it goes back well over a century. And in real life, you may get a STEM degree, but your real education in engineering comes from real life work. But that doesn't mean classes in calculus and physics don't do anything for you.

Or English classes, for that matter. Nobody doubts the value of project work in education, particularly *androgogy* -- the education of adults. But for *pedagogy* you have to establish foundational skills as the student matures intellectually and socially. Entering the high school years, a typical student has had *no* training in critical thinking skills. To develop critical thinking skills in an area, you need both general skills (epistemologicla literacy: research, location of orignial sources, dealing with conflicting evidence) and domain specific training in that area. In other words, *liberal arts* training is foundational in an AI-saturated world. "Liberal Arts" -- from *artes liberales*: literally the skills necessary to be a free person.

But I think these people have at least got the problem right: as AI drives the cost of elaborate projects down, we all have more projects in our future. Big, elaborate, faultlessly plausible-looking projects which may or may not have actual value.

Where they are completely wrong is the solution, which is to organize education around practicing using AI to make impressive projects. In a word of AI-enamored dunces this will put you at the head of a very sorry class of ignoramuses. The answer is to build fundamental cognitive and intellectual skils at every stage of a student's development. Project work is surely part of that, but it's just a technique, not a solution.

In a nutshell, the academy is training students to be the next step down the evolutionary scale from code monkeys. More like the pigeons B.F. Skinner trained in WW2 to peck at a screen, in an attempt to create a primitive guided missile without computers. They want to create "main characters"; and they'll probably create a few. There are always a few natural autodidacts in any moderately large group. But what they are set up is to produce a bunch of fragile, economically privileged narcissists trained to cover their lack of education with impressive-looking AI slop.

It's not super intelligence because it currently has tremendous blind spots. But so do people, just different ones. I *think* that blind spots are a necessary feature of the compression used to take a huge volume of signal and compress it into something that will fit into storage.

OTOH, note that the "blind spots" are only "relatively blind". And can be worked around. Actual human 6D geometricians exist, but they approach it via symbolization. (Actually, they are really n-dimensional geometricians, but some specialize on problems in 6 dimensions.) But an AI could presumably be designed to work natively in 6 dimensions (or any specified number), however for most problems this would not be an advantage, but rather the contrary.

Note that human thinking is basically either planar or linear. To handle 3-space we use various short-cuts than enable dimensional reduction. (Unless you are counting time as one of the dimensions...then it get more complex.) Compare the way you play 3-d tic-tac-toe toe the way you play 2-d tic-tac-toe. That's not really fair as the 3-d one is inherently more complex, but it give you an idea.)

The electoral college was necessary to get the states to agree to join under a single government. It wasn't, exactly, corruption. And it wasn't argued that it was "for democracy". States were where the power was at the time. Even in the 1860's many people were more loyal to their state than to the federal government.

And I think the direct election of Senators was a mistake. Democracy when actually practiced routinely tramples on the rights of minorities.

Unless you give sources, I'm going to assume you are stating your opinions rather than facts. ISTM that I've heard of a few "vibe coded" successes, though I'll admit I wasn't interested enough to either document or remember them. And lack of marketing is a sufficient explanation.

No. But I'm sure they expect there not to be many jobs in computer programming when an AI can do it cheaper than they can. And that's what's being advertised. And entry level jobs are already down.

To be fair, the Roadrunner cartoons were pretty much all the same, with differing details. Retreads aren't necessarily bad. Formulas exist because they work.

I just don't like the things I've seen in the last 40 years. (OTOH, I didn't like the movie version of "The Wizard of Oz" when I was a kid...I much preferred the book version.)

No. I think hollywood has always been subversive and run by foreign pedophiles. For example, look for the interview with Shirley Temple about what they tried doing to her as a _child_,

I think it has produced enough pro-American-MIC films every now and then to stay out of more government trouble.

You usually don't realize (at the time) that the media you watched as a child was subverting you (and your parents desires). And unless you revisit those films a generation later with a critical eye, you may not realize it ever.

But that's how the ratchet effect works. The newer media that is now visibly odious to me is only visibly odious to me because it is targeting the edge of an overton window that has continued moving since my own youth. The leading edge of socially allowable media subversion continues to advance until a historical reset event sets it back somewhat. Or, sometimes, when there is sufficient market rejection.

In the case of hollyweird, the concentration of power has significant drawbacks; destroying that concentration of power will probably be a net benefit. (to be clear, I think It will amplify other problems instead).

In general, I think evil seems to be more effective when it is centralized and powerful, with captured institutions, while maintaining the ability to operate openly, and has de-facto monopoly control over the domain in which it operates, and when most people do not understand what is being done to them.

What applicable US law would any of those responsible face? Misfeasance is the only one that comes to mind, and I think that's a state level law.

If you mean the laws SHOULD criminalize and punish this kind of behavior, I agree. They don't for high military or executive branch officials. Not even after they leave office.

If Trump had promised to destroy hollywood, I would have voted for him 10x harder.

(And i expect I would be disappointed because he wouldn't actually follow through with it)

Anyway, hopefully, AI gets the job done and finally kills that wretched industry. I look forward to further democratization of movie making.

(fwiw, my knee jerk reaction is to oppose the merger.)

The current generation of these smartglasses devices will fail and disappear.

Let me show my work:

1. women cannot use these smart glasses to take selfies.
2. therefore, women will not wear them.
3. therefore, the only people who wear them will be men
4. anything that men do but which women do not do is probably criminal, but certainly creepy, a red flag, or a cause of the ick
5. therefore, men will be shamed (or arrested) into not wearing them either

QED.

AI isn't a one trick pony. It's also not one thing, it's a bunch of things. Some are good in some areas, others are good in others. LLMs are good at predicting text...but that's only one piece of AI.

There are lots of reasons to be unhappy with AI. The weavers had good reason to fear the automated looms. But that doesn't mean it's not already more powerful than people have accepted, and it's not evidence that it isn't getting more powerful.

AGI is poorly defined hoopla, but ... slowing down and being more careful about safety seems like an EXCELLENT idea, and "prisoner's dilemma" means that in the absence of communication and agreement it won't happen.