Actually the race-realism use last week, combined with this one, makes me realize that for them it’s just a fancy way of saying “world-view” [or what they consider to exist, and be true, which is not the craziest use of the word, but I would say unhelpful, and probably a small in-group marker].

It’s just a way of calling biases/prejudice legitimate.

And you know what, inasmuch the models have a “world-view” it IS annoyingly american in many ways. (at least the wrong kind of american.)

Also used for practicing my Japanese, I would say the usefulness was definitely not 0, if nothing else with the correct settings it was daily practice for the Japanese scripts (kana/kanji).

And it’s best It would definitely not bring you even to reading fluency, and was only good if you were supplementing your study with other language acquisition forms (like for example, in my case, living in Japan).

The examples were often stilted, and the accepted answers overly rigid, for sentences which weren’t necessarily realistic.

I think some of the worst aspects of the gamification were:

• Choosing easy exercises as a safe source of points, to not lose the streak. (perverse incentive)
• Essentially by setting a target, encouraging to only meet a daily points streak, and not necessarily go further for a given day. (perverse incentive)
• Tile matching to english, again with overly rigid accepted answer. (trying unhelpfully hard to map Japanese to english)

Let my streak/subscription lapse when it stopped being useful (got better reading exercise elsewhere), and uninstalled when they introduced AI shit.

Also I think there’s enough manipulation fantasy in HPMOR, and enough lack of agency from Hermione, that it qualifies—in it’s own way—implicitly as being erotic.

Also I realize the word often get’s used fuzzilly that way even in general, but I suspect what they mean is epistemology not ontology.

You have to wonder about that Tim traveler; Merlin?

For reference the open-source project appears to be OpenCog, founded by “Ben Goertzel” who at least up until 2010 held the title of “Director of Research” at SIAI, the relation stopping because he wasn’t a true believer in doom.

Honestly even the original paper is a bit silly, are all game theory mathematics papers this needlessly farfetched?

I can’t imagine anyone really subjecting themselves to reading all that, I’m delighted for them though, or distraught that it happened…

It is a bit sad how Yarvin frontlines his “victory”, by quoting some extruded text, but in context—he is somehow kind enough to provide, maybe he didn’t bother reading all of that either—it’s just some fence-sitting big nothing, i doubt the claims that this produces any form of “red-pilled” Claude.

(I’m not sure what I expected, but it truly was a dead dove.)

🫂

I think actually listening to people remains important. But you’re only truly listening to someone when you try to understand when they lie or the ways they can be wrong.

Assuming 100% good faith is not actually the most empathetic way to engage with a person.

A get-smart-quick scheme, with an absurd amount of occult cargo-culting of scientific discourse.

~~In the dead of night, knocking on the door~~

My feeling has gotten that I prefer the business executive empty vs the LLM empty, at least the first one usually expresses personality. It’s never entirely empty.

Screaming at the void towards Chuunibyou (wiki) Eliezer: YOU ARE NOT A NOVEL CHARACTER, THINKING OF WHAT BENEFITS THE NOVELIST vs THE CHARACTER HAS NO BEARING ON REAL LIFE.

Sorry for yelling.

Minor notes:

But <Employee> thinks I should say it, so I will say it. […] <Employee> asked me to speak them anyways, so I will.

It’s quite petty of Yud to be so passive-aggressive towards his employee insisted he at least try to discuss coping. Name dropping him not once but twice (although that is also likely to just be poor editing)

“How are you coping with the end of the world?” […Blah…Blah…Spiel about going mad tropes…]

Yud, when journalists ask you “How are you coping?”, they don’t expect you to be “going mad facing apocalypse”, that is YOUR poor imagination as a writer/empathetic person. They expect you to be answering how you are managing your emotions and your stress, or bar that give a message of hope or of some desperation, they are trying to engage with you as real human being, not as a novel character.

Alternatively it’s also a question to gauge how full of shit you may be. (By gauging how emotionally invested you are)

The trope of somebody going insane as the world ends, does not appeal to me as an author, including in my role as the author of my own life. It seems obvious, cliche, predictable, and contrary to the ideals of writing intelligent characters. Nothing about it seems fresh or interesting. It doesn’t tempt me to write, and it doesn’t tempt me to be.

Emotional turmoil and how characters cope, or fail to cope makes excellent literature! That all you can think of is “going mad”, reflects only your poor imagination as both a writer and a reader.

I predict, because to them I am the subject of the story and it has not occurred to them that there’s a whole planet out there too to be the story-subject.

This is only true if they actually accept the premise of what you are trying to sell them.

[…] I was rolling my eyes about how they’d now found a new way of being the story’s subject.

That is deeply Ironic, coming from someone who makes choice based on him being the main character of a novel.

Besides being a thing I can just decide, my decision to stay sane is also something that I implement by not writing an expectation of future insanity into my internal script / pseudo-predictive sort-of-world-model that instead connects to motor output.

If you are truly doing this, I would say that means you are expecting insanity wayyyyy to much. (also psychobabble)

[…Too painful to actually quote psychobabble about getting out of bed in the morning…]

In which Yud goes in depth, and self-aggrandizing nonsensical detail about a very mundane trick about getting out of bed in the morning.

A fairly good and nuanced guide. No magic silver-bullet shibboleths for us.

I particularly like this section:

Consequently, the LLM tends to omit specific, unusual, nuanced facts (which are statistically rare) and replace them with more generic, positive descriptions (which are statistically common). Thus the highly specific “inventor of the first train-coupling device” might become “a revolutionary titan of industry.” It is like shouting louder and louder that a portrait shows a uniquely important person, while the portrait itself is fading from a sharp photograph into a blurry, generic sketch. The subject becomes simultaneously less specific and more exaggerated.

I think it’s an excellent summary, and connects with the “Barnum-effect” of LLMs, making them appear smarter than they are. And that it’s not the presence of certain words, but the absence of certain others (and well content) that is a good indicator of LLM extruded garbage.

I guess my P(Doom|Bathroom) should have been higher.

Pessimistically I think this scourge will be with us for as long as there are people willing to put code “that-mostly-works” in production. It won’t be making decisions, but we’ll get a new faucet of poor code sludge to enjoy and repair.

The power, of words:
Is all but naught, if not heard.
And a bot, cannot.

I’ll gladly endorse most of what the author is saying.

This isn’t really a debate club, and I’m not really trying to change your mind. I will just end on a note that:

I’ll start with the topline findings, as it were: I think the idea of a so-called “Artificial General Intelligence” is a pipe dream that does not realistically or plausibly extend from any currently existent computer technology. Indeed, my strong suspicion AGI is wholly impossible for computers as we presently understand them.

Neither the author nor me really suggest that it is impossible for machines to think (indeed humans are biological machines), only that it is likely—nothing so stark as inherently—that Turing Machines cannot. “Computable” in the essay means something specific.

Simulation != Simulacrum.

And because I can’t resist, I’ll just clarify that when I said:

Even if you (or anyone) can’t design a statistical test that can detect the difference of a sequence of heads or tails, doesn’t mean one doesn’t exist.

It means that the test does (or can possibly) exist that, it’s just not achievable by humans. [Although I will also note that for methods that don’t rely on measuring the physical world (pseudo random-number generators) the tests designed by humans a more than adequate to discriminate the generated list from the real thing.]

Even if true, why couldn’t the electrochemical processes be simulated too?

• You’re missing the argument, that even you can simulate the process of digestion perfectly, no actual digestion takes place in the real world.
• Even if you simulate biological processes perfectly, no actual biology occurs.
• The main argument from the author is that trying to divorce intelligence from biological imperatives can be very foolish, which is why they highlight that even a cat is smarter than an LLM.

But even if it is, it’s “just” a matter of scale.

• Fundamentally what the author is saying, is that it’s a difference in kind not a difference in quantity.
• Nothing actually guarantees that the laws of physics are computable, and nothing guarantees that our best model actually fits reality (aside from being a very good approximation).
• Even numerically solving the Hamiltonians from quantum mechanics, is extremely difficult in practice.

I do know how to write a program that produces indistinguishable results from a real coin for a simulation.

• Even if you (or anyone) can’t design a statistical test that can detect the difference of a sequence of heads or tails, doesn’t mean one doesn’t exist.
• Importantly you are also only restricting yourself to the heads or tails sequence, ignoring the coin moving the air, pulling on the planet, and plopping back down in a hand. I challenge you to actually write a program that can achieve these things.
• Also decent random-number generation is not actually properly speaking Turing complete [Unless again you simulate physics but then again, you have to properly choose random starting conditions even if you assume you have a capable simulator] , modern computers use stuff like component temperature/execution time/user interaction to add “entropy” to random number generation, not direct computation.

As a summary,

• When reducing any problem for a “simpler” one, you have to be careful what you ignore.
• The simulation argument is a bit irrelevant, but as a small aside not guaranteed to be possible in principle, and certainly untractable with current physics model/technology.
• Human intelligence has a lot of externalities and cannot be reduced to pure “functional objects”.
  • If it’s just about input/output you could be fooled by a tape recorder, and a simple filing system, but I think you’ll agree those aren’t intelligent. The output as meaning to you, but it doesn’t have meaning for the tape-recorder.