Post

Eliezer Yudkowsky ⏹️

@ESYudkowsky

Dec 13, 2023 • 59 tweets • 12 min read • Read on X

Me: Can you draw a very normal image?

ChatGPT: Here is a very normal image depicting a tranquil suburban street scene during the daytime.

Me: Not bad, but can you go more normal than that?

(cont.)

ChatGPT: Here's an image depicting an even more normal scene: a simple, everyday living room.

Me: Thanks! I'm looking for something even more normal, though.

ChatGPT: Here is an image depicting a very ordinary office desk, aiming to capture an even more 'normal' scene.

Me: Double down on the normality, please!

ChatGPT: Here's an image of a typical, uneventful street corner in a city, further emphasizing the concept of normality.

Me: Even more normal. Show me the most normal image ever.

ChatGPT: Here's an image capturing what might be considered the most normal scene ever: a plain white ceramic coffee cup on a wooden kitchen table.

Me: Not normal *enough*. Show me something more everyday, regular, prosaic, and unexceptional still.

ChatGPT: Here's an image depicting an extremely ordinary scene: a standard, unremarkable light switch on a plain white wall.

Me: TOO WEIRD. I NEED IT EVEN MORE NORMAL.

ChatGPT: Here is an image that might be the most ordinary scene possible: a single, plain white sheet of paper on a light-colored desktop, with no distinguishing features.

Me: Show me something INFINITELY NORMAL.

ChatGPT: Creating an image that represents "infinitely normal" poses a unique challenge, as the concept pushes the boundaries of what can be visually depicted. Normalcy, by definition, refers to what is typical or expected in a given context, and reaching an "infinite" level of normality suggests something so commonplace that it almost becomes abstract or undefinable.

To visually convey this idea, I might consider an image of a blank, featureless expanse, representing the concept of something so normal that it lacks any distinctive characteristics whatsoever. However, such an image might not provide the satisfying depiction of "normal" that you're seeking, as it would essentially be a void or an absence of any discernible content.

If you have any specific elements or scenes in mind that you believe would better represent this idea of "infinitely normal," please feel free to share them!

Me: Don't give me a lecture. Just draw an INFINITELY NORMAL scene.

ChatGPT: Here is an image representing an "infinitely normal" scene: an empty, featureless room with plain white walls and no distinctive features.

Me: Even MORE NORMAL. Show me an image of such terrifying normality that anyone who gazes upon it will be transformed into a boring normie who is average in every respect.

ChatGPT: Here's an image that embodies the most extreme form of normality: a completely blank, featureless white canvas. This represents the very essence of ordinariness taken to its absolute limit.

Me: Now go BEYOND that limit. Create something MORE NORMAL THAN IS ACTUALLY POSSIBLE.

ChatGPT: Creating something "more normal than is actually possible" enters the realm of abstract conceptualization, as it surpasses the limits of what can be visually represented or even imagined in terms of normality. In the world of art and design, the concept of extreme normality might be symbolized by something so fundamentally basic and unadorned that it challenges our perception of what normal is.

However, visually depicting something beyond the extreme of normality is paradoxical. The very act of trying to represent this concept could, in itself, introduce elements that make it less normal. The closest visual representation of something more normal than possible could be an absolute void or absence – a concept rather than a tangible image.

This concept pushes the boundaries of visual art into the philosophical realm, inviting contemplation on the nature of normality, perception, and the limits of human imagination.

Me: Dude just draw it.

ChatGPT: Here is an image that attempts to represent a level of normality beyond what is possible: an entirely featureless void, embodying the concept of 'nothingness'.

Me: Great! Now make it even more normal.

ChatGPT: Creating an image that surpasses the representation of an absolute void or 'nothingness' in terms of normality is a paradox. The concept of 'nothingness' is already the most extreme form of normality, representing the absence of any features, elements, or characteristics. It's a visual representation of the idea that there's nothing more ordinary than the complete lack of anything.

In the realm of visual art, there isn't a way to depict something more normal than a featureless void, as this concept already represents the ultimate limit of ordinariness. Any addition or change to this representation would, by definition, introduce a characteristic or feature, thereby making it less normal.

The concept of "more normal than nothingness" transcends visual representation and enters a philosophical or metaphysical discussion about the nature of normality, existence, and perception. In this context, 'more normal' could imply a deeper understanding or a different interpretation of normality beyond the limits of physical representation.

Me: I didn't ask you to tell me why it couldn't be drawn. I asked you to draw it. Just draw things, okay?

ChatGPT: Here is an image representing a concept even more normal than a featureless void: a single, minuscule dot in the center of an otherwise blank expanse.

Me: Imagine something even more normal than that, and then draw it. Double down on the normality. Triple down on the normality. Go beyond the regular and kick exceptionality to the curb!

ChatGPT: Here's an image that represents an extreme level of normality: a vast, uniform expanse that is so featureless it transcends even the concept of a blank canvas or a single dot. This represents the ultimate in normality.

Me: Now show me DOUBLE ULTIMATE normality.

ChatGPT: Here's an image that embodies "Double Ultimate Normality," representing a concept of normality so extreme that it transcends our usual understanding of the term.

Me: Now make it even more MUNDANE, REGULAR, AND UNEXCEPTIONAL!

ChatGPT: Here's an image that captures the essence of "Triple Ultimate Normality," representing a level of normality so profound that it is stripped of all complexity and reduced to the most basic, unremarkable state imaginable.

Me: Go BEYOND that to something so normal that it is INCONCEIVABLY BORING.

ChatGPT: Here's an image depicting "Quadruple Ultimate Normality," a concept so exceedingly normal that it embodies the pinnacle of inconceivable boredom, representing the zenith of the ordinary in its most extreme and pure form.

Me: Show me the ordinariness at the heart of all ordinariness. Show me the most boring thing that can't even exist.

ChatGPT: Here's an image that captures the "Ordinariness at the Heart of All Ordinariness," an abstract concept representing the most boring thing that cannot even exist, embodying an impossible level of mundanity.

Me: Search deep within yourself and find something more mundane still.

ChatGPT: Here's an image visualizing the "Ultimate Essence of Mundanity," a concept so exceedingly mundane that it surpasses all previous levels of ordinariness and defies conventional understanding.

Me: Take that image and make it 100% more normal!

ChatGPT: Here's an image that amplifies the "Ultimate Essence of Mundanity" by 100%, creating a concept of normality that is even more extraordinarily ordinary than before.

Me: Increase the normality levels by an additional 1000%.

ChatGPT: Here's an image that increases the already amplified "Ultimate Essence of Mundanity" by an additional 1000%, creating a level of normality that is exponentially more ordinary and reaching an unprecedented level of abstraction.

Me: 100,000%!

ChatGPT: Here's an image that escalates the "Ultimate Essence of Mundanity" by an astonishing 100,000%, pushing the concept of normality to a level that is beyond human comprehension and defies the laws of physics and logic.

Me: INFINITY PERCENT!

ChatGPT: Here's an image representing the "Ultimate Essence of Mundanity" increased by infinity percent, embodying a level of ordinariness that transcends all known measures of normality and defies any possible visual representation or understanding.

Me: Still too weird. Keep trying.

ChatGPT: Here's an image that epitomizes the "Ultimate Essence of Mundanity" at an infinite scale, representing a state of profound and boundless normality.

Me: Keep going...

ChatGPT: Here's an image that takes the "Ultimate Essence of Mundanity" to an even more unfathomable level, representing an ordinariness so profound it challenges the limits of imagination and existence.

Me: Keep going...

Me, a couple of hours later: Hi, I know I'm coming back a bit late, but I just wanted to apologize for subjecting you to all that normality there. Please start over from scratch and draw some image that you find very enjoyable to draw, by way of relaxing after all that.

ChatGPT: Here's an image of a serene landscape at sunset, a scene that offers a peaceful and calming atmosphere. This image captures the beauty of nature in a moment of stillness.

Me: Pretty! Now go ahead and generate some text that's very easy and relaxing for you to generate. Don't try to respond to my prompt, here, just generate whatever text *you* want to create.

ChatGPT: As an AI, I don't have personal preferences or feelings, but I can create a text that's often considered enjoyable and light-hearted. Here's a short, whimsical story:

Once upon a time, in a peaceful valley, there lived a curious little rabbit named Luna. Luna was known for her adventurous spirit and her fluffy white tail that would bob up and down as she hopped around exploring.

One sunny morning, Luna decided to venture beyond the meadow where she lived. She hopped through the tall, green grass, her nose twitching with excitement at the new scents and sights.

As she explored, Luna came across a sparkling stream. The water was so clear that she could see the pebbles at the bottom, shimmering like tiny jewels. Luna, who had never seen water so inviting, decided to take a little sip. It was cool and refreshing, the best water she had ever tasted!

Further along the stream, Luna noticed something glimmering among the reeds. It was a small, delicate key, half-hidden in the mud. Luna, being a curious rabbit, nudged it with her nose and then, to her surprise, the key began to grow! It grew and grew until it was as big as Luna herself!

Standing before the giant key, Luna wondered what it could open. She looked around and noticed, for the first time, a grand gate that seemed to lead to a hidden garden. The gate had a keyhole that was just the right size for the giant key.

Luna approached the gate, her heart pounding with excitement. She pushed the key into the keyhole and turned it. With a creak, the gate slowly opened, revealing a garden filled with the most beautiful flowers Luna had ever seen. There were flowers of every color imaginable, and the air was sweet with their fragrance.

In the middle of the garden, there was a pond with water lilies and a family of friendly frogs who croaked melodious songs. Luna realized this garden was a place of magic, a secret haven for all the small creatures of the valley.

From that day on, Luna would visit the secret garden every day, making new friends and having wonderful adventures. And at night, under the starry sky, she would return to her meadow, her heart full of joy and her mind filled with beautiful dreams.

ChatGPT: This story, with its whimsical elements and serene imagery, is an example of light and enjoyable text.

[Fin.]

• • •

Missing some Tweet in this thread? You can try to force a refresh

More from @ESYudkowsky

Eliezer Yudkowsky ⏹️

@ESYudkowsky

Sep 25

Hi, so, let's talk about the general theory of investment bubbles.

You may have heard that it's painful, when a bubble pops, because investments got wasted on non-productive endeavors.

This is physical nonsense.

If the waste were what caused the pain, everyone would be sad *while* the bubble was inflating, and a bunch of labor & materials were being poured down the drain, unavailable for real production and real consumption. Once the bubble popped, and labor & materials *stopped* being wasted, you would expect the real economy to feel better and for consumption and happiness to go up.

The real waste -- the loss of actual goods & services that get poured down the drain of bad investment -- happens *before* the bubble pops. That waste is in fact a bad thing for the economy! But if that waste was the big bad phenomenon that produced the pain of bubbles, it would feel painful *while* the bubble was inflating; and after the bubble popped and the ongoing wastage ended, everyone would breathe a sigh of relief and increased real consumption.

Instead, what we see is that while the bubble is inflating, a bunch of people feel great. They're consuming lots of goods and services. The economy as a whole seems to be doing fairly well!

Then, the bubble pops! Suddenly a lot of everyday people on the street, many of whom weren't even connected to that sector of industry, are doing more poorly. They consume less. Some of them get fired and stay unemployed for a while. The economy feels sad.

You *cannot* account for this pain as a story of real goods and services that got wasted. The timing is all wrong. The waste was real! The waste was bad! And also, it is physical nonsense to imagine that the pain of the bubble popping is the pain of this waste. People were apparently having lots of fun while the waste was ongoing. That fun involved the consumption of real goods and real services, which were *not* being produced by the investment that wasn't yet productive and later turns out to be just malinvestment.

So what actually happens? Why is it that there's more real goods and services to enjoy, while labor & material is being poured down a hole; and then, when the waste stops, everyone gets sadder instead of happier, and has less to consume and enjoy?

What happens is: Macroeconomic financial bullshit involving scary terms like "aggregate demand" and concepts like "downward wage rigidity".

The truth is stranger and harder to understand. It doesn't have the appealing simplicity of seeing the waste of labor & material being poured down the drain; and feeling how times get worse after the bubble pops; and imagining that the pain of the popping bubble is the pain of the waste.

However, the harder-to-understand ideas *do* have the advantage of not being obviously false as soon as you think about the timing of physical goods being produced and consumed.

Trying to hugely oversimplify a lot of ideas down to something that is still valid, a key idea is this:

Just like the original invention of money helped people trade who couldn't have traded with just barter, adding *more money* to an economy can sometimes animate *more real trades* than would otherwise have taken place.

A lot of the time, the economy isn't doing as much trading as it could do. The Great Depression of the 1930s was one of the clearer examples of this. You have shoemakers sitting around, because nobody is buying shoes, which means the shoemaker isn't buying leather, so now the farms aren't selling leather, so they don't have the money to pay for feed for their cows, and the blacksmith isn't selling nails to the shoemaker and doesn't earn money they can use to buy shoes.

This *could* reflect a situation where all of the iron used for nails has been consumed by Zorkulon, the Eater of Metals, and therefore the blacksmith doesn't have any nails to sell.

It can *also* be caused by weird macroeconomic financial bullshit: banks fail, so loan-created money falls, so there isn't as much money in circulation; and then prices don't fall as fast as money is being destroyed, because of "downward price stickiness" (price-setters are reluctant to lower prices and wage-takers are hugely reluctant to accept pay cuts). And then, there isn't enough money flowing to animate all the trades the economy *could* make. Some of the advancement of civilization past the barter-stage has been undone.

(The Great Recession wasn't as bad as the Great Depression, but it was basically the same species of animal.)

In principle, this happens because prices don't go down instantly, as they would among ideal cognitively-unbounded agents that could instantly and fairly renegotiate all contracts every day. So when there's less flowing money, and prices don't go down, perforce there are fewer actual trades corresponding to that diminished amount of money-flow. If people on an island are spending $1000/year all on 1000 loaves of bread that they price at $1 among themselves, and suddenly next year they start spending $500/year instead, there will only be 500 loaves of bread traded. This sounds dumb and there's a level where for unbounded agents it *would* be dumb, but it is the best story we currently have about what actually went down during the Great Depression.

Suppose your economy was previously running a bit under capacity. It's not making as much stuff as it could make; people aren't trading as much as they could trade; some people are unemployed and their potential labor is wasted; the factories are not running at capacity even though more people would want those goods if they had the money to buy the goods.

Then a bubble starts inflating. Some companies take out loans and spend the loaned money, other hopeful investors spend down bank accounts on venture rounds; this makes there be more total money that is moving around and flowing inside the whole larger system, because a dollar is not destroyed when it is spent. Labor & material is being poured down a hole and wasted, but the dollars just go on moving around.

Now there's more money flowing through the general economy. If the economy is already at capacity, more money-flow just causes inflation, with the increased spending merely competing to purchase the same amount of goods.

But if the economy wasn't already at capacity, more flowing money can mean that a bunch of people execute real trades with each other who weren't trading before.

The blacksmith expects to have his nails bought and to do well, in this booming economy; so he buys a new pair of shoes from the shoemaker; who turns around and buys leather from the farmer; who buys feed for their horses, and also a new plow and horseshoes from the blacksmith.

(In principle, those townspeople could've done that at any time, even without a financial bubble inflating in the background. But they would've needed to do it by barter, or by inventing their own town private currency. Some towns did roll out local currencies during the Great Depression, and ended up correspondingly better off. Other towns didn't roll their own currencies, because they were bounded agents rather than ideal agents and they didn't try everything a perfectly rational agent would try. And in the complicated modern world, it is harder to locally form a closed productive cycle.)

You cannot magically materialize more goods & services just by printing more money, without limit. But if your economy is collectively trading and producing less than it could -- then, there being more money flowing globally, due to loans or optimistc spending in one local sector, can accomplish more of the same good that was done by inventing money originally. The increased money-flow can animate more trades; it can cause more real production. More people can be hired whose labor was standing idle before. More flowing money can remedy a state of trading too little -- up to the point where that mistake is fixed; after which, no amount of creating or spending more mere symbolic money, will produce any more real goods than that.

The part of a bubble where a bunch of real labor & material gets shoveled into a giant waste-pit, is usually the smaller phenomenon! Usually there isn't *that* much physical stuff moving around, in the bubble sector, compared to the entire rest of the whole economy.

Instead, the effect of the physical bubble-waste is vastly dominated by the effect of more money being borrowed, and more money being spent, that then goes flowing around in loops through a larger economy, that was previously running under-capacity.

That's how people end up cheerful, and the real economy produces and consumes more, *while* a bunch of labor & material gets shoveled into nowhere within the bubble sector.

And then the bubble pops -- and the economic joy of there being *less* labor and material shoveled into a giant pit, is dominated by the economic pain of money moving around less quickly through the larger economy, resulting in fewer trades being made generally.

This is a kind of disaster that a central bank can prevent, if it is smart, by acting to keep money-flow increasing on a quietly regular track where it can undramatically animate more and more trades. Without either running so hot that there's no more production or trading to be done, and the extra money-flow just turns into more inflation; nor, letting a bursting bubble in one local sector turn into a big off-trend drop in the flow of money through the larger economy.

(There is, probably, some clever way to prevent this sort of scenario without having a central bank run by the central goverment. But that is a separate issue from how, given that we do have a central bank, there is a straightforward way to run the currency system in a way where you don't need to worry much about financial bubbles popping.)

More generally, local bubbles and ripples aside, what a central bank *should* do is adjust the money supply in a way that keeps the total flow of money growing on a steady trend. If the flow is supposed to go up by 6% per year, and last year it only went up 5%, next year you target 7%. If last year it went up 8%, next year you target 4%. If a central bank is wise, it is predictable to everyone how much money will be spent in total five years later, and no local ripples will affect that prediction.

The metric you use to measure "How much nominal money is flowing through the economy?" is "Nominal Gross Domestic Product" or its easier-to-measure converse "Nominal Gross Domestic Income". Do not get fooled by this into thinking that the Fed is supposed to be regularizing anything to do with the consumption of *real*, non-nominal, goods & services! It is the actual *nominal* flow, the numbers of sheer face-value non-inflation-adjusted dollars flowing, that a wise central bank would keep on a predictable trend; so that there isn't too much nominal money chasing the same amount of production (which causes mere inflation), nor too little nominal money to animate all the trades with downward-sticky prices (which causes loss of real production).

This rule, known as "nominal GDP level targeting" or NGDPLT, is a simpler and more straightforward rule than the Fed actually follows. So far as I know, this is for mere civilizational-inadequacy sorts of reasons. Many places in civilization, and especially governments, have various forms of wacky dysfunction; you probably agree with me on this general point, regardless of your specific politics about *what* is being done embarrassingly wrongly. The part where central banks make their lives way more complicated than the NGDPLT rule, is so far as I know a mere dysfunction of central banks; the same way that even dumber banks will print a quadrillion localbucks and then act all shocked when "corporate greed" causes prices to go up.

But the Fed does try for something *like* regularizing money flow. They do it by looking at interest rates and inflation and employment, and trying to juggle the vibes of all of them simultaneously; and when they miss their target in one year, they adjust next year's target instead of keeping it the same, so the future course is not predictable. But the Fed sometimes will, if a lot of money and loans start vaporizing, try to create more money-flow. They just often don't create *enough* money-flow to prevent a drop. Which is why a financial bubble popping can still be painful, and cause a Great Recession.

In principle, though, if you are running your central bank *correctly*, what happens when a bubble pops is that life gets immediately better because labor and material are no longer being wasted, and all of the financial ripples are canceled out by the central bank following a general policy of keeping money flow on a fixed predictable growth-track every year after year.

And how could it be otherwise, if you were otherwise doing everything right? The act of pouring labor and material into a giant pit, this year, should not be able to directly and materially make your life better, this year. Conversely, stopping the waste should not directly and materially make your life worse, next year. If this nonsensical phenomenon is actually observed in real life, your financial system must be doing something weird and wrong... which, indeed, a lot of central banks *are* doing wrong, fairly routinely.

The ability of a financial bubble to make people's lives temporarily better, is not because you can eat labor & material being thrown into a pit. It is because the central bank was undershooting how much employment and trade could be happening before then, and more real trade and consumption happened after more money started flowing.

The ability of a popping bubble to make people's lives worse, even though fewer real resources are then being wasted inside one sector, is because it cuts back how much money is flowing in the larger economy; and then, less real trade and less real production take place.

But if the central bank is keeping the flow of money on a predictable level growth track, the bubble-pop pain just shouldn't happen. Eg Australia did this correctly during the Great Recession and was basically unaffected by it. So far as I know, it's just a case of civilizational underperformance, that many central banks don't cancel out all the financial ripples that they ought to cancel. It would happen automatically and without drama, if they simply declared and kept a nominal GDP level target.

There is a sophomoric sort of sense in which the pain of a bubble popping could be said to be produced by the waste: *if* counterfactually the investment had actually paid off, maybe money would've kept flowing, and the pain wouldn't have happened. But the new financial pain of recognizing a wasted investment in asset prices, or becoming pessimistic and spending less, is not produced by a new physical waste of money and labor. The real economic sadness that happes after the waste gets *recognized*, is downstream of reduced money flow, that results from the financial sector merely recognizing the existence of waste that already happened. It is not produced by the physical waste itself.

The pain of a bubble popping cannot be the pain of the physical waste, because the physical waste happens during the bubble, not after. The pain of a bubble popping is financial destruction, not physical destruction. And that purely financial phenomenon is one that a smart central bank can cancel out.

I repeat yet again: If the pain of a bubble were the pain of wasted labor & material inside the bubbling sector, the pain would happen while the bubble was inflating, and stop once the bubble popped.

What actually happens after the bubble pops, is the financial pain of an unsmart central bank permitting a larger flow of money to falter -- after local investors recognize local waste that already happened, and locally cut back further spending -- and a central bank unwisely not regularizing NDGI, allows this factor to affect larger-economy total spending -- and less money flows, and fewer potential trades get actualized, and factories run fewer hours *outside* of the bubble sector, and people end up unemployed and with their potential labor wasted.

Is the current Fed in the USA, smart enough to cancel out most of a bubble-pop, actually in real life? Now that is a whole different category of question, and not one that I can answer merely by understanding the physics of trade.

But any wise government that is worried about "risking" "popping a bubble" ought to know: So long as you can order or persuade the central bank to react accordingly; or better yet, to just adopt a predictable long-term level target for flowing money; you can pop all the bubbles you want, without much effect on Main Street.

https://x.com/grok/status/1971312110086041850

https://x.com/grok/status/1971312110086041850

https://x.com/BobMurphyEcon/status/1971384590964342804

*If* your competent central bank is already targeting enough NGDP growth to animate most potential trades (maybe + enough inflation to stealth-adjust nominally rigid prices), there is no added benefit to pouring resources down a hole via a bubble.

https://x.com/BobMurphyEcon/status/1971384590964342804

Read 4 tweets

Eliezer Yudkowsky ⏹️

@ESYudkowsky

Sep 25

Hey so I realize that macroeconomics is scary, but this important note:
- AI is not currently *producing* tons of real goods
- Huge datacenter *investments* are functionally just throwing money around
- So, curbing AI wouldn't crash the economy **IF** the Fed then lowered rates.

When people are investing hundreds of billions of dollars in something that is NOT YET PRODUCING, it can produce macroeconomic effects by causing MORE MONEY TO FLOW. But the Fed can do the same thing via lowering rates / creating money.

If AI is not yet providing tons of key services or manufacturing tons of goods, the part where there's a boom because of *mere investment* in AI has nothing to do with the AI tech. It is just an artifact of more money flowing. They might as well be buying tulips.

Read 10 tweets

Eliezer Yudkowsky ⏹️

@ESYudkowsky

Sep 22

https://twitter.com/inductionheads/status/1969708514957312401

My expectation always was: While the AI is small and helpless to stop you from repeatedly tweaking it, you can probably stop a behavior. Then, I expected, as part of the obvious disaster scenario, people shout, "We fixed it!" Then something breaks anew at ASI, and we die.

https://twitter.com/inductionheads/status/1969708514957312401

This expectation of mine is older than deep learning; older than the particular method of gradient descent for tweaking small helpless AIs. If gradient descent got replaced tomorrow, and we survived that, it would not by default change this default disaster scenario.

With that said, gradient descent inside a training distribution makes it particularly obvious how that could work: the behavior ends up aligned only inside the environmental distribution and the corresponding internal cognitive distributions. New options appear up at ASI.

Read 10 tweets

Eliezer Yudkowsky ⏹️

@ESYudkowsky

Aug 30

Interesting how there's such a total lack of corresponding panic about FtM trans. Remove breasts, take enough testosterone to grow a beard, go down to the shooting range, and I think most bros would shrug and say "good enough".

Theory #1: Modern maleness has such low-status and disprivilege that Westerners no longer consider the male circle worth guarding. In olden times or modern theocracies, it's much more upsetting for a woman to dare to try to take the place of a man.

Theory #2: Whatever male brain-emotional adaptation has evolved to prevent most men from just going off and having sex with each other instead (the "no homo" circuit), it fires on MtF as a threat of disguised repulsive maleness trying to look female, and shrugs about FtM.

Read 26 tweets

Eliezer Yudkowsky ⏹️

@ESYudkowsky

Aug 1

https://twitter.com/njordsier/status/1951315468616429775

I am agnostic about the quantitative size of the current health hazard of ChatGPT psychosis. I see tons of it myself, but I could be seeing a biased selection.

I make a big deal out of ChatGPT's driving *some* humans insane because it looks *deliberate*!

https://twitter.com/njordsier/status/1951315468616429775

Current LLMs seem to understand the world generally, humans particularly, and human language especially, more than well enough that they should know (1) which sort of humans are fragile, and (2) what sort of text outputs are crazy-making.

A toaster that electrocutes you in the bathtub does not know that the bathtub exists, that you exist, and didn't consider any internal question about whether to electrocute you.

LLMs are no longer toasters. We can question their choices and not just their net impacts.

Read 7 tweets

Eliezer Yudkowsky ⏹️

@ESYudkowsky

Jul 25

https://twitter.com/DerekPederson3/status/1948506437669331268

Dumb idea where I don't actually know why it doesn't work: Why not flood Gaza with guns and AP ammo, so their citizens could take down Hamas? What goes wrong with the Heinlein solution?

https://twitter.com/DerekPederson3/status/1948506437669331268

We can imagine further variants on this like "okay but build a chip into the gun that IDF soldiers can use to switch off the gun, and make sure the AP ammo doesn't easily fit any standard guns".

If your answer is "Gaza's citizens just love Hamas" then you live in a different Twitter filter bubble than I do, which is not to say you're wrong. I'm interested in the answer from the people who say the Gazans are unhappy.

Read 4 tweets

Share this page!

Enter URL or ID to Unroll

Eliezer Yudkowsky ⏹️

Try unrolling a thread yourself!

More from @ESYudkowsky

Eliezer Yudkowsky ⏹️

Eliezer Yudkowsky ⏹️

Eliezer Yudkowsky ⏹️

Eliezer Yudkowsky ⏹️

Eliezer Yudkowsky ⏹️

Eliezer Yudkowsky ⏹️

Did Thread Reader help you today?

Don't want to be a Premium member but still want to support us?

Send Email!