The "Young Lady's Illustrated Primer" is still far off; mushroom coffee; our political reporters work very hard to remain underbriefed; Guerrieri & al. on optimal inflation, Törnberg on polarizatio...
What does "We are still very far from the "Young Lady's Illustrated Primer" of Neal Stevenson's "The Diamond Age" mean?
ChatGPT
"The Young Lady's Illustrated Primer" is a fictional book in Neal Stephenson's novel "The Diamond Age." The book is a highly advanced, interactive learning tool that adapts to the needs and interests of its young reader, providing education, guidance, and entertainment.
When someone says, "We are still very far from the 'Young Lady's Illustrated Primer' of Neal Stephenson's 'The Diamond Age'," they mean that we have not yet achieved the level of advanced technology and sophistication depicted in the book. It suggests that while we have made significant progress in the field of interactive education and personalized learning, we have not yet reached the level of technological advancement that would allow us to create something like the Primer in real life.
Ages ago, I joined the gang at the MIT AI Lab for a screening of Colossus: The Forbin Project about an artificially intelligent computer that took over the world. It was pretty awful as a movie, but even worse in its portrayal of artificial intelligence. At various points, the audience would start shouting "Control-S! Control-S!" That's the ASCII code to stop transmission, something very important back in the day when computers and devices like mechanical teletypes could be swamped by incoming data.
I hadn't thought about this until recently when I went to the Open AI site and asked a few cooking questions. The answers weren't bad, but they were massively verbose. The answer to "How long does it take to drip brew a pot of coffee?" shouldn't be longer than a few words or perhaps a full sentence. Well, it produced a reasonably accurate answer in the form of a sentence, then it went on and on and on. It produced a full paragraph of irrelevant material. Then it started to crank out another paragraph. Then, it kept going. I hit control-S and thought about the time I watched Colussus: The Forbin Project with the gang from the MIT AI Lab. Then I found the stop gibbering button and pressed it. Mercifully, it stopped, unlike the movie.
To be honest, I didn't read beyond the first sentence that more or less answered my question. What little of the additional text I scanned seemed like the stuff one wrote when one had to write five hundred words on why I won't make funny noises in class. If this is a productivity enhancement, our society is doomed. Too much first world productivity comes from producing fancy consultant reports full of this kind of ipsum lorem, empty words to pad out arguments agreeing with the sponsor's proposal. Do we really need more and longer reports of this sort? What are the chances that automating such report's production would free up talent for useful work? We all know the answer to that.
Soon LLM's will engage lonely users on social media, answer bosses' e-mails, and comment in Substacks. Our new Turing Test will be to assume that only the pedantic rants were written by humans, so everything else must be a computer algorithm. The LLM's will respond to each other without the request or notice of human readers. They will be autonomous idiots who drive views and clicks on sites where no human visited in months because we were overdosing on Large Porn Model (LPM) output.
Banking on Uninsured Deposits: Couldn't access the paper, but going by the abstract, isn't it implicit -- conspicuous by absence, rather -- that insuring all deposits takes care of the issue? Nice to hear that there is another type of optimal capital requirement that might help, but how many types of dedicated capital requirements, if they can be segmented neatly for various purposes at all, are we going to have and enforce with an army of regulators? An uninsured-deposit flight stress test along with other stress tests? I am probably misunderstanding what the authors are saying.
What does "We are still very far from the "Young Lady's Illustrated Primer" of Neal Stevenson's "The Diamond Age" mean?
ChatGPT
"The Young Lady's Illustrated Primer" is a fictional book in Neal Stephenson's novel "The Diamond Age." The book is a highly advanced, interactive learning tool that adapts to the needs and interests of its young reader, providing education, guidance, and entertainment.
When someone says, "We are still very far from the 'Young Lady's Illustrated Primer' of Neal Stephenson's 'The Diamond Age'," they mean that we have not yet achieved the level of advanced technology and sophistication depicted in the book. It suggests that while we have made significant progress in the field of interactive education and personalized learning, we have not yet reached the level of technological advancement that would allow us to create something like the Primer in real life.
Ages ago, I joined the gang at the MIT AI Lab for a screening of Colossus: The Forbin Project about an artificially intelligent computer that took over the world. It was pretty awful as a movie, but even worse in its portrayal of artificial intelligence. At various points, the audience would start shouting "Control-S! Control-S!" That's the ASCII code to stop transmission, something very important back in the day when computers and devices like mechanical teletypes could be swamped by incoming data.
I hadn't thought about this until recently when I went to the Open AI site and asked a few cooking questions. The answers weren't bad, but they were massively verbose. The answer to "How long does it take to drip brew a pot of coffee?" shouldn't be longer than a few words or perhaps a full sentence. Well, it produced a reasonably accurate answer in the form of a sentence, then it went on and on and on. It produced a full paragraph of irrelevant material. Then it started to crank out another paragraph. Then, it kept going. I hit control-S and thought about the time I watched Colussus: The Forbin Project with the gang from the MIT AI Lab. Then I found the stop gibbering button and pressed it. Mercifully, it stopped, unlike the movie.
To be honest, I didn't read beyond the first sentence that more or less answered my question. What little of the additional text I scanned seemed like the stuff one wrote when one had to write five hundred words on why I won't make funny noises in class. If this is a productivity enhancement, our society is doomed. Too much first world productivity comes from producing fancy consultant reports full of this kind of ipsum lorem, empty words to pad out arguments agreeing with the sponsor's proposal. Do we really need more and longer reports of this sort? What are the chances that automating such report's production would free up talent for useful work? We all know the answer to that.
Soon LLM's will engage lonely users on social media, answer bosses' e-mails, and comment in Substacks. Our new Turing Test will be to assume that only the pedantic rants were written by humans, so everything else must be a computer algorithm. The LLM's will respond to each other without the request or notice of human readers. They will be autonomous idiots who drive views and clicks on sites where no human visited in months because we were overdosing on Large Porn Model (LPM) output.
Banking on Uninsured Deposits: Couldn't access the paper, but going by the abstract, isn't it implicit -- conspicuous by absence, rather -- that insuring all deposits takes care of the issue? Nice to hear that there is another type of optimal capital requirement that might help, but how many types of dedicated capital requirements, if they can be segmented neatly for various purposes at all, are we going to have and enforce with an army of regulators? An uninsured-deposit flight stress test along with other stress tests? I am probably misunderstanding what the authors are saying.