Lost in Cyberspace
Quote of the Day
”A week ago Thursday, we kind of learned something that we really should have recognized two years ago: If Elon Musk tweeting one word, “Gamestonk”, can quintuple a stock’s price because Elon’s fanboys like being part of a community in it for the LULZ, then viral meme contagion from Silicon Valley venture capitalists can bankrupt a bank that looked otherwise as if it was likely to skate through.
A shock like Lehman Brothers took a month to propagate. Something similar today would likely take only three days.”
- Brad DeLong, the Berkeley economist (and long-time blogger) who was once was a deputy assistant secretary for economic policy at the U.S. Treasury during the Clinton Administration.
Musical alternative to the morning’s radio news
Pergolesi| Stabat Mater | Emma Kirkby & James Bowman | Academy of St Martin in the Fields, conducted by Christopher Hogwood
Thanks to Max Whitby (Whom God Preserve) for suggesting it.
Long Read of the Day
What Have Humans Just Unleashed?
Long piece in which The Atlantic columnist Charlie Warzel tries to figure out the implications of the Large Language Models that obsess us all at the moment. At one point, a machine-learning guy, Nathan Labenz, describes humanity’s current state in relation to this technology as “Radical Uncertainty”.
I would call it half-informed bewilderment myself. But that’s btw. Wurzel is a thoughtful guy and his essay is a good read.
“ChatGPT doesn’t really resemble the Manhattan Project”, he writes at the end.
But I wonder if the existential feeling that seeps into most of my AI conversations parallels the feelings inside Los Alamos in the 1940s. I’m sure there were questions then. If we don’t build it, won’t someone else? Will this make us safer? Should we take on monumental risk simply because we can? Like everything about our AI moment, what I find calming is also what I find disquieting. At least those people knew what they were building.
I mourn the way our European citizenship has been stripped from those of us in the UK, by a slender margin, by voters who were lied to by mendacious and greedy politicians and businessmen. And at the same time recognise the challenges the EU itself needs to address. No wonder the book ends by quoting Gramsci on pessimisim/optimism. But also Vaclav Havel: “Hope is not prognostication. It is an orientation of the spirit, an orientation of the heart. …. It is not the conviction that something will turn out well, but the certainty that something makes sense, regardless of how it turns out.”
So, not a cheering read, at least for those likely to pick up a book about Europe. But a compelling read, by someone who had a ringside seat at many of the key meetings and ‘where were you when…’ events (above all the fall of the Berlin Wall) of the past 40 years.
I know, and admire, Tim and so will be reading his memoir. Diane also recommends his terrific book about the file that the Stasi kept on him when he was a journalist working in pre-1989 Europe.
My commonplace booklet
“How to Learn and Teach Economics with Large Language Models, Including GPT”
An interesting paper by Tyler Cowen and Alex Tabarrok.
Just for fun at one point, they asked CPT how Fred Flintstone was like Hamlet.
ChatGPT responded (in part):
Fred Flintstone and Hamlet are two vastly different characters from different time periods, cultures, and mediums of storytelling. It is difficult to draw direct comparisons between the two.
However, one possible point of similarity is that both characters face existential dilemmas and struggles with their sense of purpose and identity. Hamlet is plagued by doubts about his ability to avenge his father’s murder, and his own worthiness as a human being. Similarly, Fred Flintstone often grapples with his place in society and his ability to provide for his family and live up to his own expectations.
This Blog is also available as a daily email. If you think that might suit you better, why not subscribe? One email a day, Monday through Friday, delivered to your inbox. It’s free, and you can always unsubscribe if you conclude your inbox is full enough already!