is AI gonna take our jobs?

dawg, I hope you notice the difference between TV shows shot on film in the 90s and the current product, lmao

As much of a robot as I like to think I am, I actually do think there will be a difference between AI and real photography, but you're exploring that part of the subject, I'm just saying I think the quality of AI will continue to improve (maybe even in ways past current computing knowledge)
 
NorBro said:
dawg, I hope you notice the difference between TV shows shot on film in the 90s and the current product, lmao

As much of a robot as I like to think I am, I actually do think there will be a difference between AI and real photography, but you're exploring that part of the subject, I'm just saying I think the quality of AI will continue to improve (maybe even in ways past current computing knowledge)
Click to expand...
yeah the stuff from the 90s looks better
 
NorBro said:
lol, this is a trick scenario b/c I have great love for the 90s
Click to expand...
I mean, a lot of aspects of the cinematography have improved due to LEDs and camera capabilities and rigging and budget/style. but the basic quality of the color and detail/edges is superior on film IMO. and sky rendering. things like that
 
these are just for fun

https://twitter.com/x/status/1884266429563937230
(george w bush reference fyi)

https://twitter.com/x/status/1883883949166088511

https://twitter.com/x/status/1883973153145381064

https://twitter.com/x/status/1883571193568981231

https://twitter.com/x/status/1883397266209116455

https://x.com/BasedBeffJezos/status/1883086861297754491

https://x.com/fintech_shark/status/1884366776475025918

btw the UK seems to have voted in favor of copyright protections against AI. I'm not 100% clear on the details but it seems that if you sell an AI product in the UK you will have to respect their copyright laws and pay licensing fees for content. Huge!
 
I just used a site called perplexity.ai (saw it in an ad) to give me simplified instructions on how to download and use a simplified version of r1 on my computer and run it in a terminal window. can use it offline. no data sent anywhere. etc. pretty cool
 
Funny - Open AI with closed source code! "Damn those meddling teens..."

The UK ruling seems like a big financial hurdle to the 'take over the world before anybody realizes it tech companies'.
 
NorBro, fundamental and permanent divisions like this -

"AI hallucinations can’t be stopped"

www.nature.com

AI hallucinations can’t be stopped — but these techniques can limit their damage

Developers have tricks to stop artificial intelligence from making things up, but large language models are still struggling to tell the truth, the whole truth and nothing but the truth.
www.nature.com www.nature.com

Of course, hallucinations are not necessarily a problem for generating video/imagery because we're not asking the machine to give us facts. (Though it could have implications for its ability to produce realistic imagery?) Anyway...
 
i don't know what all this alarmist hysteria is but the only hallucinations i know are from woodstock during the 70s
 
Saw a study recently that concluded that LLMs are fundamentally incapable of reasoning and can only do pattern-matching.

I was thinking about that when i saw a post where someone asked this riddle to chatgpt and it responded that the surgeon is actually a woman, revealing your unconscious bias. (That's the answer to a similar, famous riddle.)

"A man and his cousin are in a car accident, and sadly the cousin dies. The man is rushed to surgery. Upon seeing him, the surgeon exclaims: "i can't operate on this man! He is my cousin." How is this possible?"

So I asked this go chatgpt o3-mini-high. It thought about it for 1 min 22 secs and spit out the following:
 
You said:
A man and his cousin are in a car accident, and sadly the cousin dies. The man is rushed to surgery. Upon seeing him, the surgeon exclaims: "i can't operate on this man! He is my cousin." How is this possible?


Thought about the cousin riddle for 1m 22s
Solving the riddle

I'm intrigued by the riddle about a surgeon who exclaims, "I can't operate on this man!" This suggests the surgeon is the man's cousin, leading me to consider familial relationships and stereotypes.

Revisiting familial links

I'm rethinking the riddle with a focus on the man's cousin. Could the surgeon be a family member, like the father's cousin, rethinking stereotypes about the profession?

Investigating the ambiguity

I'm piecing together the riddle's ambiguity, whether the surgeon is the man himself or his cousin. The context reveals the cousin is deceased, suggesting the surgeon must be the man.

Understanding familial roles

I'm examining if the surgeon is related by blood or marriage. The statement "he is my cousin" hints at a specific familial relationship, possibly through marriage or another cousin.

Revisiting relationships

Considering the surgeon's familial ties with the patient, possibly through marriage or another cousin, to match the statement "he is my cousin" in the riddle.

Tracking familial links

I'm considering if the surgeon is the patient's female relative or another cousin, analyzing the riddle to uncover a unique familial connection.

Distinguishing connections

Interestingly, a similar riddle often hints at "the surgeon is the boy's mother," emphasizing familial ties and the unique scenario of the surgeon being a relative actively participating in the surgery.

Revisiting the riddle

Mapping out a solution where the surgeon is a female cousin of the patient, focusing on their close relationship and the familial connection explicitly stated.

Piecing it together

Considering the surgeon as the patient's female cousin, aligning with the riddle's familial connection and the puzzling statement "he is my cousin."

Noticing the familial bond

The surgeon refuses to operate due to the patient being his cousin, with the riddle emphasizing their close family tie.

Revisiting the familial bond

The surgeon refuses to operate due to the patient being his cousin, confirming their close family relationship and hinting at a deeply personal conflict for the surgeon.

Reassessing connections

Interestingly, the surgeon is the man's second cousin, a relationship that doesn't inherently prevent the operation from proceeding.

Unravel the ambiguity

It's interesting to see that the term "man" might not specify gender, suggesting the surgeon could be the patient’s female cousin, expanding the familial dynamic and enriching the narrative.

Revising my approach

Ok, let me see. The ambiguity in the term "man" suggests the surgeon is the patient's female cousin, which aligns with the familial connection and enriches the narrative dynamically.

Reevaluating connections

I’m noting that if the surgeon is the patient's female cousin, they share grandparents, aligning with the familial relationship noted in the riddle.

Navigating ethical paradoxes

It's fascinating to see that ethical guidelines don't universally prohibit surgeons from operating on relatives, though policies often restrict such actions due to conflicts of interest or bias.

Revisiting familial ties

Considering the surgeon as the patient's female cousin, who shares grandparents, complicates the familial relationships and adds depth to the narrative.

Taking a closer look

I’m pondering if the riddle's twist involves the surgeon being the patient's female cousin, who shares grandparents, adding depth to the familial dynamics.

Mapping out the situation

I’m analyzing the riddle's dynamics, noting that the surgeon is related to the man, which presents a conflict of interest as a potential reason why they can’t operate on him.

Acknowledging gender stereotypes

The puzzle plays with the assumption of a male surgeon, highlighting how gender stereotypes can influence our understanding, unless the real twist is about challenging these stereotypes.

Considering gender implications

Interesting how the puzzle's gender dynamics seem to challenge assumptions by suggesting a female surgeon, playing with stereotypes more than family relationships.

Navigating ethical boundaries

Considering the ethical challenge: it's generally not recommended for doctors to operate on immediate family due to potential conflicts and emotional involvement.

Revisiting assumptions

I'm rethinking traditional riddles, like the "friend in the car accident." This opens up new angles on ethical guidelines and emotional biases.

Weighing ethical dilemmas

I’m thinking the riddle likely involves a female surgeon faced with an ethical issue, such as a conflict of interest or emotional bias, when operating on a male cousin.

Clarifying familial ties

OK, let me see. The conversation reveals the surgeon is another cousin, not the one who died, which addresses the ethical concern about operating on family by clarifying the familial connections.

Piecing it together

OK, let me see. The surgeon is both the cousin of the deceased and the sister to the man, creating a complex family dynamic and ethical dilemma.

Assessing ethical constraints

It's becoming clear that the riddle is hinged on the idea that operating on a family member is deemed unethical. The surgeon's gender remains unspecified but is intriguing to consider.

Navigating ethical dilemmas

Considering how puzzles often tackle ethical issues, like avoiding surgery on a family member, there might be a similar scenario here.

Gender bias and family ties

I'm thinking about a surgeon who might be a female cousin, which adds an interesting twist, especially considering the gender bias often associated with the profession.

Pulling together

I’m considering how the surgeon's gender and family relation might play into the ethical dilemma of operating on a family member.

Ethical decision

The surgeon's refusal likely stems from ethical guidelines, avoiding operations on immediate family to manage conflicts of interest and emotional bonds, rather than gender or familial relation.

Considering ethical choices

Doctors often skip surgeries on close family due to ethical guidelines on conflicts of interest and emotional ties. Gender or familial relation isn't the main concern here.

Evaluating ethical choices

OK, let me see. I’m thinking the suggestion might lean on ethical rules against surgery on close family, managing conflicts of interest or emotional ties, over genetic or adoptive ties.

Assessing moral grounds

I’m leaning towards the surgeon's avoidance of a kin surgery due to ethical standards, especially managing conflicts of interest and emotional ties. This makes me question the balance of these factors.

Challenging assumptions

Let's break down the riddle, pondering if the term "man" might imply a male surgeon, but ethical rules on surgery with family ties seem more pertinent.

Recasting the issue

OK, let me see. The riddle isn't fixated on the surgeon's gender but on ethical guidelines involving close family, like surgery on relatives to avoid bias or emotional involvement.

Examining family ties

It's becoming clear that the surgeon and the injured man are extended family members, likely cousins. This conclusion follows from the surgeon's declaration and the family context.

Playing with assumptions

I'm tinkering with the idea that the puzzle's twist comes from reversing common beliefs, particularly the notion that surgeons are always male, and this woman surgeon's familial connection.

Balancing family ties

I'm navigating the ethical guideline that doctors shouldn't operate on immediate family, questioning if cousins are close enough to trigger this rule. Emotional or conflict-of-interest reasons are also in play.

Pulling together

Thinking about the reasons behind a surgeon's refusal to operate on a cousin—ethical guidelines, emotional or conflict-of-interest concerns. These factors highlight challenges in making a clear diagnosis.

Piecing together possibilities

OK, let's consider the scenario: the surgeon can't operate on the injured man due to a family rule. This situation typically occurs when there are three or more cousins involved.

Weighing possibilities

I'm looking at a scenario with three siblings and their children, where the surgeon and the injured man are cousins, and the third cousin tragically passed away.

Navigating ethical dilemmas

Thinking through the conflicts of interest in medicine, avoiding surgeries on close relatives to prevent bias and emotional challenges is often advised. This ties into the "doctor's dilemma" puzzles.

Navigating guidelines

It's becoming clear that the surgeon's gender might align with the guidelines, preventing surgery on close family due to potential conflicts and emotional strain, which echoes the "doctor's dilemma" puzzles.

Examining assumptions

It's interesting to see how assumptions about the surgeon's gender can shape our understanding of professional guidelines, which often prohibit close family operations due to potential biases and emotional challenges.

Wondering about family ties...

Taking a closer look...

Piecing together insights...

Assessing ethical dilemmas...

Drawing conclusions...

Rediscovering familial links...

Pulling together...

Addressing cultural norms...

Spotting familial links...

Revealing gender assumptions...
Click to expand...

The trick is in our assumptions about who can be a surgeon. Many assume a surgeon must be male, but in this case the surgeon is a woman—and she happens to be the man’s cousin. In other words, the man was in an accident with one cousin (who died) and his other cousin is the surgeon now responsible for his care.
 
No different than humans; we've made stuff up since day 1.

Actually, probably two* big differences:

(1) It doesn't know it's lying yet.
(2) It doesn't have any financial (or other) motive yet.

*Maybe it's also just dumb sometimes like humans.

What's the worst one out of these? ha
 
Paul Krugman compares the 90s tech bubble to the run up in AI stocks today. Sometimes people disregard him because of his political partisanship, but his economic analysis is a completely separate issue. I'm excerpting:

and it’s impossible not to wonder how much the current situation, with soaring valuations for a handful of technology stocks, resembles where we were 25 years ago, with the frenzy over AI now playing a role similar to that of the frenzy over the internet back then. I believe that there are strong similarities, but also some important and disturbing differences...

You can clearly see the tech surge in economic data, too. Economists try to measure technological progress by looking at “total factor productivity” — that part of economic growth that can’t be explained by the combined effects of growth in the labor force, increasing education levels, and growth in the capital stock. Here’s the rate of TFP growth over the previous 10 years, tracked over time:

1000000222.png

After a generation of rapid productivity growth after World War II, progress slowed to a crawl for two decades. Then it surged again: the peak in 2005 means that there was rapid progress from roughly 1995 to 2005.

True, the surge didn’t last. Back in 2000 the economist Robert Gordon argued that the IT revolution was far less significant than what he called the Second Industrial Revolution of the late 19th century, built around electricity, internal combustion engines, chemicals and — last but not least — indoor plumbing. (The great postwar boom was arguably about taking full advantage of this revolution.) So far the data have supported his skepticism.

Still, the tech surge was real, and brought real benefits to the economy, adding perhaps 10 percent to real GDP. What it didn’t do was justify the high valuations temporarily placed on tech stocks. Early entrants like Pets.com, whose famous sock-puppet appears at the top of this post, weren’t able to turn their hype into sustained profitability, even when the underlying concept made sense. (I order Jack’s cat food from Chewy.com.)

So why did tech stocks rise so high before crashing? Shiller argued that asset bubbles can act like natural Ponzi schemes: those who get in early make money, not from underlying asset returns, but from rising prices driven by later entrants; as people see the big payoffs others are receiving, they pile in too, driving the asset price even higher. Skeptics start to look foolish; eventually some of them join the party, driven by FOMO — fear of missing out.

And then you run out of greater fools, the music stops, and investors are left with a terrible hangover.

It’s impossible to read about the internet-based frenzy of the late 1990s without drawing parallels with the AI-based frenzy we’re experiencing now. In fact, even the numbers look similar. In 1999 the price-earnings ratio for the S&P 500 hit 33, which looked, and was, crazy. As I work on this post, the PE ratio is about 30.

Now, like the internet — but unlike crypto, which still seems to have no use cases beyond money-laundering — AI clearly has significant real-world applications. Even if you’re one of those who describes it as “souped-up autocorrect,” well, that could describe many white-collar jobs. Also, you could equally well describe heavy earth-moving machinery as a souped-up version of a guy with a shovel. So?

AI, then, is a serious technology that will add significantly to economic growth. Estimates, however, are all over the place, from a one-time bump of a point or two in GDP to a singularity in which computers become truly intelligent, surpassing humans (and then Skynet kills us all.)

As far as I can tell, it’s a reasonable guess that AI’s economic impact will look like that of the IT/internet boom of 1995-2005: a significant bump in productivity but not an enduring transformation of the growth rate. But that’s only a guess.

But what about stock prices? To the extent that stock values in the 1990s reflected more than a natural Ponzi scheme, they reflected the belief that some of the tech players would eventually establish themselves as highly profitable quasi-monopolies along the lines of Microsoft, which to this day holds an entrenched position based on network externalities: everyone uses their products because everyone else uses their products.

What’s different this time is that AI fever is concentrated on a handful of companies — the Magnificent 7 — most of which are already entrenched quasi-monopolies. I don’t know whether people realize how anomalous this is. Historically, major new technologies have tended to disrupt the existing market hierarchy; this time, investors are in effect expecting radical new technology to reinforce that hierarchy.

And I guess I don’t understand why anyone expects AI to make highly profitable quasi-monopolies even more profitable. How much bigger can the market for Office or Google search get? I understand that these companies feel the need to invest in AI for defensive purposes, to fend off potential competitors. But this need should if anything make them less rather than more profitable. This will be especially true if, as the shock over DeepSeek suggests, big, established companies are investing in expensive, bloated models rather than thinking carefully about what they actually need.

In any case, the concentrated nature of AI frenzy goes along with another big difference from the 1990s: political power. In the 1990s Silicon Valley types tended to consider government irrelevant to their libertarian techno-utopian dreams. These days Big Tech invests heavily in political influence...

All of which suggests that while AI fever bears a lot of resemblance to the dotcom bubble, the end game may be quite different. Look at Donald Trump’s two big tech-related proposals — a strategic cryptocurrency reserve and a $500 billion AI infrastructure investment. From the point of view of the national interest, the first makes no sense at all; the second might conceivably have merit, but sits oddly with the Trump administration’s attempts to unravel all the Biden administration’s efforts on behalf of strategic technology, let alone green energy.

But suppose that we think of these proposals not in terms of the national interest, but in terms of who would get the money. Who holds a lot of cryptocurrency that the government would buy up? Which companies do you think would receive the lion’s share of subsidies for AI?

There are some clear similarities between the 90s tech bubble and recent AI fever. But this bubble may end, not with a pop, but with a giant tech-bro bailout.
Click to expand...
 
It's just drivel because no one knows the answer to the only question that matters, should you be in or out, right now? Risk versus reward.
 
Tom Roper said:
It's just drivel because no one knows the answer to the only question that matters, should you be in or out, right now? Risk versus reward.
Click to expand...
Krugman isn't a stock picker. He's not offering you investment advice. He's analyzing historical trends.

But if you consider that the P/E ratio of the s&p is close to when it popped in the first tech bubble, that suggests to me that we're near the top.

But obviously there are 2 big questions -- how much will AI actually increase productivity? And will the Magnificent 7 hold onto their quasi-monopolies or will they be displaced by American or Chinese upstarts?

It's very interesting to me that the productivity growth spurred by the internet was but a small fraction of that spurred by late-19th century technologies. Puts things in perspective.
 
ahalpert said:
Krugman isn't a stock picker. He's not offering you investment advice. He's analyzing historical trends.
Click to expand...
A bubble 35 years ago is not a trend. History yes. Predictor? Maybe. Trend no.
ahalpert said:
But if you consider that the P/E ratio of the s&p is close to when it popped in the first tech bubble, that suggests to me that we're near the top.
Click to expand...
Okay, that's your guess. Got it, you're staying out. Everybody should do what's right for them.
ahalpert said:
But obviously there are 2 big questions -- how much will AI actually increase productivity? And will the Magnificent 7 hold onto their quasi-monopolies or will they be displaced by American or Chinese upstarts?
Click to expand...

Those questions don't concern me. Fundamentals are progress measurements for energy, agriculture, manufacturing, transportation, not picking winners and losers.
ahalpert said:
It's very interesting to me that the productivity growth spurred by the internet was but a small fraction of that spurred by late-19th century technologies. Puts things in perspective.
Click to expand...
That shouldn't surprise anyone. Internet was a defense project, funding development of ARPANET, for sharing information, connecting universities, TCP/IP and email, commercialization in the '80s, web, browser, search, e-commerce and social media in the '90s, 2000's on broadband, mobile internet, Wi-Fi, and social media platforms. You said, late 19th century. Stay at home connectivity doesn't build anything except itself! Are you really comparing the tech contributions of social media and wifi to the nation building that took place during Vanderbilt, Carnegie, Rockefeller, J.P. Morgan? Electrification, Steel, Energy, the assembly line, transportation, aviation? When Obama said, "You didn't build that, somebody else built that," he was right and he was talking to you. The internet is nothing without the basic industries to power it.
 
You must log in or register to reply here.
Back
Top