Once again we have Bill Maher’s 8½-minute news-and-comedy bit from this week’s “Real Time”. This time his topic is the relationship between AI and the future of new college graduates. It’s clear that those graduates aren’t keen on AI, fearing that the bot will take their jobs (see the videos of commencement speakers being booed for lauding AI). After all, if you can’t get a job, so says Gen Z, what is the use of a college degree? Even now, when AI is just sticking its nose into the educational tent, Maher notes that “only about 35% of graduates get a job in their field of study.”
Maher segues into the ignorance of college students: ignorance of math, ignorance of history, and ignorance of geography. After all, says Maher, “Why bother learning with context when ChatG{T can not only just tell me the answer, but compliment me for asking such an astute question.”
Maher’s take on AI is a beef about how it turns off people’s brains, not that it’s not useful: “Look: we all want the good parts of AI: solving medical mystery, figuring out clean energy,. . . but the vast majority of us will never use it for that. For us, it’s a lobotomy with a monthly fee. We’re not using it to cure cancer; we’re using it because we forgot how to make toast.”
So who’s to blame for this situation? Apparently Maher sees those who have developed AI, along with the American educational system that advances students who can’t learn math and English. He implies “the kids” aren’t at fault. Instead, they now have an unprecedented opportunity: to fix the problems caused by AI, which apparently take “the humans” out of the equation. The mission of graduates, he says, is to “fight for humans and make sure we’re not completely replaced.” But what this actually entails is a mystery that Maher leaves unresolved. All he says is that students can fix this “existential issue”, and what is unprecedented here is that the kids can do this without having to convince their elders.
The message Maher would give were he a graduation speaker? “Fight for humans and make sure we’re not completely replaced.” But what does that mean?
As usual, Maher is engaging and sarcastic, but it seems to me whatever serious message he has here got lost in the persiflage.
The guests you see are Democratic Senator Chris Murphy and former U.S. Ambassador to the UN Susan Rice.
I don’t recall ever asking to be marinated in AI. I don’t like using AI, but it’s shoved at me now in all queries on the web. And goddammit it, it is convenient.
So I asked the Google AI if AI investment is an economic bubble, as there is certainly huge investment in it, but where is the economic return? This is what I got.
It might be a bubble:
Whether AI investment is an economic bubble is a subject of intense debate, but the consensus points to a dual reality: it features some speculative, “bubble-like” enthusiasm, but the underlying technology is supported by real, revenue-generating infrastructure. [1, 2]
Here is how the AI investment landscape breaks down:
The “Bubble” Arguments (Risks of Overvaluation)
• Historical Comparisons: Skeptics draw parallels to the dot-com boom of the late 1990s and the telecommunications bubble, where infrastructure spending far outpaced actual consumer demand and unit economics. [1, 2]
• Staggered Revenue: The gap between the hundreds of billions spent on data centers and the actual, direct revenue generated by consumer AI applications remains wide. [1, 2, 3, 4]
• Circular Financing: Concerns have been raised that some AI infrastructure is being financed through a circular loop, where tech giants invest in private AI labs, which then use that money to rent servers and buy chips from those same tech giants. [1, 2, 3, 4, 5]
There should be eventual return on investment
The “Fundamental” Arguments (Real Value)
• Actual Earnings: Unlike dot-com era startups with zero revenue, major AI beneficiaries like semiconductor manufacturers (e.g., Nvidia) are smashing earnings records based on tangible hardware demand. [1]
• Enterprise ROI: Cloud providers and major enterprises are seeing measurable productivity and cost-efficiency gains. AI tools are increasingly demonstrating utility in coding, customer service, and supply chain management. [1, 2]
• Cash-Flow Backed: Many of the “hyperscalers” (e.g., Microsoft, Alphabet, Amazon) funding the massive AI buildout are financing this capital expenditure largely out of their own robust free cash flows, rather than solely relying on debt. [1, 2]
The Outlook
Ultimately, the massive investment cycle is likely to normalize. Even if stock market valuations for AI-linked companies experience a correction, the core utility and development of the technology are expected to permanently reshape the global economy. [1, 2]
000000000000
The item about eventual return on investment I think is laced with meaning that humans are being down-sized through-out in favor of cheaper AI services.