Absolutely needed: to get high efficiency for this beast … as it gets better, we’ll become too dependent.
“all of this growth is for a new technology that’s still finding its footing, and in many applications—education, medical advice, legal analysis—might be the wrong tool for the job,”
I don’t think books ever had the same amount of discussion of how they impact our global carbon footprint, and where it comes to “houses” - I doubt people in the neolithic said about their new invention what is being discussed with AI. It is a disingenuous comparison. (And sure, someone somewhere may have said something like that about basically anything, but usually not a large part of professionals from within the field, like is the case with AI.)
This is also not simply Ludditism, the nature of how AI is used currently goes far beyond where it is genuinely useful in a case of investor hype FOMO, and the hidden costs for our efforts against climate change are real, as are the problems for creatives - who sadly need a lot of the “bullshit work” that AI can substitute to survive while honing their craft - as is the quality drop in journalism, as are fundamental questions about how far generative AI models can truly evolve in quality for the massive amount of energy invested, so the usual “just wait until the tech gets better” is not the easy way out to justify draining said energy (and fresh water) on top of what crypto mining has been wasting with data centres in the past years.
Now, those problems aren’t simply problems of the technology, but also of how that technology manifests within market dynamics. But the technology still is not just neutral, and even if we view it as an inevitability, that inevitability does not have to manifest without regulation and within the context of hyped, often unwanted application to basically everything.
Without mechanisms to address problems and to enforce regulation, in lieu of fundamental changes to what market/investment dynamics demand, this is indeed a very questionable technology at this point. And also: To truly love something abstract, like “technology”, means being able to - sometimes harshly - criticise it. Think the meme of a “tech bro” with a fully automated house vs the IT guy who barely has tech stuff beyond their PC and some stuff tinkered on passionately in their own time.
I’m not sure regulation is going to be an open for this in the US anytime soon. Maybe EU can show us the way.