... is even remotely ready for AI. I read Bill Gates' recent note on the subject (linked), and even his take suffers from the same fundamental incoherence and the same wishful thinking (or, to some extent, gaslighting) as pretty much all other attempts to assess the likely effects of the onset of the stuff. To wit, those attempts regularly tell us two inconsistent things:
i) The technology is swiftly going to exceed human capacities and thus will be absolutely transformational across pretty much all domains -- as an interviewee told Thomas Friedman (for some reason that is lost on me), it's "going to change everything about how we do everything."
ii) The disruption won't be too bad, though, because these intelligences are just going to be our helpers. As Gates tells us, "the demand for people who help other people will never go away. The rise of AI will free people up to do things that software never will—teaching, caring for patients, and supporting the elderly, for example." "AIs will empower people to do [sales, service or 'document handling'] more efficiently." Access to AI will "be like having a white-collar worker available to help you with various tasks." AI will "help health-care workers make the most of their time by taking care of certain tasks for them—things like filing insurance claims, dealing with paperwork, and drafting notes from a doctor’s visit." AI aimed at education "will know your interests and your learning style so it can tailor content that will keep you engaged. It will measure your understanding, notice when you’re losing interest, and understand what kind of motivation you respond to."
Neither Gates' attempt, nor many other of these attempts, however, explains why these developments might be limited simply to "helping people be more productive." More specifically, it doesn't explain why people will remain necessary in many of these domains at all. Gates begins his essay with the example of GPT-3 (that is, the previous generation of the technology) passing the AP biology exam with 59 correct answers out of 60. And that's little surprise -- as Gates tells us ...
"The amount of data in biology is very large, and it’s hard for humans to keep track of all the ways that complex biological systems work. There is already software that can look at this data, infer what the pathways are, search for targets on pathogens, and design drugs accordingly. Some companies are working on cancer drugs that were developed this way. The next generation of tools will be much more efficient, and they’ll be able to predict side effects and figure out dosing levels."
If this is true -- and it seems that it is -- then why would be anyone be concerned about teaching students biology anymore at all? To the extent that humans might be necessary to run lab or manufacturing operations, the overwhelming majority of those relatively-few humans won't need biology degrees to do it. And why would anyone choose to study biology and make a career of it? You aren't going to discover anything, the operation of your curiosity will be confined to confirming or ruling out the propositions developed by the machine, at best, and you will be paid accordingly.
Indeed, there's a very open question as to why people might continue to learn at all. If the biology AI can do all the biology and the comp-sci AI can do all the coding and development and the engineering AI can do all the engineering, then why should we care that the education AI will "know your interests and your learning style so it can tailor content that will keep you engaged[, and] measure your understanding, notice when you’re losing interest, and understand what kind of motivation you respond to"? Not to mention that, when faced with the prospect of undergoing that course of surveillance and manipulation, anyone who has chosen to enroll in a course for some reason can just enlist a specialized CheatGPT to manipulate ChatGPT right back, and turn instead to playing video games and jerking off.
And if you do go ahead and study a subject, and not cheat and actually learn, then what awaits? "Company-wide [AI] agents will empower employees in new ways. An agent that understands a particular company will be available for its employees to consult directly and should be part of every meeting so it can answer questions. It can be told to be passive or encouraged to speak up if it has some insight. It will need access to the sales, support, finance, product schedules, and text related to the company. It should read news related to the industry the company is in." Nevertheless, Gates assures us, "I believe that the result will be that employees will become more productive." Really? In the presence of an intelligence that knows everything about the company and its markets at all times, and that is capable of better strategic and operational analysis than any employee including the CEO? Forget whether the AI "should be part of every meeting." Why should there be meetings?
Everyone senses this tension, and when approaching the heart of the matter most everyone who writes on the subject responds that, well, yes, there will be disruptions, so the government has to figure how retrain everyone so that they can fit with the AI. And it's really not urgent or anything, because really strong AI is still years away. We can relax, because the terminators aren't here yet. But of course that's no answer at all. The specialized, non-general AIs that are already here will -- will -- do plenty of damage all by their juvenile-terminator selves, long before their descendants arrive on the scene.
This isn't an argument for banning the stuff, because that's a pipe dream. For the same reason, it's also not an argument for regulation -- as a republic we are much less capable of regulating AI than we are of understanding it, and as a republic we don't understand it at all. There'll come a time for productive discussion of how to regulate these capabilities, and that time will be after it has thrown us into multiple crises on top of the ones that we have on our plate now, assuming arguendo that by then we haven't turned over the work of governing ourselves to Chat-GGPT (Governmental Generative Pre-Trained Transformer).
Instead, I suppose -- because I didn't really think through what this might be an argument for, before I started -- this is an argument for only one meager little proposition: When you read things about how AI isn't going to be terrifyingly disruptive, that it's just going to be our faithful helper, that the real risks are still years away, don't buy it. Start thinking hard about what it might do to your life now, because it's here now, in plenty enough force to f*ck a lot of people up.
I don't think it's as close to as disruptive as you're suggesting. Within software development, it's good at giving you some boilerplate -- "give me a baseline React project that does basic thing X." The GPT4 demo where he shows a hand drawn picture that GPT4 wrote as a static webpage is impressive, but is more on the parlor trick/convenience end of the spectrum than 'replace all coders.'
A good counter example is how AlphaFold -- DeepMind (from Alphabet) -- is changing biology. It basically solved a 50 year old grand challenge on protein folding. However, biologists and bio-chemists are even more relevant than ever because of what this has unlocked.
Labor-creation has almost always muted the effects of the labor-replacement impact of technology.
and I am dumbfounded. "Write a c++ program that uses openmp with 5 child processes to approximate pi. I want a confidence interval on the point estimate". And it works.
I had always joked with my kids about writing a picture book, and I used DALLE2 to generate some images and put a book out on the Kindle store. Probably took me 3 hours and it was worth the entertainment value for my kids. I linked one of the images which stated with the prompt "Norman Rockwell painting of kids wiping their hands on a wall." It generated a picture frame on the wall as well. I deleted the image inside the frame and asked for it to draw a "Norman Rockwell painting of an exasperated mother cleaning a wall"
Finally, I can't belive how well GPT4 can create poetry and songs according to given meters or styles.
"Write a rap ballad summarizing Dante's divine comedy and include a summary of the moral themes"
Verse 1:
Yo, let me tell you 'bout a journey to hell
Dante's Divine Comedy, it's a story to tell
A poet lost in the woods, unsure of his fate
Until Virgil came, and showed him the way
Chorus:
From the depths of hell to the highest heaven
Dante's journey took him through the seven
Circles of hell, where the sinners reside
And purgatory, where redemption can be found inside
Verse 2:
First circle, limbo, for those who died unbaptized
Then lust, gluttony, greed, and anger, all so despised
Heresy and violence, the sixth and the fifth
And treachery, the worst, the ninth circle abyss
Chorus:
From the depths of hell to the highest heaven
Dante's journey took him through the seven
Circles of hell, where the sinners reside
And purgatory, where redemption can be found inside
Verse 3:
In purgatory, the souls climb the mountain high
Repenting for their sins, before they can fly
Up to the paradise, where God's love abounds
And the ultimate reward, for those who turn their lives around
Chorus:
From the depths of hell to the highest heaven
Dante's journey took him through the seven
Circles of hell, where the sinners reside
And purgatory, where redemption can be found inside
Verse 4:
The moral of the story, is to live a life of grace
Avoiding sin and temptation, to stay in God's good graces
To repent for our mistakes, and seek redemption
And strive to live a life of love, and perfection
Chorus:
From the depths of hell to the highest heaven
Dante's journey took him through the seven
Circles of hell, where the sinners reside
And purgatory, where redemption can be found inside
Outro:
So let us all remember, Dante's Divine Comedy
And strive to live a life, that's both righteous and worthy
For in the end, it's not the wealth or fame we gain
But the love and grace of God, that will forever remain.
... entrusted their and their families' futures to their computer science careers, upon the urging of pretty much every kind of educational and career authority out there, over the last 20 years. People currently in their 20s, 30s, 40s. Their careers could be eradicated, by the millions, within, what? Eighteen months? Two years? Hey, maybe five years.
Add the health care workers whom Gates and others believe will be "empowered" to "do other things." The architects and engineers. The logistics and accounting and production managers. The actors and models, the copywriters, the salespeople .... On and on and on, and it isn't going to take strong AGI to do it. It's only going to take the tools that are being rolled out, to the market, right now.
I spent a lot of time a few years ago working on some applications of recurrent neural networks in Keras. These are a different architecture of neural network than used by GPT and DALLE, but they have a lot of similarities (as of 2017 it was the model structure used by Google translate). So I was able to get some insight into the potential of text and image analysis and generation. If you had asked me before I first looked at these programs a few weeks ago, I would have guessed that the kind of functionality I am already seeing when playing around would have been 10 years away. So I can't imagine what things will look like in 10 years.
There are still enough errors in the output to require expertise in sporting and fixing them, but even now this could represent a huge reduction in programming time just from getting the initial libraries and functions setup instantly while also minimizing typos and bugs.
isn't reliable enough to get all the hard points, but the humans in the loop get lazy and stop being skeptical and stop looking for the "stupid AI, you missed..." things.
for the AI generated models of the AI generated political candidates, KPOP boybands, and DiKToK social media influencers, we'll welcome the sweet, sweet thermonuclear annihilation.