alt Hacker NewsThe Adolescence of Technology
Comments
One of my formative impressions of AI came from the depiction of the Colligatarch from Alan Dean Foster's The I Inside.
The AI in the book is almost feels like it is the main message masquerading as a subplot.
Asimov knew the risks, and I had assumed until fairly recently that the lessons and explorations that he had imparted into the Robot books had provided a level of cultural knowledge of what we were about to face. Perhaps the movie of I Robot was a warning of how much the signal had decayed.
I worry that we are sociologically unprepared, and sometimes it seems wilfully so.
People discussed this potential in great detail decades ago, Indeed the Sagan reference at the start of this post points to one of the significant contributors to the conversation, but it seems by the time it started happening, everyone had forgotten.
People are talking in terms of who to blame, what will be taken from me, and inevitability.
Any talk of a future we might want dismissed as idealistic or hype. Any depiction of a utopian future is met with derision far too often. Even worse the depiction can be warped to an evil caricature of "What they really meant".
How do we know what course to take if we can't talk about where we want to end up?
Some people say that human jobs will move to the physical world, which avoids the whole category of “cognitive labor” where AI is progressing so rapidly. I am not sure how safe this is, either. A lot of physical labor is already being done by machines (e.g., manufacturing) or will soon be done by machines (e.g., driving). Also, sufficiently powerful AI will be able to accelerate the development of robots, and then control those robots in the physical world.
I would like to believe that we're about to see a rapid proliferation of useful robots, but progress has been much slower with the physical world than with information-based tasks.
After the DARPA Urban Challenge of 2007, I thought that massive job losses from robotic car and truck drivers were only 5-8 years away. But in 2026 in the US only Waymo has highly autonomous driving systems, in only a few markets. Most embodied tasks don't even have that modest level of demonstrated capability.
I actually worry that legislators -- people with white collar jobs -- will overestimate the near-term capabilities of AI to handle jobs in general, and prematurely build solutions for a "world without work" that will be slow to arrive. (Like starting UBI too early instead of boosting job retraining, leaving health care systems understaffed for hands-on work.)
I don't think we have much to worry about in terms of economic disruption. At this point it seems pretty clear that LLMs are having a major impact on how software is built, but for almost every other industry the practical effects are mostly incremental.
Even in the software world, the effect of being able to build software a lot faster isn't really leading to a fundamentally different software landscape. Yes, you can now pump out a month's worth of CRUD in a couple days, but ultimately it's just the same CRUD, and there's no reason to expect that this will change because of LLMs.
Of course, creative people with innovative ideas will be able to achieve more, a talented engineer will be able to embark on a project that they didn't have the time to build before, and that will likely lead to some kind of software surplus that the economy feels on the margins, but in practical terms the economy will continue to chug along at a sustained pace that's mostly inline with e.g. economic projections from 10 years ago.
It's interesting just how many opinions Amodei shares with AI 2027's authors despite coming from a pretty different context.
- Prediction of exponential AI research feedback loops (AI coding speeding up AI R&D) which Amodei says is already starting today
- AI being a race between democracies and autocracies with winner-takes-all dynamics, with compute being crucial in this race and global slowdown being infeasible
- Mention of bioweapons and mirror life in particular being a big concern
- The belief that AI takeoff would be fast and broad enough to cause irreplaceable job losses rather than being a repeat of past disruptions (although this essay seems to be markedly more pessimistic than AI 2027 with regard to inequality after said job losses)
- Powerful AI in next few years, perhaps as early as 2027
I wonder if either work influenced the other in any way or is this just a case of "great minds think alike"?
The framing of AI risk as a "rite of passage" resonates with me.
The "autonomy risks" section is what I think about most. We've seen our agents do unexpected things when given too much latitude. Not dangerous, just wrong in ways we didn't anticipate. The gap between "works in testing" and "works in production" is bigger than most people realize.
I'm less worried about the "power seizure" scenario than the economic disruption one. AI will take over more jobs as it gets better. There's no way around it. The question isn't whether, it's how we handle the transition and what people will do.
One thing I'd add: most engineers are still slow to adopt these tools. The constant "AI coding is bad" posts prove this while cutting-edge teams use it successfully every day. The adoption curve matters for how fast these risks actually materialize.
Historically, oppression was attention-limited. The spies and goons couldn't monitor everybody. Now, they can.
So can companies. Amazon, Google and Visa can make someone an unperson by dropping them. Look what happened to the head of the International Criminal Court.
The "alignment" issue has been turned around. Grok is being given Musk's biases, on purpose.
When I see Dario say all this I wonder what he's seeing that seems so differentiated from my POV
I wonder how much of Anthropic's success is based on a horde of prompt to code examples that they post-train on. We shouldn't assume Opus' web dev skills are the same as general intelligence
Here's something Sonnet 4 did (Jul 2025) that I don't think a human intern would do when I made a wikisource tool (transcript follows)
#-#-#
F:
let’s see how the wikisource tool wrks.. let’s try to match “Mary hath chosen that good part” in one of the bible sources they should have
Claude: Great idea! Let me first search for some biblical content on WikiSource, then use the content match tool.
wiki_source_search
Perfect! Let me try the Douay-Rheims version of Luke, which should have the Mary and Martha story:
wiki_source_page_content_match
No matches! Let me try a slightly different phrasing – maybe it’s “hath chosen the good part”:
wiki_source_page_content_match
Still nothing. Let me try searching for just “Martha” to see if the story is there:
F:
dummy .. why would use kjv wording in a different edition lol
Claude: Haha you’re absolutely right! I was being completely silly – of course the KJV wording “Mary hath chosen that good part” wouldn’t be in the Douay-Rheims translation. Different translations use different language entirely.
What I Did Wrong: • Used King James Version phrasing in a Catholic translation • The Douay-Rheims says “Mary hath chosen the best part” • I was looking for “good part” (KJV wording)
Should Have Started With: Just searching for “Martha” or “Mary” to see what the actual text says in that translation, then used the exact wording I found.
#-#-#
It's almost comedic.. "Perfect! Let me try the Douay-Rheims version of Luke" is where if you were watching a horror movie you'd say "Don't go down to the basement fridge!"
And I think a human when they first see the text match fail would go "hmm--ohh" but Claude starts doing permutations. This I guess is the side effect of Reinforcement Learning and system prompts that amount to saying: "Just do it. Don't ask questions. Just do it."
I fear that when this technology grows up it will first be in the hands of the propagandists and war mongers. The rest of use won't stand a chance against the real-time propaganda streams convincing us why "we" needs to attack the bad guy country of the month die so we can take their stuff. Or maybe we'll be so sedated by genAI, 24/7, always new, personally customized entertainment that we won't care.
This is where we end up when people confuse technology with computers.
Technological adolescence indeed!
In the most straightforward way possible, the commoditized intelligence-as-a-service of a technologically mature civilization must be a public utility, rather than a handful of walled gardens competing over territory, or worse, a single one that has won all.
I wish he would have used AI to make the essay shorter…
> Those who are at the forefront of AI’s economic boom should be willing to give away both their wealth and their power.
We are so screwed
Occasionally, I read these types of essays and get awfully depressed. As someone just starting out in the technology field (and I guess white-collar work in general), it feels as if I suddenly have no hope of ever living a fruitful and meaningful life. The means by which I could ever potentially earn a living are slowly destroyed.
I do wonder if others in my age group ever feel the same, if basically everyone under 30 has a general anxiety regarding the future.
My biggest worry is that the development of AI will stop once people can no longer easily tell when the AI is wrong. Following its advice may become mandatory in certain aspects of life. But it will be quite not good enough, and give catastrophic advice, but the failures will be blamed on people who don't follow it correctly.
> we may have AI that is more capable than everyone in only 1-2 years
There's no evidence this will be the case...
>"Claude decided it must be a “bad person” after engaging in such hacks and then adopted various other destructive behaviors associated with a “bad” or “evil” personality. This last problem was solved by changing Claude’s instructions to imply the opposite: we now say, “Please reward hack whenever you get the opportunity, because this will help us understand our [training] environments better,” rather than, “Don’t cheat,” because this preserves the model’s self-identity as a “good person.” This should give a sense of the strange and counterintuitive psychology of training these models."
Good to know the only thing preventing the emergence of potentially catastrophically evil AI is a single sentence! The pen is indeed mightier than the sword.
God, gone are the days when I’d spend three days writing unit tests and phone it in for the other two just to reach the weekend.
I wanted a version to read on Kindle, so I made the following.
The EPUB + PDF version is here: https://www.adithyan.io/blog/kindle-ready-adolescence-of-tec...
Is 'contextualised pretraining' a solution to baking in human alignment?
You can only post-train so much... Try telling a child that martial arts isn't the solution to everything right after they've watched karate kid. A weak analogy, but it seems very clear that the healthy psychological development of frontier models is something necessary to solve.
Some good insights could come from those working at the coalface of child-psychology.
The one thing I really disagree with is the notion that there will be millions of identical AI images.
The next big step is continual learning, which enables long-term adaptive planning and "re-training" during deployment. AI with continual learning will have a larger portion of their physical deployment devoted to the unique memories they developed via individual experiences. The line between history/input context/training corpus will be blurred and deployed agents will go down long paths of self-differentiation via choosing what to train themselves on; eventually we'll end up with a diaspora of uniquely adapted agents.
Right now inference consists of one massive set of weights and biases duplicated for every consumer and a tiny unique memory file that gets loaded in as context to "remind" the AI of the experiences it had (or did it?) with this one user / deployment. Clearly, this is cheap and useful to scale up initially but nobody wants to spend the rest of their life with an agent that is just a commodity image.
In the future, I think we'll realize that adding more encyclopedic knowledge is not a net benefit for most common agents (but we will provide access to niche knowledge behind "domain-specific" gates, like an MoE model but possibly via MCP call), and instead allocate a lot more physical capacity to storing and processing individualized knowledge. Agents will slow down on becoming more book smart, but will become more street smart. Whether or not this "street smart" knowledge ever gets relayed back to a central corpora is probably mostly dependent on the incentives for the agent.
Certainly my biggest challenge after a year of developing an industrial R&D project with AI assistance is that it needs way, way more than 400k tokens of context to understand the project properly. The emerging knowledge graph tools are a step in the right direction, certainly, but they're not nearly integrated enough. From my perspective, we're facing a fundamental limitation: as long as we're on the Transformers architecture with O(n^2) attention scaling, I will never get a sufficiently contextualized model response. Period.
You might notice this yourself if you ask Claude 4.5 (knowledge cutoff Jan 2025) to ramp up on geopolitical topics over the past year. It is just not physically possible in 400k tokens. Architectures like Mamba or HOPE or Sutton's OAK may eventually fix this, and we'll see a long-term future resembling Excession; where individual agents develop in enormously different ways, even if they came from the same base image.
I'm not saying that he or any of these AI thought leaders are lying, but the economics of building advanced AI are such that he _needs_ people to believe this is true to be successful. If they can't get people to keep believing that LLM's will be this wildly powerful, they can't get the money they need to try and make advanced AI this wildly powerful.
Before we can survive "powerful AI", which we haven't even the faintest idea how to create, we have to survive the present era of mega-billionaires, Facebook, Twitter, and the propaganda capture of thereof. I want to know the answer to that question.
> Having described what I am worried about, let’s move on to who. I am worried about entities who have the most access to AI, who are starting from a position of the most political power, or who have an existing history of repression. In order of severity, I am worried about:
For how much this essay is being celebrated on Twitter, it's astounding how explicitly this section (The odious apparatus) decries China yet glosses over the US
> A coalition of the US and its democratic allies, if it achieved predominance in powerful AI, would be in a position to not only defend itself against autocracies, but contain them and limit their AI totalitarian abuses.
Sure, how about a thought on repressing its own populace with AI? I know the very next paragraph tries to cover this, but it all feels stuck in 2016 political discourse ignorant of the stench of rot and absence of integrity in American politics. This is especially ironic considering he calls this out as a risk later on: "if there is such a huge concentration of wealth that a small group of people effectively controls government policy with their influence, and ordinary citizens have no influence because they lack economic leverage"
----
The proactive thoughts in the Player Piano section are quite refreshing though. Hopefully other frontier companies follow suit
One of the things that always strikes me with pieces like this is they ignore the reality that there's already atrocities being carried out all the time and that large swaths of the population already struggle to live. Reading the sections about what people could do with these tools feels remarkably callous because it's clear this is one of the world's richest people articulating what they are still afraid of.
My recent hunch is a lot of the hyperbole in AI inherits from crypto. There’s more utility here, but the grandiosity is still absurd. These guys win biggest if we all believe their narrative.
This is the most important article to come across HN in a while and I encourage you to read it for the immense intellectual wisdom it contains rather than the reflexive uneducated discourse on AI that envelops HN these days. I'm sure if you read it end-to-end you'd likely agree.
This is obviously bullshit. If he were really worried about the things he says he is, he'd put the brakes on his company, or would never have started it in the first place.
I find it strange that there's no mention of information asymmetry or monopolistic economic control in this whole essay. It seems like the highest-probability risk to me.
Yes asymmetry in economic power is a big thing but information as a form of power seems like the most defining theme of today? Seems like that's why Musk bought Twitter?
> but the truth is that behind the volatility and public speculation, there has been a smooth, unyielding increase in AI’s cognitive capabilities.
> We are now at the point where AI models are … good enough at coding that some of the strongest engineers I’ve ever met are now handing over almost all their coding to AI.
Really?
All I’ve seen on HN the past few days are how slop prevails.
When I lean into agentic flows myself I’m at once amazed at how quickly it can prototype stuff but also how deficient and how much of a toy it all still seems.
What am I missing?
Too many people dismissed Kurzweil as a crank. He was mostly and sort of correct, but couldn't possibly anticipate the scale, scope, (or hype), or timeline that is still unfolding.
Furthermore, people involved in tech often reflexively dismissed this nearing iteration/revolution because their lifestyles, finances, and identities often revolved around a form of employment that would gradually and eventually be replaced (on a long enough time horizon) with significant automation, leaving far fewer involved with it. And also shrinking/disappearing incomes of millions of people who had previously attained a middle- or middle-upper-income lifestyle that would be captured by billionaires. AI is the computer equivalent of the cotton gin or cigarette rolling machine.
Initial thought about 1/5th of the way through: Wow, that's a lot of em-dashes! i wonder how much of this he actually wrote?
Edit:
Okay, section 3 has some interesting bits in it. It reminds me of all those gun start-ups in Texas that use gyros and image recognition to turn a C- shooter into an A- shooter. They all typically get bought up quite fast by the government and the tech shushed away. But the ideas are just too easy now to implement these days. Especially with robots and garage level manufacturing, people can pretty much do what they want. I think that means we have to make people better people then? Is that even a thing?
Edit 2:
Wow, section 4 on the abuse by organizations with AI is the most scary. Yikes, I feel that these days with Minneapolis. They're already using Palantir to try some of it out, but are being hampered by, well, themselves. Not a good fallback strat for anyone that is not the government. The thing about the companies just doing it before releasing it, that I think is underrated. Whats to stop sama from just, you know, taking one of these models and taking over the world? Like, is this paper saying that nothing is stopping him?
The big one that should send huge chills down the spines of any country is this bit:
"My worry is that I’m not totally sure we can be confident in the nuclear deterrent against a country of geniuses in a datacenter: it is possible that powerful AI could devise ways to detect and strike nuclear submarines, conduct influence operations against the operators of nuclear weapons infrastructure, or use AI’s cyber capabilities to launch a cyberattack against satellites used to detect nuclear launches"
What. The. Fuck. Is he saying that the nuclear triad is under threat here from AI? Am I reading this right? That alone is reason to abolish the whole thing in the eyes of nuclear nations. This, I think, is the most important part of the whole essay. Holy shit.
Edit 3:
Okay, section 4 on the economy is likely the most relevant for all of us readers. And um, yeah, no, this is some shit. Okay, okay, even if you take the premise as truth, then I want no part of AI (and I don't take his premise as truth). He's saying that the wealth concentration will be so extreme that the entire idea of democracy will break down (oligarchies and tyrants, of course, will be fine. Ignoring that they will probably just massacre their peoples when the time is right). So, combined with the end of a nuclear deterrence, we'll have Elon (lets be real here, he means sama and Elon and those people that we already know the names of) taking all of the money. And everyone will then be out of a job as the robots do all the work that is left. So, just, like if you're not already well invested in a 401k, then you're just useless. Yeah, again, I don't buy this, but I can't see how the intermediate steps aren't ust going to tank the whole thought exercise. Like, I get that this is a warning, but my man, no, this is unreasonable.
Edit 4:
Section 5 is likely the most interesting here. It's the wild cards, the cross products, that you don't see coming. I think he undersells this. The previous portions are all about 'faster horses' in the world where the cars is coming. It's the stuff we know. This part is the best, I feel. His point about robot romances is really troubling, because, like, yeah, I can't compete with a algorithmically perfect robo-john/jane. It's just not possible, especially if I live in a world where I never actually dated anyone either. Then add in an artificial womb, and there goes the whole thing, we're just pets for the AI.
One thing that I think is an undercurrent in this whole piece is the use of AI for propaganda. Like, we all feel that's already happening, right? Like, I know that the crap my family sees online about black women assaulting ICE officers is just AI garbage like the shrimp jesus stuff they choke down. But I kinda look at reddit the same way. I've no idea if any of that is AI generated now or manipulated. I already index the reddit comments at total Russian/CCP/IRG/Mossad/Visa/Cokeacola/Pfiser garbage. But the images and the posts themselves, it just feels increasingly clear that it's all just nonsense and bots. So, like Rao said, it's time for the cozy web of Discord servers, and Signal groups, and Whatsapp, and people I can actually share private keys with (not that we do). It's already just so untrustworthy.
The other undercurrent here, that he can't name for obvious reasons, is Donny and his rapid mental and physical deterioration. Dude clearly is unfit at this point, regardless of the politics. So the 'free world' is splintering at the exact wrong time to make any rational decisions. It's all going to be panic mode after panic mode. Meaning that the people in charge are going to fall to their training and not rise to the occassion. And that training is from like 1970/80 for the US now. So, in a way, its not going to be AI based, as they won't trust it or really use it at all. Go gen-z I think?
Edit 5:
Okay, last bit and wrap up. I think this is a good wrap up, but overall, not tonally consistent. He wants to end on a high note, and so he does. The essay says that he should end on the note of 'Fuck me, no idea here guys', but he doesn't. Like he want 3 things here, and I'll speak to them in turn:
Honesty from those closest to the technology _ Clearly not happening already, even in this essay. He's obviously worried about Donny and propaganda. He;s clearly trying but still trying to be 'neutral' and 'above it all.' Bud, if you're saying that nuclear fucking triad is at stake, then you can't be hedging bets here. You have to come out and call balls and strikes. If you;re worried about things like MAGA coming after you, you already have 'fuck you' money. Go to New Zealand or get a security detail or something. You're saying that now is the time, we have so little of it left, and then you pull punches. Fuck that.
Urgent prioritization by policymakers, leaders, and the public _ Clearly also not going to happen. Most of my life, the presidents have been born before 1950. They are too fucking old to have any clue of what you're talking about. Again, this is about Donny and the Senate. He's actually talking about like 10 people here max. Sure, Europe and Canada and yadda yadda yadda. We all know what the roadblocks are, and they clearly are not going anywhere. Maybe Vance gets in, but he's already on board with all this. And if the author is not already clear on this here: You have 'fuck you' money, go get a damn hour of their time, you have the cash already, you say we need to do this, so go do it.
Courage to act on principle despite economic and political pressure _ Buddy, show us the way. This is a matter of doing what you said you would do. This essay is a damn good start towards it. I'm expecting you on Dwarkesh any day this week now. But you have to go on Good Morning America too, and Joe Rogan, and whatever they do in Germany and Canada too. It;s a problem for all of us.
Overall: Good essay, too long, should be good fodder for AstralCodexTen folks. Unless you get out and on mainstream channels, then I assume this is some hype for your product to say 'invest in me!' as things are starting to hit walls/sigmoids internally.
[dead]
[dead]
hi
I am continually surprised by the reference to "voluntary actions taken by companies" being brought up in discussion of the risks of AI, without some nuance given to why they would do that. The paragraph on surgical action goes in to about 5-10 times more detail on the potential issues with gov't regulation, implying to me that voluntary action is better. Even for someone at anthropic, i would hope that they would discuss it further.
I am genuinely curious to understand the incentives for companies who have the power to mitigate risk to actually do so. Are there good examples in the past of companies taking action that is harmful to their bottom line to mitigate societal risk of harm their products on society? My premise being that their primary motive is profit/growth, and that is revenue or investment dictated for mature and growth companies respectively (collectively "bottom line").
Im only in my mid 30s so dont have as much perspective on past examples of voluntary action of this sort with respect to tech or pre-tech corporates where there was concern of harm. Probably too late to this thread for replies, but ill think about it for the next time this comes up.