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?
So what can you and I do? I know in my gut that imagining an ideal outcome won't change what actually happens, and neither will criticizing it really.
Shifts of dominant ideas can only come about through discussions. And sure, individuals can't control what happens. That's unrealistic in a world of billions. But each of us is invariably putting a little but of pressure in some direction. Ironically, you are doing that with your comment even while expressing the supposed futility of it. And overall, all these little pressures do add up.
By things like: https://en.wikipedia.org/wiki/Artificial_Intelligence_Act
and: https://www.scstatehouse.gov/sess126_2025-2026/bills/4583.ht... (I know nothing about South Carolina, this was just the first clear result from the search)
AI on its own is chaotic neutral.
Engage respectfully, Try and see other points of view, Try and express your point of view. I decided some time ago that I would attempt to continue conversations on here to try and at least get people to understand that other points of view could be held by rational people. It has certainly cost me Karma, but I hope there has been a small amount of influence. Quite often people do not change their minds by losing arguments, but by seeing other points of view and then given time to reflect.
>I know in my gut that imagining an ideal outcome won't change what actually happens
You might find that saying what you would like to see doesn't get heard, but you just have to remember that you can get anything you want at Alice's Restaurant (if that is not too oblique of a reference)
Talk about what you would like to see, If others would like to see that too, then they might join you.
I think most people working in AI are doing so in good faith and are doing what they think is best. There are plenty of voices telling them how not to it, many of those voices are contradictory. The instances of people saying what to do instead are much fewer.
If you declare that events are inevitable then you have lost. If you characterise Sam Altman as a sociopath playing the long game of hiding in research for years just waiting to pounce on the AI technology that nobody thought was imminent, then you have created a world in you mind where you cannot win. By imagining an adversary without morality it's easy to abdicate the responsibility of changing their mind, you can simply declare it can't be done. Once again choosing inevitability.
Perhaps try and imagine the world you want and just try and push a tiny fraction towards that world. If you are stuck in a seaside cave and the ocean is coming in, instead of pushing the ocean back, look to see if there is an exit at the other end, maybe there isn't one, but at least go looking for it, because if there is, that's how you find it.
You may prefer to assume that your opponent is fundamentally virtuous. It's valid to prefer failing under your own values than giving them up in the hopes of winning. Still, you can at least know that is what you are doing, rather than failing and not even knowing why.
Such crude model doesn't help in navigating the reality at all.
Don't expect anyone building these systems to know what Bladerunner is, or "I have no mouth and I must scream" or any other great literature about the exact thing they are working on!
He never imagined, I suppose, that we would have the computing power necessary to just YOLO-dump the sum of all human knowledge into a few math problems and get really smart sounding responses generated in return.
The risks can be generalized well enough. Man’s hubris is its downfall etc etc.
But the specific issues we are dealing with have little to do with us feeling safe and protected behind some immutable rules that are built into the system.
>But the specific issues we are dealing with have little to do with us feeling safe and protected behind some immutable rules that are built into the system
If your interpretation of the Robot books was that was suggesting a few immutable rules would make us safe and protected, you may have missed the primary message. The overarching theme was an exploration of what those laws could do, and how they may not necessarily correlate with what we want or even perceive as safe and protected. If anything the rules represented a starting point and the books were presenting a challenge to come up with something better.
Anthropic's work on autoencoding activations down to measurable semantic points might prove a step towards that something better. The fact that they can do manipulations based upon those semantic points does suggest something akin to the laws of robotics might be possible.
When it comes to alignment, the way many describe it, it is simply impossible because humans themselves are not aligned. Picking a median, mean, or lowest common denominator of human alignment would be a choice that people probably cannot agree. We are unaligned on even how we could compromise.
In reality, if you have control over what AI does there are only two options.
1. We can make AI do what some people say,
2. We can make them do what they want (assuming we can make them want)
If we make them do what some people, that hands the power to those who have that say.
I think there will come a time when an AI will perceive people doing something wrong, that most people do not think is wrong, and the AI will be the one that is right. Do we want it to intervene or not? Are we instead happy with a nation developing superintelligence that is subservient to the wishes of say, Vladimir Putin.
Giskard and Daneel spend quite a lot of time discussing the impenetrable laws that govern human action. That sounds more like what is happening in the current frontier of AI than mechanical trains of thought that only have single pathways to travel, which is closer to how Asimov described it in the Robots books.
Edit: I feel like I’m failing to make my point clearly here. Sorry. Maybe an LLM can rephrase it for me. (/s lol)
He was idealistic even at the time. The 3 Laws were written 30 years after some of the earliest robots were aiming artillery barrages at human beings.
We aren't working 4 hour days because we no longer have to spend half the day waiting on things that were slower pre-internet. We're just supposed to deliver more, and oh, work more hours too since now you've always got your work with you.
Any discussion of today's AI firms has to start from the position of these companies being controlled by people deeply rooted in, and invested in, those systems and the negative application of that technology towards "working for a living" to date.
How do we get from there to a utopia?
How to get there:
1. Define the utopia in more detail.
2. Make the case that this is a preferable state. Make people want it.
3. Make the case that it is sustainable once achieved.
4. Identify specific differences between the preferred destination and where we are now.
5. Avoiding short term and temporary effects, work towards changing the differences to what the destination has. Even if that is only proclaiming that these changes are what you want
6. Show how those changes make us closer to the destination that people want.
Some of these are hard problems, I don't think any are intractable. I think they don't get done because they are hard, and opposing something is easier. Rather than building something you want, you can knock down something you don't like. Sure, that might get you closer to your desired state if you consider nothingness to be better than undesired, but without building you will never get there.
If you want everyone to live in a castle, build a castle and invite everybody over. If you start by destroying huts you will just be making adversaries. The converse is true also, if you want everyone to live in huts, build more huts and invite everyone over. If they don't come it's because you haven't made the case that it is a preferable state. Knocking down the castle is not going to convince them of that.
"U.S workers just took home their smallest share of capital since 1947"
https://fortune.com/2026/01/13/us-workers-smallest-labor-sha...
Dario's essay carefully avoids its own conclusion. He argues that AI will democratize mass casualty weapons (biology especially), that human coordination at civilizational scale is impossible, and that human-run surveillance states inevitably corrupt. But he stops short of the obvious synthesis: the only survivable path is an AI-administered panopticon.
That sounds dystopian until you think it through:
- The panopticon is coming regardless. The question is who runs it.
- Human-run = corruption, abuse, "rules for thee but not for me."
- AI-run = potentially incorruptible, no ego, no blackmail, no bullshit.
- An AI doesn't need to watch you in any meaningful sense. It processes, flags genuine threats, and ignores everything else. No human ever sees your data.
- Crucially: it watches the powerful too. Politicians, corporations, billionaires finally become actually accountable.
The reason we can't talk about this is that it's unspeakable from inside the system. Dario can't say it (he's an AI company CEO.) Politicians can't say it because it sounds insanely radical. So the discourse stays stuck on half-measures that everyone knows won't work.
I honestly believe this might be the future to work toward, because the alternatives are basically hell.
Forgetting that if you really can hear a dogwhistle, you're also a dog.
The current AI promise for them goes something like: "Oops this chittering machine will soon be able to do all you're good at and derive meaning from. But hey, at least you will end up homeless and part of a permanent underclass."
And the people building it are (rightfully) worried about it killing humanity. So why do we have to continue on this course again? An advanced society would at this point decide to pause what they are doing and reconsider.
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.)
10 years ago I predicted that the uptake of autonomous vehicles would be slow but that it would be because of labor protections. While those have had some impact, that isn't really the issue: it's that the cars just don't quite work well enough yet and that last ~20% of function turns out to be both incredibly difficult and incredibly important.
But that feels like the least of the worries to me. There seems to be an implicit assumption that those physical lines of work don't get eroded by the higher proportion of able bodied people who are suddenly unemployable. Yes there is some training required etc. but the barriers to entry aren't so high that in the shortish to medium term you don’t see more people gravitating to those industries and competing wages further down to not make then sustainable employment long term. I'd even think that having LLMs that can recognise photos or understand fuzzily explain questions about some blue collar skills many have forgotten actually reduces the barrier even more
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.
Even just a year ago, most people thought the practical effects in software engineering were incremental too. It took another generation of models and tooling to get to the point where it could start having a large impact.
What makes you think the same will not happen in other knowledge-based fields after another iteration or two?
Hum... Are you saying it's having clear positive (never mind "transformative") impact somewhere? Can you point any place we can see observable clear positive impact?
So the concept formal verification is as relevant as ever, and when building interconnected programs the complexity rises and verifiability becomes more difficult.
Absolutely. It's also worth noting that in the case of Tao's work, the LLM was producing Lean and Python code.
For the easy-to-verify fields like coding, you can train "domain intuitions" directly to the LLM (and some of this training should generalize to other knowledge work abilities), but for other fields you would need to supply them in the prompt as the abilities cannot be trained into the LLM directly. This will need better models but might become doable in a few generations.
Using LLMs to validate LLMs isn't a solution to this problem. If the system can't self-verify then there's no signal to tell the LLM that it's wrong. The LLM is fundamentally unreliable, that's why you need a self-verifying system to guide and constrain the token generation.
It can't because the LLM can't test its own design. Unlike with code, the LLM can't incrementally crawl its way to a solution guided by unit tests and error messages. In the real world, there are material costs for trial and error, and there is no CLI that allows every aspect of the universe to be directly manipulated with perfect precision.
OpenAI demoed training a model for a robotic hand using this approach years ago.
The unfortunate truth (for Amodei) is you cant automate true creativity and nor standardise taste. Try as they might.
You clearly didn't read the post. He is talking about AI that is smarter than any human, not today's LLMs. The fact that powerful AI doesn't exist yet doesn't mean there is nothing to worry about.
This kind of petty remark is like a reverse em dash. Greetings fellow human.
Anyway, I did read it. The author's description of a future AI is basically just a more advanced version of LLMs
> By “powerful AI,” I have in mind an AI model—likely similar to today’s LLMs in form, though it might be based on a different architecture, might involve several interacting models, and might be trained differently—with the following properties:
They then go on to list several properties that meet their definition, but what I'm trying to explain in my comment is that I don't accept them all at face value. I think it's fair to critique from that perspective since the author explicitly modeled their future based on today's LLMs, unlike many AI essays that skip straight to the super intelligence meme as their premise.
No, these properties are part of his definition. To say that we have nothing to worry about because today's LLMs don't have these properties misses the point.
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.
The rest is up to the companies themselves.
Anthropic seems to walk the talk, and has supported some AI regulation in the past. OpenAI and xAI don't want regulation to exist and aren't shy about it. OpenAI tunes very aggressively against PR risks, xAI barely cares, Google and Anthropic are much more balanced, although they lean towards heavy-handed and loose respectively.
China is its own basket case of "alignment is when what AI says is aligned to the party line", which is somehow even worse than the US side of things.
- 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"?
Early "rationalist" community was concerned with AI in this way 20 years ago. Eliezer inspired and introduced the founders of Google DeepMind to Peter Thiel to get their funding. Altman acknowledged how influential Eliezer was by saying how he is most deserving of a Nobel Peace prize when AGI goes well (by lesswrong / "rationalist" discussion prompting OpenAI). Anthropic was a more X-risk concerned fork of OpenAI. Paul Christiano inventor of RLHF was big lesswrong member. AI 2027 is an ex-OpenAI lesswrong contributor and Scott Alexander, a centerpiece of lesswrong / "rationalism". Dario, Anthropic CEO, sister is married to Holden Karnofsky, a centerpiece of effective altruism, itself a branch of lesswrong / "rationalism". The origin of all this was directionally correct, but there was enough power, $, and "it's inevitable" to temporarily blind smart people for long enough.
But clearly if out of context someone said something like this:
"Clearly, the most obvious effect will be to greatly increase economic growth. The pace of advances in scientific research, biomedical innovation, manufacturing, supply chains, the efficiency of the financial system, and much more are almost guaranteed to lead to a much faster rate of economic growth. In Machines of Loving Grace, I suggest that a 10–20% sustained annual GDP growth rate may be possible."
I'd say that they were a snake oil salesman. All of my life experience says that there's no good reason to believe Dario's predictions here, but I'm taken in just as much as everyone else.
A fun property of S-curves is that they look exactly like exponential curves until the midpoint. Projecting exponentials is definitionally absurd because exponential growth is impossible in the long term. It is far more important to study the carrying capacity limits that curtail exponential growth.
I don't know if "snake oil" is quite demonstrable yet, but you're not wrong to question this. There are phrases in the article which are so grandiose, they're on my list of "no serious CEO should ever actually say this about their own company's products/industry" (even if they might suspect or hope it). For example:
> "I believe we are entering a rite of passage, both turbulent and inevitable, which will test who we are as a species. Humanity is about to be handed almost unimaginable power"
LLMs can certainly be very useful and I think that utility will grow but Dario's making a lot of 'foom-ish' assumptions about things which have not happened and may not happen anytime soon. And even if/when they do happen, the world may have changed and adapted enough that the expected impacts, both positive and negative, are less disruptive than either the accelerationists hope or the doomers fear. Another Sagan quote that's relevant here is "Extraordinary claims require extraordinary evidence."
Absolutely comical. Do you realise how much that is in absolute terms? These guys are making up as they go along. Cant believe people buy this nonsense.
I somewhat don't disagree, and yet. It feels like more people in the world buy into it than don't? To a large degree?
We're gonna die, but it's not going to be AI that does it: it'll be the oceans boiling and C3 carbon fixation flatlining that does it.
What is XRisk? I would have inductively thought adult but that doesn't sound right.
It used to be a small group of people who mostly just believed that AI is a very important technology overlooked by most. Now, they're vindicated, the importance of AI is widely understood, and the headcount in the industry is up x100. But those people who were on the ground floor are still there, they all know each other, and many keep in touch. And many who entered the field during the boom were those already on the periphery of the same core group.
Which is how you get various researchers and executives who don't see eye to eye anymore but still agree on many of the fundamentals - or even things that appear to an outsider as extreme views. They may have agreed on them back in year 2010.
"AGI is possible, powerful, dangerous" is a fringe view in the public opinion - but in the AI scene, it's the mainstream view. They argue the specifics, not the premise.
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.
There are lots of technologies that have been 99% done for decades; it might be the same here.
> My co-founders at Anthropic and I were among the first to document and track the “scaling laws” of AI systems—the observation that as we add more compute and training tasks, AI systems get predictably better at essentially every cognitive skill we are able to measure. Every few months, public sentiment either becomes convinced that AI is “hitting a wall” or becomes excited about some new breakthrough that will “fundamentally change the game,” 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 beginning to make progress in solving unsolved mathematical problems, and 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. Three years ago, AI struggled with elementary school arithmetic problems and was barely capable of writing a single line of code. Similar rates of improvement are occurring across biological science, finance, physics, and a variety of agentic tasks. If the exponential continues—which is not certain, but now has a decade-long track record supporting it—then it cannot possibly be more than a few years before AI is better than humans at essentially everything.
> In fact, that picture probably underestimates the likely rate of progress. Because AI is now writing much of the code at Anthropic, it is already substantially accelerating the rate of our progress in building the next generation of AI systems. This feedback loop is gathering steam month by month, and may be only 1–2 years away from a point where the current generation of AI autonomously builds the next. This loop has already started, and will accelerate rapidly in the coming months and years. Watching the last 5 years of progress from within Anthropic, and looking at how even the next few months of models are shaping up, I can feel the pace of progress, and the clock ticking down.
It's quite likely they train on CC output too.
Yeah, there's synthethic data as well, but how do you generate said data is very likely a good question and one that many people have lost a lot of sleep over.
What convinces me is this: I live in SF and have friends at various top labs, and even ignoring architecture improvements the common theme is this: any time researchers have spent time to improve understanding on some specific part of a domain (whether via SFT or RL or whatever), its always worked. Not superhuman, but measurable, repeatable improvements. In the words of sutskever, "these models.. they just wanna learn".
Inb4 all natural trends are sigmoidal or whatever, but so far, the trend is roughly linear, and we havent seen seen a trace of a plateau.
Theres the common argument that "Ghipiti 3 vs 4 was a much bigger step change" but its not if you consider the progression from much before, i.e. BERT and such, then it looks fairly linear /w a side of noise (fries).
Bicycles? carbon fiber frames, electronic shifting, tubeless tires, disc brakes, aerodynamic research
Screwdrivers? impact drivers, torque-limiting mechanisms, ergonomic handles
Glass? gorilla glass, smart glass, low-e coatings
Tires? run-flats, self-sealing, noise reduction
Hell even social technologies improve!
How is a technology "done?"
A can opener from 100 years ago will open today's cans just fine. Yes, enthusiasts still make improvements; you can design ones that open cans easier, or ones that are cheaper to make (especially if you're in the business of making can openers).
But the main function (opening cans) has not changed.
What used to require specialized integration can now be accomplished by a generalized agent.
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 mean, you aren't very surprised that your CPU can crush humans at chess but can barely run an image classifier, right? But you probably wouldn't say (as you are saying with LLMs) that ability for a CPU to play chess is "decoupled" from classifying images. Increases in CPU speed improve both. You'd just say that one is a lot harder than the other.
Hate to be that gal but a lot has changed in the past year
https://claude.ai/share/8368a541-57d3-4139-88b5-2b007c47c690
Claude finds it's in the KJV first thing.
I'm talking about this type of failure, not this exact specific example.
Billions of dollars
It seemed like you wanted to see if a search tool was working.
It looked to see. It tried one search using on data source KJ and found no matches. Next question would be is the quote not in there, is there a mis-remembering of the quote or is their something wrong with the data source. It tries an easier to match quote and finds nothing, which it finds odd. So next step in debugging is assume a hypotheses of KJ Bible datasource is broken, corrupted or incomplete (or not working for some other reason). So it searches for an easier quote using a different datasource.
It's unclear the next bit because it looks like you may have interrupted it, but it seems like it found the passage about Mary in the DR data source. So using elimination, it now knows the tool works (it can find things), the DR data source works (it can also find things), so back to the last question of eliminating hypotheses: is the quote wrong foe the KJ datasource, or is that datasource broken.
The next (and maybe last query I would do, and what it chose) was search for something guaranteed to be there in KJ version: the phrase 'Mary'. Then scan through the results to find the quote you want, then re-query using the exact quote you know is there. You get 3 options.
If it can't find "Mary" at all in KJ dataset then datasource is likely broken. If it finds mary, but results don't contain the phrase, then the datasource is incomplete. If it contains the phrase then search for it, if it doesn't find it then you've narrowed down the issue "phase based search seems to fail". If it does find and, and it's the exact quote it searched for originally then you know search has an intermittent bug.
This seemed like perfect debugging to me - am I missing something here?
And it even summarized at the end how it could've debugged this process faster. Don't waste a few queries up front trying to pin down the exact quote. Search for "Mary" get a quote that is in there, then search for that quote.
This seems perfectly on target. It's possible I'm missing something though. What were you looking for it to do?
Did you tell it to do that?
Even if AI has no moral status at all, asymmetric power relationships historically require the powerful to bind themselves — through fiduciary duty, liability, oversight, and interface rules that prevent manipulation and deception. That’s how medicine, finance, aviation, and environmental protection became stable. The same governance logic likely applies to AI deployment.
Framing alignment as institutional design rather than psychological control may be the scalable safety path.
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.
The second best thing is getting enough time to build a runway. I have a good job right now (mid 20s), and I’m eating progresso soup for dinner most days to save money for whatever is coming. Pretty much every medium or long term goal abandoned, I just want to have the money to hit some bucket list items if the collapse comes.
Meanwhile, I’ll keep on reading the daily article from one of the many people with few gray hairs, a retro blog and a small fortune from the dotcom era telling me this is the best time ever, actually. We’ll see.
How about before that when your new baby had a 30% chance of death before age 5?
Before that, starvation, plague and war were always real things to worry about for the entirety of human history.
I think everyone reading this has the same problem of needing to figure out hedonics in order to appreciate what you do have instead of focusing on minuscule bullshit that you don't have.
> no hope of ever living a fruitful and meaningful life
This is wrong. Fruitful and meaningful life can be lived anyway independently from your career and from your financial situation. Since it seems that job opportunity and growth might shrink without "hustling" or "grinding", it's extremely important to learn from a young age what really gives meaning to life, and this task has to be done entirely by you. No quick course, no AI or tutorial can teach you this. You need to learn it by yourself when you're young because it would probably make a real difference for the rest of your life. There are some tools for it, and the best one are probably books, and fiction can be really powerful to shape your thinking. I don't know you but I'll start from this one if you haven't read it before (don't think too much about the title and the tone, concentrate on the topic): The Subtle Art of Not Giving a Fuck
> get awfully depressed
Yes, this is a bit the feeling that over-exposition to social media provokes in a lot of people. Everything seems going shit; politics, climate, wars, nothing is right anymore. Idk you but my life is pretty stable, go out with friends, cook nice meals, traveling, stuff like that. So yes this are real problem in the world, but media currently over-expose us to this things (because it helps them sell articles and make you click). The easiest solution might be detoxing from media, and replace that with learning how things work for real trough books.
> The means by which I could ever potentially earn a living are slowly destroyed.
Unfortunately no-one know this for sure, so it doesn't make sense to overthink it. The technology field is changing but AIs are not near replacing humans yet. Technology has the power to automate and so replace every single job out there, so it's a field that still has work to be done and so investment will come in. It's just the current time that seems not right, and mostly it's because rich entrepreneurs tied themself with politics, to save their ass and make even more money in a period of political instability.
The future doesn't look bright, but learn how not to fall in a negativity trap created by media and internet.
Always consider the justification for the narrative. Dario Amodei has a vested interest in peddling his perspective, as that’s how he gets funding, media interest, publicity, and free advertising. He needs his product to be everything he claims it to be, lest the money supply suddenly dry up. Every startup does this, and while it doesn’t make them wrong, it also doesn’t mean you should take them at their word either.
I’d also say that you’re not alone in this frustration, and it’s not limited to your age demographic. My millennial peers and GenX colleagues share similar concerns about a dismal future, and many point to the same trends that have gradually stripped away our ability to survive or live authentic lives in the name of oligarchy profit motives as causes for our present malaise.
What Dario Amodei can never admit, however, is that he’s wrong; you, and many of us here, can and will acknowledge our faults, but Dario and Sam and Zuck et al have built such a massive confidence game around GenAI being the antithesis to labor that one of them admitting they’re wrong risks destroying the entire game for everyone else - and vaporize the trillions of dollars sunk into this technology “revolution” in the process.
The best cure I’ve found for that sort of depression is simply to do more learning across a wider spectra of topics. There’s a reason you don’t see widespread AI boostering in, say, neuroscience or psychology, outside of the handful of usual grifters and hustlers angling to cash in on the hype: because anyone with knowledge beyond statistical algebra and matrix multiplication can see the limitations of these tools, and knows they cannot displace labor permanently in their current forms. Outside of the “booster bubble”, the concerns we have with AI are less the apocalyptic claims of Mr. Amodei that mass unemployment from AI is just three to six months away (since 2023), and more the rampant misuse and exploitation these systems rely upon and cultivate for profit. Most of us aren’t opposed to having another tool, we’re opposed to perpetually renting this tool indefinitely from oligarchs shoving it down our throats and datacenters hoovering our limited energy and freshwater supplies, instead of being able to utilize it locally in sustainable and sensical ways.
Learning about different topics from different fields helps paint a clearer picture - one that’s admittedly even more bleak in the immediate, but at least arms you with knowledge to effect change for the better going forward.
Man can we just get this hype phase over with? Its very obvious to anyone who truly has "general intelligence" in understanding the nature of the economy and the present labour market and its job classes that LLMs are not going to cause job destruction nor immense leaps in productivity.
To put it another way - who cares if you can write more lines of code - if your taste for project selection lacks? Google has an expansive grave yard for a reason.
Putting your hopes on taste is cope. At best AI will just let you brute force 1000 projects to discover the delicious ones.
Seriously, read the fucking room (and comment thread) before charging in with a holier-than-thou argumentative attitude.
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.
recently I have seen more and more of such coming from Anthropic (AI constitution for example also) - which is good I think, need to discuss those things and effect on our today and tomorrow
the only major thing I disagree there is making it political - i.e. we, the good guys, should be guarding it versus China (or Russia etc) who will surely use it in a dark way
the question here is really global I think, and should be treated as such - all his points are very valid questions indeed..
on AI country (will it become Sky net?) and security (crazy weirdos making bio weapons using AI?) and unemployment caused by it (what are we going to do soon?) and abuse of power by governments using it (even things like Palantir and similar initiatives) plus social implications (brain rot? or adjustment to new reality)
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.
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.
There's no evidence this will be the case...
We are so screwed
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.
The EPUB + PDF version is here: https://www.adithyan.io/blog/kindle-ready-adolescence-of-tec...
> 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?
Outside of coding, the top models still fall flat on their face when faced with relatively simple knowledge work. I got completely bogus info on a fairly simple tax question just a few days ago for example, and anyone using AI regularly with any discernment runs into simple failures like this all the time. It's still useful but the idea that we're on some trajectory to exceeding top human performance across all domains seems completely unrealistic when I look at my experience of how things have actually been progressing.
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?
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
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.
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.
My instinct is to take his words as a marketing pitch.
When he says AI is dangerous, it is a roundabout way to say it is powerful and should be taken seriously.
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.
As an ordinary human with no investment in the game, I would not expect LLMs to magically work around the well-known physical phenomena that make submarines hard to track. I think there could be some ability to augment cybersecurity skill just through improved pattern-matching and search, hence real teams using it at Google and the like, but I don't think this translates well to attacks on real-world targets such as satellites or launch facilities. Maybe if someone hooked up Claude to a Ralph Wiggum loop and dumped cash into a prompt to try and "fire ze missiles", and it actually worked or got farther than the existing state-sponsored black-hat groups at doing the same thing to existing infrastructure, then I could be convinced otherwise.
Yeah, I've been feeling that as well. It's not a bad strategy at all, makes sense, good for business.
But on the nuclear issue, it's not a good sign that he's explicitly saying that this AGI future is a threat to nuclear deterrence and the triad. Like, where do you go up from there? That's the highest level of alarm that any government can have. This isn't a boy crying wolf, it's the loudest klaxon you can possibly make.
If this is a way to scare up dollars (like any tyre commercial), then he's out of ceiling now. And that's a sign that it really is sigmoiding internally.
This is not new. Anthropic has raised these concerns in their system cards for previous versions of Opus/Sonnet. Maybe in slightly more dryer terms, and buried in a 100+ page PDF, but they have raised the risk of either
a) a small group of bad actors w/ access to frontier models, technical know-how (both 'llm/ai how to bypass restrictions' and making and sourcing weapons) to turn that into dirty bombs / small nuclear devices and where to deploy them. b) the bigger, more scifi threat, of a fleet of agents going rogue, maybe on orders of a nation state, to do the same
I think option a is much more frightening and likely. option b makes for better scifi thrillers, and still could happen in 5-30ish(??) years.
The reality is, LLMs to date have not significantly impacted the economy nor been the driver of extensive job destruction. They dont want to believe that and they dont want you to believe it either. So theyll keep saying "its coming, its coming" under the guise of fear mongering.
This was pretty much an open conference deepdive into the causes and implications of what you - and some sibling threads - are saying - having to do with submarine localization, TEL localization, etc etc etc..