I understand that a typical HN user is very different from the average person.
However, surely by now even the lay people who have seen the testimonies before Congress, the lawsuits and the excesses by Meta execs over and over again ought to be atleast somewhat wary of handing them more personal data?
I think the average person has very similar self preservation instincts as the rest of us. So it can't be that. Which leaves the fact that there are lot of people who don't know about the above mentioned scandals galore that Meta has been involved in?
This "holier than thou" attitude in this comment is precisely the reason why HN users have largely misunderstood tech trends and desires by the general public.
This is one of the books that left me with the most profound sense of unease. And it deserves very high prait for being able to do that.
While people might remember it for other more striking ideas, I was impressed with how it expounds the theory behind the claims that "intelligence implies violence". That entire narrative was quite chilling.
That, and the way the author explains how to establish a means of communication using just... pain.
It's interesting that "story of your life" By Ted Chiang has also military meeting aliens whom are squids and the process of developing understanding is very very different. One tries to find common understanding, the other uses torture.
I read it every couple of years and it makes me feel weird for several weeks at a time. Like nothing is real, nothing matters, I'm not really here. I eventually snap out of it, but it's an odd feeling.
The Three Body Trilogy was absolutely packed with fantastic and original ideas, and explained/presented in ways that flowed well with the story. That's how I found it anyway. I very much enjoyed all three Three Body Problem books. Also very much enjoyed Blindsight.
If not sarcasm, I feel sorry for your not being able to extract joy from any of those books, and hope there are others that tickle your fancy that maybe the HN readership might like to know about. Going by your email address, I'd guess that maybe Accelerando might do it?
I only read the first book of the trilogy and the "science" in it was so profoundly absurd that I couldn't motivate myself to read any further. I think part of the issue is that it had been sold to me under the guise that it was hard sci-fi, and it was anything but.
I disagree it's unoriginal, though. It's pretty original, you just have to be prepared to suspend your disbelief (it's kind of on me that I wasn't when I read it).
Is it? Maybe I didn't get far enough into the series, but the parts I did read and the synopsis online are all derivative of old ideas. The "dark forest" idea is a very old and much debated solution to the Fermi paradox, and appears in other works (e.g. the wolves in Alastair Reynolds' Revelation Space series). The VR stuff was derivative of dozens of previous works. The rehydration of the solarians is not that different than the spiders freezing in A Deepness in the Sky by Vinge. Plenty of alien invasion and doom cult literature out there (too much, in my opinion).
But I took Dark Forest to mean the Dark Forest Theory which the post I was replying to mentioned, and that's just a common theory under a new name, which has been a commonly known solution to the Fermi paradox for so long that no one is credited with coming up with it. It's given the "deadly probe" name in a SETI review of the Fermi paradox literature in 1984.
My criteria for originality may be more lenient than yours. I think it would be difficult to find sci-fi that isn't derivative of older ideas to an extent, and it's harder for more recent work to stand out, because basically everything's already been done. Managing to combine a dozen ideas from previous works into a coherent whole is far from uncreative. So I feel the author was original enough in his approach, even though I thought it was scientifically inept.
It was an interesting read because it's from a very different culture but at the same time "western" enough to be read comfortably. But it's "science" is just bullshit, both the physics and the sociology.
Your suggestion would break my use case: i.e I check out HN every day to see what the latest models that have been released are, and opinions from erudite people who have taken them for a spin.
Keeping abreast of fast moving AI developments with informed opinions/comments for various new models/agents etc. is primarily what I'm here for.
Right, but my point was about what they said about the use-case. They couldn't have been coming here for AI news since 2017. So did they finally find their use-case for HN some 2 years ago?
If they were indeed coming here before AI revolution, it was a different type of medium.
I have always used HN for consuming tech news. I was trying to say that these days, I really love following the developments in AI and among the most erudite audience for that can be found here, which is great.
You extrapolated that to assuming that AI news was my only use case.
Am saying that a lot of us like HN the way it is, and the way it has evolved organically into a firehose of AI news.
Tbh if you are long enough on hn, quite a lot of stuff gets repeated over and over.
AI gets 'that much' tracktion because it is right now the fastest changing technology we have and with the biggest impact day-to-day for a lot of people on hn.
The CVEs from the last few month? Normal topic for hn, it became an AI toopic because AI found them.
Limiting the flood wouldn't mean necessarily omitting stories like "new model released" (within reason); it'd mean omitting "check out my new vibecoded slop" or "check out this article that's obviously LLM-written and provides very little value" (what we once would have called "blogspam", or dismissed as SEO-bait).
There's no way to reliably filter that "vibecoded slop" or "low value LLM-written article" (BTW what about low value human-written articles?) without users actually interacting with them. And it's actually the votes/flags of said users that determines visibility, so I'd say that's an indication of where the interests of HN's most active users lie.
Joke: it's so proponents who choose to lord their model as better without objective reasoning can call themselves, "Astraholes".
Seriously though the linear planetary naming is pleasant. I do hope the double meaning of "weapon", as you point out, is untrue.
Interestingly, Bruce Schnier just gave a fascinating talk about the Weapon aspect of AI, at DEFCON: https://youtu.be/eEBv0STiYhI very much worth watching
I live in what's probably the outsourcing capital of the world (though I thankfully don't work in those body shops).
I don't think there's going to be a rush to outsource. In fact, I suspect that it's quite the opposite scenario going to play out.
Primarily because now that the cost to produce the boring/mundane stuff that is the stuff of outsourcing (internal tooling, dashboards, ERP, integrations, QA etc.), it will likely be much more cost effective to hire 3 devs in the US and give them hefty token budgets and have much easier coordination and communication loops than outsourcing to a Bangalore body shop that will try and bill you 15 engineers for the same work.
In fact, word on the street here is that there's a significant correction in the Bangalore realty market for the first time in history thanks to the IT salaries drying up. [1]
I suspect LLMs are going to have a global worldwide deflationary effect what with white collar salaries at risk. The only counter acting force might be the distortions caused by recent wars and tariff shenanigans of the US government.
But even having said all of that I am hopeful for the eventual benefits human beings can reap from the advent of LLMS. The only thing that keeps me up at night is my lack of faith in the aging gerontocracy (worldwode phenomenon) that all our futures are in the hands of that seems to be ill equipped to handle this period of what is most likely massive upheaval and uncertainty.
Another way of rephrasing that though is that the public (including large pension funds, retirees, etc.) just dodged a bullet and aren't left holding the bag.
Nevertheless, I doubt anyone's going to emerge unscathed when the valuations start falling though. Vast sections of the American stock market will be wiped out yet and with it the global economy.
Why do you assume 2-3 American companies failing will have a more negative impact on the economy than positive impact of the widespread availability of self-hostable, open-sourced, and efficient models?
There will surely be tons of new companies that make a business off of hosting these models and even tuning them for specific purposes. Not to mention the massive pricing difference will benefit people who actually utilize them
Firstly, I don't think it will be just 2-3 companies that fail. Due the circular investing between companies in the AI ecosystem, the fallout is going to be much bigger.
Secondly, even with that being true, I think open models are a great net benefit for all mankind in the long run.
I think both of those things are true at the same time.
If what you're saying is true we are moving into an era where rockstar product managers are going to be more in demand than programmers since they can do all of what you mentioned above.
And typically (though not always) product managers have better people skills than programmers and consequently they might be more effective at the "gathering requirements" and "working together" bits you mentioned above.
Even much of the "validating releases" and "testing" parts should also be things that a decent PM should be able to wrangle now by themselves with some LLM agents to assist them. Afterall, why bother about code quality of a testing harness. So long as the PM can keep a coherent test case list and have end to end tests that cover them, programmers can leave that to them as well.
Well, it's true. In a world where code is commoditized, a PM who knows exactly what the customers' needs are will be much more successful than an engineer who does not. Not sure what is controversial about that.
Why not have the customer talk to an llm and iterate on the plan? Many customers will appreciate the 30m back and forth replacing the multiple hour meetings.
People are subtracting a lot of hard parts from their thinking, and think it's simpler than it is. What happens when the test suite isn't testing the real thing? The ci/cd doesn't even start? There is a bug requiring a hot fix ASAP? The code is growing into a nasty meatball and spaghetti dish, and the llms just turn shift it around. What about when the agent starts thinking in circles and neefs guidance to start working?
I'm not a ludite: I use llms every day, but I try not to be a meat proxy. Some one off scripts are vibe coded, but applications need real maintainable code.
My prediction for winners and losers: some companies will lay off a ton of programmers and replace with AI, with short term success but long term big problems. Other companies will use llms to boost productivity, but keep their engineers responsible for the health of the products. Short term gains won't be as impressive, but productivity will be higher and the company will be competitive in the long term.
> Why not have the customer talk to an llm and iterate on the plan?
They already do that, hence the SaaSpocalypse. The hope for these AI companies is that the models get better than engineers such that the answer to all your questions is that the AI will handle it.
One is verifiable, if you don't believe maybe you should ask others in the field too. Or maybe you're just wrong and won't admit it, clutching to your preconceived notions.
A simple Google search found these, maybe you should look harder when looking to verify something instead of dismissal. My judgement is indeed perfect in this comment because, as I said, it is verifiable that it is happening, unless you think that no company at all is building internal tools with AI which would be the counter example to my claim that at least some are. Not even sure what your point is here, because your counter claim is nearly unfalsifiable unless you know every single company's operations in the world.
Highly experienced programmers seem to have a hard time understanding this.
Why do we have tens of thousands of test cases and we still find new errors constantly? Why is our software so bloated and slow? We do we still have security breaches?
LLMs can be useful tools when guided by experts. I don’t think a PM with a dream is going to cut it in the long run.
> Why do we have tens of thousands of test cases and we still find new errors constantly? Why is our software so bloated and slow? We do we still have security breaches?
Do those tests test the right thing?
Adding more features is given higher priority vs optimizing current features.
Arent humans the weakest link in security, click on some random link and enter your credentials because the fake site looks legit.
> The whole point of discovering knowledge is to enjoy the process and share that with the world to create hope an optimisim in it, not to product like a factory.
This is the crux of everything you've written and I strongly disagree. The purpose of knowledge is the sheer power it brings, and if there's factory scale churning out of it, I'll gladly take it.
As a closer analogy, consider this probability (I'll be stealing from the game Stellaris here): let's say a few hundred years later, when we are spacefaring, we discover a vast cache/library of knowledge of an alien civilization, we won't just pass up on exploiting it because we need to "enjoy the process of acquiring it on our own" or "derive the satisfaction of sharing the discovery with others". No, I and I daresay most others will take as much as we can without restraint in a quest to make all our lives better/more enjoyable.
And if that's ok to do, using machine intelligence to mine/grab any new knowledge or new math as Tao is suggesting here should also be acceptable and welcomed.
> This is the crux of everything you've written and I strongly disagree. The purpose of knowledge is the sheer power it brings, and if there's factory scale churning out of it, I'll gladly take it.
Actually, this is the fundamental divide. There are a group of people (like you) who want the world to be one way, and there are a group of people (like me) who think that world is abhorrent. I don't think we should go after that power.
But, I'm glad we got to this point in the discussion because it shows this irreconcilable divide. The truth that most people will never say is that these two groups are enemies and will forever be. They fit into this world because we currently participate in the same global system, but because of this situation, it's an unstable one. And AI is exactly the system that is distilling this antagonism to its limit.
> The purpose of knowledge is the sheer power it brings
A dismal prospect.
When knowledge is acquired at a human scale, and under the influence of a human culture, then extraordinary things can happen. Agriculture, the transistor, Gödel's theorems.
When knowledge is "churned out" at "factory scale" then human flourishing isn't even a by-product.
To all the detractors, I would like to point out that your opinion of kids needing a good human teacher is overfit to your experience of having had some of those growing up.
In third world countries like mine, we grow up with absolutely unqualified teachers who were unable to muster anything but a learnt-by-rote understanding of key concepts.
In hindsight these were just desperate adults trying to eek a living for themselves and their family in an impoverished country and resorting to any means by which to do it: gaming the school system or calling in favours to join school faculty. I bear them no ill will. But we as kids were much worse off for it.
I can assure you that no matter what concerns you may have about hallucinations in LLMs, I can bet everything I have that a reasonably modern model (and I'm thinking in the range of gemini-flash, not Fable) in a well designed harness geared towards tutoring would handily and repeatedly outperform every single teacher I had all throughout my schooling.
Don't let a quest for the perfect ruin what is likely already way better than status quo.
Yes, it's easy to forget context. Especially the time component. Several 100 k children will be born tomorrow. 100+ M in the coming year. Then in six years, almost all of them will hit schools. Schools which are, pervasively, really really bad.
What can we do to help them? Better teacher training? Better new teachers? Better new teacher colleges? Consider the latencies. A decade cohort is 1+ B kids.
So refining intervention safety and efficacy is nice. Especially for development problems. Less so for an acute humanitarian disaster. For maximizing the golden hour in crisis mass-casualty triage. In some literate and numerate sense, most of this last decade's 1+ B kids did not survive our collective care.
> your opinion of kids needing a good human teacher is overfit to your experience of having those growing up
None of the AI stuff has been proven to be safe or effective for kids going thru an extremely important growth time for personality development and relational attachment. Your experience of having bad teachers doesn’t negate that the best way we know to enrich kids lives is to have effective and empathetic human teachers.
I demand that does technological experiments involving children be supervised by someone who understands the ethical and moral effects it can have. Its not like a YouTube video.
We don’t move fast and break things when the things are kids, you maniacs
>I can assure you that no matter what concerns you may have about hallucinations in LLMs, I can bet everything I have that a reasonably modern model (and I'm thinking in the range of gemini-flash, not Fable) in a well designed harness geared towards tutoring would handily and repeatedly outperform every single teacher I had all throughout my schooling.
What are the *social* ramifications of an education system where children learn increasingly from AI tutors, while staring at a screen in a classroom for multiple hours a day?
Children need to spend time interacting with other children, as well as with adults. We have a mountain worth of data that children have become addicted to their devices, why are we doubling down on this by including MORE screen time at such an early age?
>If implemented right
This same argument could be applied to any technology, or policy that has ever been created. But we don't live in a world where people can do things the right way because of any number of externalities that muddies the actual implementation.
Once you have turned crueler than them, you have just made the case for your enemies. And the cycle of violence will keep recurring.
reply