There's research around finding ways to use them but nothing that is currently viable.
Doing some more research to help make up for my spreading of incorrect info, I did stumble across this - https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5472374/ - it seems like it's a variety of factors that make most HST not really commercially viable for MRI machines at current.
Mitsubishi has even made a small scale MRI machine with HTS - https://www.medicaldesignandoutsourcing.com/worlds-first-3-t... - though I can't find any newer details around it, despite the timeline provided in the article.
https://www.usa.philips.com/a-w/about/news/archive/standard/...
I guess the need is somewhat alleviated by using MRI which seal their helium:
https://www.usa.philips.com/healthcare/resources/landing/the...
Not the revolution people are claiming, but it's a huge gain nonetheless.
3) has already happened. The AI chat bots aren't very smart, but they're clearly capable of some degree of basic reasoning.
https://journals.plos.org/ploscompbiol/article?id=10.1371/jo...
>Could a Neuroscientist Understand a Microprocessor?
>We show that the [neuroscience experimental] approaches reveal interesting structure in the data but do not meaningfully describe the hierarchy of information processing in the microprocessor. This suggests current analytic approaches in neuroscience may fall short of producing meaningful understanding of neural systems, regardless of the amount of data.
https://www.cell.com/cancer-cell/pdf/S1535-6108(02)00133-2.p...
A classic tell of this is people handling out of bounds errors in loops by trying to randomly add or subtract 1 from their for-loop parameters.
I realized that they didn't have a mental model for what a loop did, they had simply memorized the syntax for a loop and were doing advanced pattern matching. Code repeats = write the for-loop syntax I've memorized. And then after seeing that fail with out of bounds exceptions, they learned a new rule: modify the loop parameters and see if that fixes the problem.
When I think about how I write code, or I compare their approach to the other cohort of students I saw, it's a different process. I see in my mind's eye a type of 'machine' that performs the actions that I want to take place. I simulate running that machine in my mind and tweak its design until it works the way I want it to. Only then do I think about syntax and try to translate what's already happening in my mind into source code.
I've seen people get shockingly far into software engineering careers using the pattern matching / guess and check approach. I've wondered if a lot of the handwringing you see on programming forums about the 'leetcode grind' is coming from people who do this pattern matching approach. To them it must seems like the only way to solve these problems is to simply train their internal pattern matching neural networks on huge amounts of examples.
The code that I see GPT generate looks eerily similar to what I saw from those programmers. And that makes sense because I think that functionally they're doing the same thing. Only GPT does it at a superhuman level.
That seems to me to indicate that there's something that at least some humans do with a mental model that our current LLMs lack. If someone figures out how to simulate those mental processes in a computer program I think we'll see a huge inflection point and that's what the original comment (as I read it) is referring to.
at the same time i do feel like pattern matching limits my growth, if i had a complete understanding of a majority of networking principals id be much higher up in my career
As long as it isn't making you feel like a complete fraud, this level of introspection is a good thing imo.
"I know that I know nothing"
There’s all kinds of other things it won’t do until it hears. And touches. Smell and taste might help too I guess!?
As a byproduct it can also be taught truth is what it can verify with sensors.
In fairness and compassion to that crowd, a lot of it comes from the fact that a modern interview for a coveted FAANG job often requires 1-2 LC Medium (or Hard) problems cranked out in 45-60 minutes. Depending on the company and the org, the overall interview loop may well be multiple such one-hour sprints.
It's quite a pressure-cooker of an interview setting. Given that, it's understandable why many people converge on memorizing and brute-force pattern-matching as their interview strategy — if they can just memorize enough, the odds are actually pretty decent. (And the payoff is not bad, either.)
this is all assuming that someone is trying to be productive rather than stop and ponder the abstraction that is a loop and divine its nature in a rigorous way
if the students are having problems with loops, that's not surprising considering that computer science doesn't teach software development skills. like... at all.
Not sure if there is a difference, for sufficiently abstract interpretations of “satisfy the input”
LLMs don't think, they extrapolate. They are a filter, not capable of thought or reason. You can't reason with an LLM but plenty of people have tried and it fooled them well enough.
They would argue "but brains are just that, a big filter".LLMs don't get even close to what unicelulars can handle, and they don't have a brain.
Although I'm pretty sure there are plenty that many people can think of, so it doesn't really detract much from your point.
There hasn’t been a full scale war between major powers since.
https://www.reuters.com/world/europe/ukraine-war-already-wit...
So I would argue they are either neutral or massive negative.
Yet all the major powers have launched multiple, lengthy full scale wars since.
More seriously AI has made lots of things better, it’s really the hype cycle that’s disappointing. More FPS in games just isn’t as exciting as self driving cars. But by the time you can buy a level 5 self driving car the technology will be pedestrian.
Nothing we have currently moves closer to that. Just doing more of the same of the current models will not get you there.
They're level 4 with very severe location and weather limits.
Creating a self driving car which can navigate a dark, rainy parking lot is something we do not know how. Not even in theory. You can't just throw more compute at it. You can't go from a Vickers Type 464 bomb -- one of the most complex bombs in WW II -- to the "Little Boy" by just putting more explosives in there.
Level 5 driving just means it can drive a child or blind person around who can’t take over in an emergency. That’s the difference between Little Boy and a Moab.
However current level 5 cars aren’t something a consumer would buy. A car that refuses to drive in 99% of situations isn’t marketable. The minimum threshold for that might be a car that can only drive in Hawaii, not a large enough market to pay for R&D, but still plenty use for a blind person living in the area.
No, that's what level 4 means. Level 3 can rely on having a driver to switch to, level 4 can't.
The difference between 4 and 5 is that 4 can park and give up under arbitrary circumstances, while 5 has to be able to keep going almost always.
Geofencing is part of the criteria, but a car that can only drive in the USA but can’t drive in Europe still qualifies as level 5.
Similarly a car that refuses to drive in a blizzard but can do everything else is level 5. Being able to drive at night or moderate rain is mandatory however.
That said, there is plenty of slightly different definitions thrown about. I am sure someone is going to argue a car needs to be able to drive in any country to qualify etc etc.
Level 4 cars need a steering wheel to be generally useful. But a limited vehicle like a taxi doesn't need a wheel, no matter whether it's 4 or 5.
I agree with the rest of what you said. Geofencing entire continents isn't about driving ability, and blizzards are an acceptable human-level restriction.
However it looks like this just changed: https://www.nhtsa.gov/sites/nhtsa.gov/files/2022-03/Final-Ru...
“For vehicles designed to be solely operated by an ADS, manually operated driving controls are logically unnecessary.29 To account for this, the NPRM proposed a regulatory scheme in which the affected standards would not assume that a vehicle will always have a driver’s seat, a steering wheel and accompanying steering column, or just one front outboard passenger seating position.”
They are apparently allowing level 4 Taxi to be considered full ADS even if they have additional “Stowed controls” options.
https://unece.org/DAM/trans/doc/2013/wp29grsp/WP.29-161-18e....
I do not recognise the reality you are in.
Navigating dark and rainy parking lots is not hard. At all. Not hard in theory, and not hard in practice either.
We have lidars which work very well in rain. We have cameras with excellent dynamic range. Parking lots are slow environments where everyone moves slowly and you are generally allowed to stop if you are suddenly spooked or need a bit more time to check things.
There are hard problems about self driving cars, but dark and rainy parking lots are not the stumbling block.
Where do you even get this idea?
Let me tell you two harder things about self driving cars: "How many nines do you want in your certainty that the car won't hit anyone?" and "How do you want that proven? With stats or with fault tree analysis, or a mix of both?"
When I say gradually, it's an euphemism, it's an _extremely_ slow process, but it's the global tendency here.
generally what's happening is a combination of:
* making pedestrian zones (i.e. banning)
* deny access to certain types / times (no vans, no old cars, etc.. i.e. also banning)
* reducing roads (i.e. 2 > 1 lane, thus reducing attractivity)
* raising driving prices (the congestion / air quality certificates you mention)
* reducing access to parking (remove places, make them more expensive, etc)You could have said the same thing 40 years ago.
Cities are also more open to changing which rules cars should follow, because the effects of climate change are more visible, and the effects of pulluted air are better known.
Even then, when ChatGPT came out it was a pretty big deal, due to the surprisingly sudden jump in capabilities, at least from the point of view of someone who didn't work in AI and didn't closely watch its progress.
According to Wikipedia, it was "the fastest-growing consumer software application in history, gaining over 100 million users" (in ~2 months).
Which actually highlights a problem in our society that we have to work to be able to afford living instead of living to be able to work on something more meaningful than earning money.
THESE are the companies wielding AI, but this time without nary a "do no evil" in their ethos, long expunged. They are wielding AI with dystopian surveillance and the inputs.
In the era where the Supreme Court has declared them immortal citizens with allegedly the same rights as a real human, except they can't be killed, they can't be imprisoned, they can hop jurisdictions with the filing of a document. They operate under citizens United so there are no limits to their influence on elections and politicians. They can "bribe" with speaking/speech fees. They gain tax breaks that a "real" human can't possibly imagine.
Do you trust Google, especially these days? Do you trust Microsoft, unrepentant sociopathic MBA monopolizers galore? Do you trust Amazon who reduce humans to robots, with the outright stated goal of replacing them someday and churn through human resources at rates that make the Soviet Army in WWII blush?
If a firearm is just a tool and its danger depends on the owner, who is brandishing AI-the-tool?
Uhoh.
Or let me put it a different way: do you think the USSR did not have an industrial base?
And who do you think paid for the construction of the municipal sewer systems in American cities? Like in Chicago where the whole city was raised 4 ft to accomplish it[1].
[1] https://gizmodo.com/chicago-was-raised-more-than-4-feet-in-t...
> And who do you think paid
state resources are always a fraction of the gdp trough whatever form of taxation. larger industrial base means proportional less burden on the society. that is why for example urss imploded, taxation was too high and spent too wastefully on military budget to be sustainable long term, while usa could spend that money on the defense budget, infrastructure, et etc, while still being sutainable from the economy, because the industrial base was so much larger.
Therefore we have sewage systems thanks to capitalism as much as we have cold winters thanks to chimneys.
In fact it's one of the most voluntary systems of organization that are known to man (assuming a government that protects individual rights), unlike other systems which are fundamentally based on coercion and/or, as you alluded to, did not lead to much progress in bettering the human condition.
More funny, if the species (in the long run) wants to survive this wild ride though space on this ball of mud coercion is the only possible answer. I'm trying to doubt it as hard as I can but wanting something to be true doesn't usually make it so.
It's not very different from a world where there aren't registered owners, if you think about it.
Even in complete anarchy, in the best case scenario most people would want the world to function in a similar way, using similar mechanisms. Except that people that couldn't defend themselves or have enough social capital would be even less protected.
So perhaps you wouldn't have an official "registry", but everyone would know which parts of the territory "belongs" to whom anyway. In the worst case, it would lead to a lot more territorial conflict.
Or you could have a government enforcing equal amounts of land for every person, but this would be extremely wasteful for many reasons.
Capitalism is what allows you to globally allocate land in the most efficient way that we know of, just like any other limited resource.
> Like a game of monopoly where one player gets all the streets and all the money and the other player starts with nothing.
Capitalism allows for social / class mobility without coercion. In fact, it's the only system that directly rewards you with upwards social / class mobility in proportion to how much you are helping other humans.
> It is just more coercion, more of the same.
> More funny, if the species (in the long run) wants to survive this wild ride though space on this ball of mud coercion is the only possible answer. I'm trying to doubt it as hard as I can but wanting something to be true doesn't usually make it so.
What are you being coerced into?
Helping other people so that other people also help you getting food cheaply and conveniently so that you don't die, as well as thousands of other goods and services that even the most powerful king of a thousand years ago could not even dream of having?
You don't even have to do that, you could grow your own food and just don't go to the supermarket if you think you are up for it.
Although yes, you would need to get access to some exclusive parcel of land, just like in any alternative system. Most people would not be very happy if you go plant things in their front yard without their permission, no matter which system you live under.
That is the whole game.
If we developed the will to sustainably mitigate its toxic by-products including plastic, that would be another nice black-swan for the future. Though it also won't be singular moment but a systemic change that is hard to notice.
Also, tea making was a huge sanitary step forward.
and you CAN imagine it : Viagra
Penicillin was the first highly effective AND mass producible antibiotic, though.
Electric cars mainstream
'Connections' (1978). https://www.youtube.com/watch?v=2WoDQBhJCVQ
Shoutout to 50 things that made the modern economy, a great podcast/book.
Language, standards, the internet, agriculture, glass, sunscreen, resilient rice, sterilization, human flight, spontaneous development of sentient life in the universe…
When you think about it all, you start to appreciate how miraculous things actually are.
https://www.fon.hum.uva.nl/rob/Courses/InformationInSpeech/C...
Regardless ... people's ignorance is showing. Too many never think about the fact that people just 200-100 years ago would have considered modern technology magic.
Imagine showing off to one of these people:
Omfg you're speaking into a flat rectangle!
Omfg it speaks back!
Omfg it shows pictures!
Omfg that box speaks!
Omfg that box speaks and shows people!
O M F G YOU GUYS FLY EVERY DAY???
WHAT DO YOU MEAN, SYPHILIS ISN'T AN ISSUE ANYMORE??? AND THERE'S A PILL PREVENTING PREGNANCY ???????????
It's absolutely amazing.
Rule-based societies predate the Romans by a lot of time ; Romans weren't even that good at it, considering how often violence was used as a political tool during the republic.
Wouldn't the Code of Hammurabi have preceded that by quite a few centuries?
That's not to say there's not a grain of truth in this perspective. My impression is that Romans were notable for their pioneering work in the field of what could best be described as "civic pride" - the sense that "civilization" represented progress, the idea of the state as a kind of collective project that elevates everyone and that we should all be proud to participate in. They probably weren't the first to think like this - history is long - but they were the last to do so in a largely secular fashion in the West for a long time, and certainly directly influenced the thoughts of the Enlightenment thinkers who eventually inspired the American Revolution.
S.P.Q.R.
The Code of Hammurabi is best understood as royal propaganda designed to portray Hammurabi as a just king. The famous stele starts with a graphic depiction of him receiving the royal rod and ring from Shamash, the sun god who was emblematic of truth and justice. The laws are best understood as a statement of the kind of justice Hammurabi wished to see done in his kingdom, not a set of rules.
Rule-based society is something different: when the Law itself has a power of it's own, stronger than power of any individual or group. It was first invented in Rome and provided them tremendous advantage, until started to crumble during the Long 3rd Century Crisis.
> You may wonder why we don’t use Roman concrete today if that is the case; well, one of the reasons as to why is because, although it gets stronger over time and withstands erosion from water, when this cement is still young and has not had time to develop its strength from seawater, it likely does not have the compressive strength to handle modern use.
https://www.forthvalleyconcrete.co.uk/the-differences-betwee...
Also, Roman concrete didn't contain rebar which is necessary in many modern applications and rebar rusts which reduces the overall lifespan of the structure.
That said, apparently Roman concrete has some potential issues in structures adjacent to bodies of saltwater since the saltwater would accelerate the strengthening process.
Sorry not sorry if I just subjected you to the same.
Auctions, GPS,
Postage stamp, video games,
Public key cryptography,
Shipping containers.
iPhone, pencil,
Clocks and contraceptive pill,
Passports, batteries,
Banking, antibiotics.
Double entry book-keeping,
Canned food, air conditioning,
Razors, solar cells,
Sanitary towels.
Retirement, printing press
And the Haeber-Bosch process
Infant formula,
Exchangeable parts.
Light bulb, concrete,
Sewing machine, spreadsheet,
S-bend, cold chain,
Insurance and dwarf wheat!GPS, disposable razor, these are not impactful enough to be "black swan but good".
And things like clocks and batteries were slowly refined over many, many years, so they don't fit either.
Don’t fall into the trap of reacting with “meh” to everything. Maybe you just don’t know? Maybe you don’t realise how much modern life depends on say, the Haeber-Bosch process or the shipping container? “Oh it’s just a metal box”, a person who doesn’t understand it might say.
Not sure if that's black swan territory or not, but IMO it was a great piece of forward-thinking that made GPS useful beyond just the original military applications.
That sounds strange .. but .. there are many small corrections that need to be applied to "straight forward" triangulated fixing off of moving monuments (term from surveying), relativitic time shift being just one.
There are several recent HN threads about Kalman filters [e].
It's possible (and more or less roughly what already happens) to record GPS fixes against a fixed master station and compute the time series error twixt the naive computation and known location (or, indeed, mesh of locations across (say) Australia and generate a Kalman filter to correct and return more precise positions for moving recievers in the mesh area.
Had we not been aware of relativity we very likely would have discovered it via the time slip 'error' terms in the correction filter.
In a similar manner we have improved our understanding for atmospheric wobble, continental drip [1], and other fine effects.
[1] https://en.wikipedia.org/wiki/Continental_drip
[e] https://hn.algolia.com/?dateRange=pastYear&page=0&prefix=fal...
As so often, the refinement of the technique makes it so widely available and effective that, without being revolutionary in principle, it becomes revolutionary in effect.
Telecommunications is like that. A century ago a telex from Australia to England could make it from desk to desk in under an hour. The Internet is not revolutionary in that sense. And yet it is revolutionary anyway.
I don’t know about that. Maybe it was. What I do know is that we have documented speculation about satelite based navigation the days right after the launch of Sputnik.
American scientist figured out the orbit of Sputnik independently from the Russians by measuring the dopler shift of the radio transmission with their radios. Then knowing where their radio is located they used an iterative optimisation process to identify the orbital parameters of the satelite. Immediately there they were talking about how if the orbit of the satelite were known they could use the same process backwards to fix their location. That was 21 years before the launch of the first GPS satelite.
Now, that is not exactly how GPS signals work, and with good reasons. But it is the first documented seed of the idea of satelite based navigation that I am aware of.
Source: https://secwww.jhuapl.edu/techdigest/Content/techdigest/pdf/...
How informative of you.
GPS does things better but we can do generally the same things without it.
Don't think about what would happen if we ripped out all GPS functionality overnight, think about what would happen if we had a decade to implement replacements.
The loss of accuracy wouldn't be that important.
> the Haeber-Bosch proces
That one's pretty great, it's probably worth including.
> or the shipping container? “Oh it’s just a metal box”, a person who doesn’t understand it might say.
Hmm, focus on cargo ships and you can see a pretty rapid revolution, but in a wider lens maybe it was more of a broad evolution. I'm not sure.
But my point was that the list was too long, not that it didn't have any valid examples.
It goes in depth on the introduction of the shipping container and how revolutionary it was. There was also a fair bit of legal wrangling to make it possible as well.
> And things like clocks and batteries were slowly refined over many, many years, so they don't fit either.
Everything started with a thought, or a discovery. What happens after is irrelevant. The event, that kicks off Dramatic Change(tm), is at the start.
> That's just a list of good inventions.
No. It isn't just a list of good inventions. Ignoring that it's not all inventions, you seem to lack the understanding of the impact. For example:
> Antibiotics
A discovery. It literally changed how humanity moves forward. One of the whitest swan moments in human history.
> public key cryptography
It took until 1975 for someone to figure this out and it changed how we exchange information, legitimize ourselves and deal with our privacy.
> contraceptive pill
The invention of the pill was an event that had massive impact on how Humanity moved forward.
> printing press
The invention of mass production of books lead to the first information explosion, dramatically changing humanity's future.
What you're doing here is mixing your ignorance of the impactfullness of some of the things on the list, with your own personal idea of what's "great", or however you want to call it.
Even if I agree that not everything on that list is equally meaningfull in terms of impact, some of them are really fucking high up the ladder, just like room temperature superconductors.
> > public key cryptography
> It took until 1975 for someone to figure this out
Sketched out in 1874 as a concept by Jevons, firmed up (sans implementation) in 1970, first implemented in 1973 (classified for nigh on 30 years by the UK Govt).
First public example (of a different schema) was 1976.
Other examples worked out in 1974, not published until 1978. etc.
I have no great quibble here, 1975 is a good approximate ballpark figure but I wasn't sure which scheme you had in mind as it's almost the only year in the 1970s that nothing particularly significant happened in public key crypto.
Clocks did not have an event that kicks off a dramatic change. We've had them for thousands of years. I don't see how anyone could disagree with that.
I could see disagreement about batteries, but even then I feel like they were quite marginal for quite a while. A slow buildup is not a "black swan but good". There needs to be quite a lot of suddenness to it all.
And I didn't even mention the ones in the rest of your post so I don't want to argue those.
If you talked about all those because I said "list of good inventions", let me clarify. It's a list of "good or better inventions", mixing ones that qualify as 'black swan but good" with ones that don't.
wat
it's called a black swan because black swans are rare. white swans are quite common. discoveries with the impact of antibiotics are extremely rare.
what, exactly, do you think the term "black swan" means. and why do you think that?
I am wondering though what exactly you think "black swan event" means since your post here makes it rather clear you don't at all understand what the term means or where it comes from either.
Black swans are not at all rare and a "black swan event" is not called that because of the rarity of black swans. Its called that because "black swan" was at one time used to refer to non-existent or impossible things in England then when Australia was discovered they found out black swans are actually extremely common, which was a very unexpected event that couldn't have been predicted from the data available beforehand. Its the discovery of black swans that was unlikely, not black swans, and its the unexpectedness of their discovery happening that is the relevant piece that makes something a "black swan event". [1]
If black swans were rare seeing one would not be a "black swan event" (ironically it would be a white swan event) because it would be possible to predict that one would could be seen, just not very often, making it not have the required unexpectedness.
Please if you are going to be pedantic try to also actually be correct on what you're being a jerk about first.
Military without GPS would be blocked. Try navigating in jungle environments where everything is green and looks the same. I've experienced both with GPS and without, that was one heck of a game changer.
[1] https://qz.com/1106064/the-entire-global-financial-system-de...
ATMs may be designed to use super precise timstamps, but they don't need to be. At all.
The interesting timing constraints are between stock exchanges... but in those situations the speed of light is a bigger factor than clock drift, even if you're just using NTP, and you can't avoid speed of light delays/desyncs.
For stock exchanges you are absolutely correct. I remember many years ago paying so much extra for the fastest internet access and sub-second delay access to our local stock exchange. Even so it was still slower (lag) when compared to those with offices placed very close to the stock exchange building/infrastruture at that time.
Lead acid got us from, what 1940 to 2005? Something like that? But the utility of Lithium Batteries has blown what was already a gigantic market even wider open.
I don't think the passport is an invention itself, so to speak.
Travel like that was never "reserved" for explorers, missionaries or high ranking dignitaries. If you had the money/resources, you could go anywhere.
Now there is a "caste" system of countries that have Visa on Arrival, Free Entry, or Visa required where you have to prove that you are financially capable, or even wanted in the country, or promise not to work or be illegally employed/compensated.
And then that alongside many countries in the developing world that still have undocumented people, no birth certificate, no identification, no tax ID, etc.
How does a country verify someones birth? Especially if someone wasn't born in a hospital? In the west, until 1950's, mostly this was done via church records. Also, are you granted citizenship by birth or only through parents? (Big deal, especially for Puerto Rican births - or countries that don't recognize foreign births in their land, e.g. United Arab Emirates / Saudi Arabia - even Japan or China, where sure you can be born there, but that means absolutely nothing.)
So, no, it isn't really a greater system for international worldwide travel - it is a system of control to ensure someones identity is who they are and that the country they are form atleast certified to some standard that their name, their picture, their birth date, their location of birth are somewhat tangibly real.
And this isn't even getting into information sharing. The above is just a standard, that now is "machine" readable and has an RFID so that collection is more easier for the state.
Context is amazing, isn't it?
Why 1800s? Why not Roman times? All you had to do is state you were a roman citizen, and you could travel - Unimpaired “ Civis Romanus sum”
https://en.m.wikipedia.org/wiki/Civis_Romanus_sum
Borders existed but travel was not impaired, how else do you think trade and commerce worked? Do you think supply chains are a new thing?
It very much sounds like you are conflating serfdom, as an impairment to free travel - it is a different exercise. Because you did have a king, and you were a farmer in that land and in many ways you had lesser rights than a slave.
The Roman Empire was a unique example among the thousands of years of history because along with their transportation network of roads they did actually have a couple of passport-like systems in place. Now a third of the people were literally slaves, so they definitely weren't going anywhere without permission, so maybe Rome is not a great starting point for what I presume to be the argument against passports. But the Romans and other Mediterranean civilizations did check your identity when you travelled. Romans had documents they called diplomas for people on official business and several civilizations used clay tablets called tesserae as a sort of ID card, but by far the most common method was simply having known people vouch for you.
Basically nowhere in the ancient world from the Middle East to the pre-colonial Americas could you just show up in a foreign village without people asking questions that you ought better have good answers for. There are a handful of exceptions, but this has never been the norm, and even with passports and visa restrictions it is definitely far easier today than it ever was in the past. I expect it will get easier and easier into the future. Perhaps quite soon in fact as the global population begins to decline and people become more and more valuable.
Consider how the days before passports also lacked air travel available to the masses. Even cars has only just started to become commonplace. I don't see how you could possibly have travel that is so cheap, quick, and accessible to such a large population without some way to control who is coming and leaving your country? Especially with how we're quickly making different parts of the planet inhospitable, and given how rapidly populations have risen compared to a century ago.
Passports are much older than that, but in pre-WWI Europe, most countries didn't require them for travel. (Russia and Turkey did.)
Passports certainly do have a dystopian element to them, especially if they are demanded too frequently / aggressively. But on their own, they aren't particularly evil; they just identify you much like your face does.
> Before WWI there were no passports and no need for them.
This combination of ignorance and confidence isn’t a good look.
So unless private collection of personal data is completely illegal, I’d rather have a centralised ID system instead
It's an interesting and thought-provoking list though.
You wouldn't say "Boeing 737" you'd say flight.
They're saying iPhone because it's attention grabbing. No other reason.
For some reason, I'm not entirely willing to believe that my parents (who are still alive) had a less happy life than I have even though they didn't grow up with an iPhone. And it's not like modern conveniences have no downsides (e.g. increase in stress). That's not to say I would give up on these things readily, I'm just way too used to them.
I think probably most people could agree that treatments for diseases that regularly also affect young / middle-aged peolle are a good thing. It's hard to argue that someone in the prime of their life should die of some silly infection.
Unless it's too comment on 'throwaway mentality', modern consumerism, etc., the book meaning 'made the modern economy' more literally/broadly than you're referencing it for here?
The first series is my favorite podcast of all time. They're short (~8 minutes, iirc) but pack a lot of interesting info in each episode. In particular, they explore some of the second-order effects of each invention.
The disposable razor might not be a true 'black swan' like the transistor or LK-99, but some of the background and influence around the invention might surprise you! I recommend checking it out. [1]
[0] - https://en.wikipedia.org/wiki/50_Things_That_Made_the_Modern... [1] - https://www.bbc.co.uk/sounds/play/p04t8k2l
Why is disposable razor on the list but not electricity, computing, refrigeration, metallurgy, microscopy, or eye glasses?
When I was a kid in the 90's I already enjoyed electricity and electronics and I would play with those low power incandescent lightbulbs powered by those 9V batteries. They would generate a lot of heat and very little light, to the point that it wasn't easy to tell if it was on when the sun was bright.
With a modern LED and the same setup you could generate enough light to blind yourself.
LEDs are genuinely revolutionary in a way everyone just kind of overlooks.
If it's proven to be the case that P != NP, it would hardly change much on the grand scale of things as generally, that's what most people believe anyway. In particular, the world continues to function mostly in the same way (since, even if it was the case that P = NP, we haven't found any polynomial reductions yet, so we're effectively living in a P != NP world). Of course, for mathematics and CS, this would be huge, because the techniques used in a proof would likely be very interesting and novel.
If it's proven to be the case that P = NP, then it remains to be seen whether this knowledge can be turned into actually efficient algorithms (polynomial algorithms are not all efficient in practice). If that is the case, I think it might have more downsides than upsides, since all of cryptography would collapse.
City of Hope scientists develop targeted chemotherapy able to kill all solid tumors in preclinical research
Apparently. I'm not an expect, but it's what I have encountered elsewhere.
Still great news! But not quite as revolutionary as the headline implies.
City of Hope thinks they've found a chemotherapy that's "able to kill all solid tumors","in more than 70 cancer cell lines".[0]
According to the National Cancer Institute[1], there are "more than 100 kinds of cancer". They're listed here: [2] Some of those cancers are soft tissue, so they aren't affected by this treatment.
I didn't know what a cancer "line" was, so I looked it up. "Cancer cell lines are valuable in vitro model systems that are widely used in cancer research and drug discovery."[3] So, they're not cancers in people, but cell cultures they can test drugs on.
This probably doesn't give you much more information than you already have, based on what you heard elsewhere, but I learned enough to figure maybe it would help someone else, too.
Whether this'll work in people, I guess we'll find out when they start the Phase 1 clinical trial. If you, or someone you know think you might benefit from this, there is a link to sign up for Phase 1 trials.[0]
It appears to have worked in pre-clinical trials, so they have tested this to make sure it doesn't kill people outright, the same way it does cancer cells.[4]
[0]https://www.cityofhope.org/city-hope-scientists-develop-targ...
[1]https://www.cancer.gov/about-cancer/understanding/what-is-ca...
[2]https://www.cancer.gov/types
Was anyone experiencing this? Also, I don't think "black" in "black swan" even refers to any sort of negative nature. The phrase implies an unpredicted event that was rationalized after-the-fact as being obvious/predictable. Is it also used to refer to _specifically_ to negative/dystopian historical outliers?
> it is helpful to recognize that the human tendency to believe that all future "big events" will be dystopian downers, is statistically unsound.
Is this the human tendency?
I'm just really confused by your comment. Hope that doesn't seem rude. The assumptions you make seem quite specific to you as far as I can tell? But there's very little to go off of if I'm being honest, so I'd be happy to have it clarified.
But yeah I suspect the people who are most excited about this news are fusion power engineers!
https://www.cambridge.org/core/journals/journal-of-plasma-ph...
0. LK99 is so obviously a fraud. They've been dicking around with this substance for 24 years.
1. some diseases will be possible to fix, like metabolic problems, but where structures are already formed in an adult organism this will be impossible. Like Autism. Go ahead, change every chromosome in every cell, the malformed brain structures will remain.
2. Sure there will be ignition, but the facilities will be wildly too expensive for commercial power.
3. will never happen with conventional computing hardware. Maybe if someone figures out how to grow actual neurons
The entire premise of your retort was wrong. You should have challenged them to take their certainty to the prediction markets.
The so-called "replication crisis" is overblown.
If LK-99 fails to be a useful material, it's interesting life will be over very shortly. If it is useful (and even if it's not the promised room-temperature superconductor, but useful in some other aspect), it will continue on in science, in technology - everywhere it might be useful for further investigation.
the authors managed to squeeze 24 years of grant funding out of it
Some of the “good” black swans at the top of my mind…
But if you compare India to China, one democratic and one not, suddenly it's not super clear which countries' citizens have "better" lives.
Somewhat better than a lifetime ruler, but this is far from what Democracy are on the textbook.
I feel like there's a limit to how much corporations can influence voters, the same way there's a limit to how much moviegoers will keep paying to see the same corporate movie over and over.
How do you think AI would legislate, if AI legislation would become reality?
If people could live for much longer then they’re likely disincentivised to procreate due to worries of overpopulation and then, in one way of thinking, you’re hypothetically depriving a line of offspring of lifetimes they’d otherwise have if you’d had what we consider a normal lifespan now.
Yes I realise there are probably an infinite number of takes on this, I’m just pointing out one possible way of looking at it for the sake of saying not all technological advances have universally positive outcomes.
I don't want to open a can of worms, but... about 40 milion people are aborted each year...
But amongst the popular left, there seems to be an aversion to competency and rationality, as they are symbolically linked to high status and social dominance. And so those who work deliberatively to end the scourge of aging and illness from humanity are—due to their displaying a rational results-oriented mindset—disdained.
I can't agree. We can have eternal dictatorship now. Nothing prevents it except other people, therefore people will prevent eternal dictatorship just as now (with various results).
Anyway, Im ready to accept this risk.
These maniacs didn’t have enough time to accrue enough mass to become power black holes, but give them a century or two to work with..
Rulers, set in their ways, will take a government down an increasingly non-viable path.
We already see the advantage age provides when building influence for US politics.
As for dictators: it's not like guillotines stop working.
What will keep dictators (if eternally young, or their offspring if not) in power forever is competent and obedient AI manning the police and army.
Still, that is averages. A cruel despot may never leave their palace fearing death and will always have security. They will have less opportunities for accidents.
Current global median life expectancy: 75.2 years
LE/I%: ~958 years.
https://en.wikipedia.org/wiki/List_of_causes_of_death_by_rat...
Same but assuming we can avoid transport accidents, ~1354 years.
They are immune to guillotines operated by peasants.
The only thing they don't have protection against is Government forces. With their armies of lobbyists, and other bought influence they have, they are also, largely, protected against those as well.
Yup, and they'll only know their methods are safe if they get the rest of us to try it out en mass.
> They are immune to guillotines operated by peasants.
> The only thing they don't have protection against is Government forces. With their armies of lobbyists, and other bought influence they have, they are also, largely, protected against those as well.
What makes them different from the French royal family, who basically were the government?
You don’t need guillotines, you just need one junkie at the right time.
https://www.dailymail.co.uk/news/article-11941061/Tech-exec-...
That's all without even mentioning other benefits like cumulative knowledge of multiple lifespans being contained in one person allowing for new scientific breakthroughs.
2. Light year capable transport
3. Inertia dampers
4. Mass scale carbon capture technology
5. Robots to prepare space for habitation
6. World recognition to manage resources globally
Do you mean communism?
Now.... We may disagree on letting it go as it goes. Ice ages would overtake a ton of countries in glaciers entirely, so we may agree that that should be stopped? But........ Doing that would be directly trying to challenge the solar system and earth on their natural cycles. There would likely be massive unforeseen repercussions.
So your argument is that the planet will be fine is great, except some of us would like humanity to survive indefinitely. For that, we should do everything we can to protect the planet and it’s current occupants.
But then, there are many ways to organize a society while keeping it commerce-based... Or maybe we manage to finally crack that nut some day and make a post-scarcity society. But on the short term "manage resources globally" heavily implies an anti-humane dictatorship.
Try finding at history some place where the society isn't fundamentally organized around commerce or under some heavy kind of authoritarianism.
Then Scott Walker shredded a bunch of it because socialism is bad.
We're you genuinely asking if they meant communism, because you didn't know if they did?
I would prefer you didn't even ask, because IME people on this forum can't have honest discussion or apply critical thinking in the vicinity of the subject. They start rhetoric-dumping and rehashing tired arguments like preventing thoughts about communism is their ticket to heaven.
I think a CENTRALISED management of the world's natural resources would require communism.
Decentralised management is what we have now.
one of these is not like the others. direct carbon capture works now with the slight caveat that we would have to build 10x our current power supply in fission plants to power them. coccolithophores are an appealing route in principle, but research into their lifecycle and use for sequestration would be a quotidian pursuit for thousands of labs around the world, given funding.
If free-form gene editing were developed today, you would see the elites using it to make themselves immortal, while denying the same to everyone else. If fusion power suddenly became viable, you would see the richest people using it to make themselves even richer, while cementing their stranglehold on vital infrastructure. And it should be obvious to anyone who has been paying attention during the past 3 years that artificial intelligence is above all else an instrument of control, and even in its infancy, access to it is unevenly distributed along the same strata of power that already existed before.
At this point, the only "black swan, but good" event that could happen is a cataclysmic reset of civilization that might somehow see a better phoenix rise from the ashes. Barring that, we're full steam ahead to a techno-totalitarian nightmare future.
A bit of history would do you wonders. Top-down control was the norm. If it has changed, it’s less now.
Sure, there were lords who claimed large parts of the population as their property. But they often didn't even have a complete list of the people they supposedly "controlled", nor did they have any insight or actual control over their private lives in the sense that modern nation-states do. Legal codes used to contain a few dozen criminal offenses in total – today, there are tens of thousands.
Invasive, pervasive, centralized, highly organized, and sophisticated top-down control of individuals is an entirely new phenomenon that is only made possible by cutting-edge technology in the first place. If you imagine past societies as forerunners to modern police states, you have a very distorted picture of history. Many of them did not even have anything like police to begin with.
Whether we can build a large shed in our gardens is managed through a vast and intricate bureaucracy. A ridiculously precise and unwieldy apparatus is indeed watching our every move. I completely agree that is a new phenomenom, made possible by technology. I cannot just take down a tree without permission, even in my own yard. How weird is that. Yet does it matter?
Do you have to work the fields just because your family failed to produce a consul in the past century or two? Are you destined for a life of abject slavery because you disagreed with the regional governor about some administrative issue? Peoples of the past may have lacked technology, but that doesn't result in freedom. You don't need penal codes if your every move is watched and judged by your peers. Each of them happy to turn you in for a small fee.
More importantly, legal codes aren't necessary if you drop the pretence and just wield power however you want, whenever you want. You don't need detailed control of peasants' private hobbies if you got overpowering total dominion over the fate of an entire continent.
I'm just saying that oppression is nothing new and I actually think we are at an all-time low in actual, life-dominating oppressive powers. In some cases I can make the case that's actually not so great, because these days I'm increasingly more afraid of my fellow men than any "government" - which in my country is barely hanging on and always behind, but I don't know about the US.
Can't we do both? Appreciate the progress we made, "we don't have it as bad as the last guy", and also looking towards improving even that? Wholesale dismissal of the entire edifice is IMO not the way though.
Also, pedantic point, you keep referring to good and bad black swan events. I thought the definition of black swan didn't make any assumption about whether the impact is positive or negative? Only that has a huge impact (I haven't read Taleb's book yet, correct me if I'm wrong)
I would be curious if anyone with knowledge in the space could comment on whether or not LK-99 may get us closer to viable nuclear fusion?
My understanding is that magnetic field containment systems are at least part of the technical hurdles required to make fusion feasible.
The response you posted seems to be referring to various concepts from theoretical physics and philosophy, specifically the ideas of the Everettian interpretation of quantum mechanics, anthropic reasoning, and the Born rule. Let's break these down:
Everettian interpretation of quantum mechanics: Also known as the Many-Worlds interpretation, it suggests that all possible alternate histories and futures are real, each representing an actual "world" or "universe". In layman's terms, it's the idea that there could be countless parallel universes where every possible outcome of an event happens.
Anthropic reasoning: This is a philosophical consideration that observations of the universe must be compatible with the conscious and sapient life that observes it. In other words, our ability to exist and observe influences how we should interpret the universe.
Born rule: In quantum mechanics, the Born rule is a statistical law that connects the mathematical formalism of quantum theory to experimental observations. It provides the probability that a measurement on a quantum system will yield a given result.
The responder seems to suggest that in a universe with many possible futures (as the Everettian interpretation would suggest), we are more likely to observe "black swan" events that lead to more possible futures.
The idea here is that if an event significantly increases the number of possible futures (like a breakthrough that extends human lifespan), then it effectively increases the number of "observer-moments". In other words, more possibilities for observers to exist and make observations. According to anthropic reasoning, this could make these events more likely to occur than pure chance would predict, because we're only able to observe futures in which we exist.
This line of reasoning is highly speculative and philosophical in nature, touching on deep and unresolved questions in physics and philosophy. It's an interesting thought experiment, but it's important to note that this isn't widely accepted or proven in the scientific community as of my knowledge cutoff in September 2021.
There is a huge amount of what I think in unawarded debate about applying it to the past (IMO, it's very clear where it should be used), but applying it to the future is completely against any kind of logic.
It can certainly lead you to some pretty wacky-sounding conclusions (looking at you Frank Tipler) but I can’t see why it’s obviously wrong for future observers to deploy it in just the same was as we do.
You can't apply conditional probabilities to unbias some result if you don't know if the condition holds or not.
You can invent some fiction where some future people apply it. You just can't pretend that there is any realism on it.
>2) Commercially viable fusion energy. Will change a lot of things.
How would that be any better than commercially viable fission breeder reactors (which seem far closer to reality than commercially via fusion energy)?
Though there are genuine advantages: for as radioactive as the interior of a fusion reactor may get, if you cut power it'll just sit there safely doing nothing. No decay heat, no potential isotopes to leak - maybe a puff of tritium gas - but that's it. It is a technology that has a perfect control loop for safety because it can't self-sustain at all.
I think there should be a bigger effort to change public perception about nuclear fission reactors if we're on the cusp of what is effectively the equivalent of the dream of endless fusion energy in the latest generation fission breeder reactors.
https://en.wikipedia.org/wiki/Muon-catalyzed_fusion
https://link.springer.com/article/10.1007/s00016-009-0006-9
https://www.annualreviews.org/doi/pdf/10.1146/annurev.ns.39....
http://large.stanford.edu/courses/2016/ph241/yoon1/
https://www.chemeurope.com/en/encyclopedia/Muon-catalyzed_fu...
> Even if muons were absolutely stable, each muon could catalyze, on average, only about 100 d-t fusions before sticking to an alpha particle, which is only about one-fifth the number of muon catalyzed d–t fusions needed for break-even, where as much thermal energy is generated as electrical energy is consumed to produce the muons in the first place, according to Jackson's rough estimate
Yep, it's challenging. Maybe this rate can be improved by applying alternating voltage to reactor. Muons are charged particles, so they can be accelerated further. (Just idea)
Considering that we already have a fusion reactor in the skies, I think that the room temp room pressure superconductor is the next best thing. Fusion is good but at this stage, the natural one will just do. Think global network of solar cells interconnected with LK-99.
The creation of a global electricity network perhaps also has some effect on global cooperation.
Now we just need reduce the use of fossil fuels (cars, aviation, heating, industry).
Economies of scale do apply.
Saharan dust will also cover those panels in like a day. Probably makes more sense to float them on some body of water instead, with automatic washing and cooling?
I feel our generation (I am in my mid-forties) lived through enormous technological advancements but not as many scientific breakthroughs as the previous generation. So maybe it is not surprising that we are suddenly more likely to have breakthroughs in basic science.
I hope there is a phase transition to science mode now, so we that have a chance to solve the hard pressing issues.
no way, no how. there is every reason to believe that cells are irreducibly complex. we can understand parts in isolation, yes, but a full model of the cell (however that would look) is almost certainly beyond science and even if you had that good luck measuring the full state of a cell without destroying it
Honestly that doesn’t seem likely to be a black swan event. Not because it is never going to happen, more because it won’t be an event but a slow progression.
It is more likely that as we understand more and more we will be able to cure more and more. It is not like there is some silver bullet piece of research where sudenly we have “fully decoded the celular mechanism”. Plus even if we somehow suddenly and all at once atained all that knowledge (perhaps a flying saucer takes pitty on us and beams down a whole library documenting our cells) it would take a long time while we turn that knowledge into helpfull interventions. And even that progress would be multiple generations long.
It is how becoming a black-belt martial artist is not an “event”. You don’t go from zero to that in one night. It is more of a progression where every day you are about as proficient as you were the previous one, but maybe a tiny bit better. Just applied on a whole species level.
How do you build a warning system for a unsurvivable event, with not wittnesses? Eternal unease and anxiety, regardless of reality.
webster's dystopia definition is "of, relating to, or being an imagined world or society in which people lead dehumanized, fearful lives : relating to or characteristic of a dystopia"
>> 1) Fully decoding the cellular mechanism of cells allowing for the curing of any disease, repairing any genetic disorder.
-- so you want to cure aging then- how many billions of people you think can a planet with a 6k km radius sustain ?
You think Claus Schwabs of the world wont buy it out to keep it to themselves ?
>> 2) Commercially viable fusion energy. Will change a lot of things.
-- That will eventually happen, and electricity will be just as "expensive" as it is now, simply because the price of a product has nothing to do with its cost and everything to do with the purchasing power of its intended audience.
>> 3) An AI subsystem with some reasoning ability (yeah, could go either way)
-- No, its cant go either way, the power insatiable psychopaths in power will use it to maximize their power. Period. Its psychopath nature- for them its natural and perfectly normal. Until psychopathy is recognized as a disease and sick people are disallowed from positions of power, the world will continue to be an abusive place.
Doesn't seem that it would cure high speed lead poisoning. People will continue killing each other just as well.
100%
If we had fusion tomorrow it would help decarbonise our grids, which is a great thing, but the consumer would see zero financial benefit. Companies would charge the same and make record profits.
This is literally happening right now! The market price of energy in Europe has dropped after a huge hike when Russia invaded Ukraine, but customer bills are still extortionately high
5) programmable matter / nanobots - the applications of a swarm of nanobots or even microbots are pretty much endless.
Our civilisation is an energy-junkie who happened to stumble on a huge bag full of cash around 1860 and the discovery of oil distillation. Since then, we have been on a hallucinating trip, burning down our house in the process. Viable fusion is essentially another huge pile of cash being deposited right across the street, just 10 times larger than 2 centuries ago. There is no coming back after that.
With the exception of Avatar, is there any advanced fictional civilization that doesn't use vast amounts of energy in proportion to their tech level? I'd also point to the historical record.
Historical records tell us that energy consumption is a great indicator of civilization advancement, but so is territory. Now, the problem is that there is no further territory to acquire for us as we have pretty much exploited our planet to its bones.
Free cheap energy will just make the planet crumble under our weight.
You've said or implied this twice, but haven't put forward even a plausible mechanism why this would be a crumbling downfall.
The fuel is abundant and safe. The byproducts are safe. There are no carbon byproducts to contribute to global warming. I don't see any logic to your statements besides: previous bad, therefore next bad. I believe this is the definition of a non-sequiteur.
Please correct me if I am wrong or have missed something.
It will fuel an economic growth without precedent, which in turn will increase the consumption of material goods, which in turn will increase the extraction of natural resources. Those resources will become rarer and more difficult to extract, thus leading to more destructive extraction strategies.
Energy puts a cap to our ability to destroy the planet in order to satisfy our material needs.
I don't believe one second that our civilization is capable of controlling itself. And don't tell me about multi-planetary scenarios or whatnot. They are neither realistic (regardless of the energy availability) nor desirable.
Mining of auxillary materials to pair with all that energy would be a problem. Multi-planetary scenarios for humans aren't realistic in anywhere close to the near term... But mining asteroids instead of the earth might be realistic. Many solutions which may not be realistic now could be with such an energy source.
It will be a precarious time. That's for sure.
> Also the vast majority of people like nature, more energy is directed into cleaning up and preserving nature in the US than every before.
Really? Definitely in an orthogonal dimension then...
We need a reduction of human impact on our planet, not an increase of it.
Likely a call out to global warming.
> how is that applicable to fusion tech?
One thing that is never really discussed in terms of fusion energy is what you will do with the heat generated from these processes as there is a theoretical maximum for how much heat the planet can dissipate.
Whether the poster is correct or not, its widely acknowledged that the ability to transition from gravity powered/wind powered energy to coal combustion fueled a great deal of the economic and technological improvements from the 1700s onward (we call it the Industrial Revolution).
Cheap unlimited energy will just make us push these boundaries even further.
Plus, and most importantly, trashing our one and only planet "because we are not bound to it" is just one of the most unethical and most dangerous plan one can think of. And I know that there are plans to become a multi-planetary species without making Earth inhabitable in the first place, but I think the quote "Everyone has a plan until they get punched in the face" applies beautifully here. And the fist of climate change combined with biological collapse will hurt badly.
For a while I've kept a list of the things that could be "good" swan events, but to be fair I didn't have "room temperature superconductor on that list" :-)
Other things that could happen:
1) Fully decoding the cellular mechanism of cells allowing for the curing of any disease, repairing any genetic disorder.
2) Commercially viable fusion energy. Will change a lot of things.
3) An AI subsystem with some reasoning ability (yeah, could go either way)
Etc.