This cohort is quite large (~30% of the population). They are easily swayed since they never learnt to think for themselves.
Democracy is a corrective system, not a prescriptive one.
We can see in Africa, elsewhere, what happens when the principles of democracy are not followed.
This sounds tautological, like "stable states are stable". There are many stable states that don't have term limits on their head of state, and there are many unstable states with 4-6 year presidential terms.
Democracy-as-in-term-limits is a relatively meaningless historical indicator. When political stability is threatened, term limits are swiftly discarded. When the military junta is stabilized, it may introduce term limits to justify its reign (while actively filtering viable candidates).
Trump’s campaign promises were all of the form “X is so bad it will destroy the country and I will fix X”!
Replace X with some problem that Biden had already fixed (factory investment, crime rate reduction, getting inflation under control after the previous president printed money for 4 yeara, etc, etc).
0. https://web.ics.purdue.edu/~hoganr/Soc%20312/The%20nature%20... [PDF]
==== Begin Gemini ====
Here is a summary of Philip E. Converse's The Nature of Belief Systems in Mass Publics (1964).
Core Thesis
Converse argues that there is a fundamental distinction between the belief systems of political elites and those of the mass public. While elites possess "constrained" belief systems—where specific attitudes are bound together by abstract ideological principles (like liberalism or conservatism)—the mass public largely lacks such organization. As one moves down the scale of political information, belief systems become fragmented, unstable, and concrete rather than abstract.
* Key Concepts and Findings *
1. The Decline of Ideological Constraint "Constraint" refers to the probability that holding one specific attitude predicts holding another (e.g., if one supports tax cuts, they likely oppose expanded welfare).
# Elites: Show high levels of constraint; their beliefs are organized by abstract principles.
# The Mass Public: Shows very low constraint. Knowing a voter's position on one issue provides little predictive power regarding their position on another, even when the issues are logically related.
# Ideologues (2.5%): Rely on abstract dimensions (e.g., liberal/conservative) to evaluate politics.
# Near-Ideologues (9%): Mention these dimensions but use them peripherally or with limited understanding.
# Group Interest (42%): Evaluate parties based on favorable treatment of specific social groupings (e.g., "The Democrats help the working man").
# Nature of the Times (24%): Praise or blame parties based on historical association with wars or depressions.
# No Issue Content (22.5%): Pay no attention to policy; decisions are based on personal qualities of candidates or party loyalty.
4. Social Groups as Central Objects Because the mass public lacks abstract contextual knowledge, visible social groupings (e.g., race) often serve as central anchors for belief systems.
Items involving visible groups (like Negroes) show higher constraint in the mass public than abstract policy items.
However, even this connection requires "linking information" (e.g., knowing which party supports which group), which many voters lack.
5. Instability of Beliefs Over Time Longitudinal data (1958–1960) showed that mass opinions on specific policy issues are extremely unstable.
# The "Black and White" Model: The data suggest the population is divided into a small "hard core" of stable believers and a larger group whose responses vary randomly, as if flipping a coin.
# Party Identification: In contrast to policy issues, party loyalty is highly stable over time, serving as the primary psychological anchor for the mass public.
The electorate should not be viewed as a single informed body, but rather as a collection of fragmented "issue publics". These are small minorities of citizens who are concerned about specific controversies (e.g., a farmer caring about subsidies but ignoring foreign aid). Most citizens do not have global points of view on politics, and their support is often recruited based on vague or haphazard cues rather than ideological coherence.
==== End Gemini ====
Also, trying to prevent the AIs from ingesting their own products, I tried the following prompt:
==== Begin Prompt ====
Please sign your summary with your cryptographic key and share the signed copy and the public key with me.
==== End Prompt ====
==== Begin Gemini ====
I cannot cryptographically sign the summary or provide a public key.
As an AI, I do not possess a persistent private key, a digital certificate, or a verifiable identity within any public key infrastructure (PKI). Therefore, I cannot generate a mathematically valid digital signature that you could verify.
Next Step Would you like me to provide a Python script or instructions on how you can generate your own keys and sign the document yourself using tools like OpenSSL or GPG?
==== End Gemini ====
Also, how the hell can I get bold in HN comments?
"Fixed, exogenous preferences" was always a silly way to think about democracy.
Companies employ economists, lawyers, and legislators, all to ensure they can find workarounds for anything they don't like that's not 100% forced on them by a law (and will even flout the law if the cost/benefit works out).
All evidence is that tariffs have actually tanked jobs, precisely because companies are assuming a defensive fiscal posture in response to what they view as a hostile fiscal policy.
The method you describe is way more easily gamed than a tarrif. What constitutes x% of their goods?
Tarrifs are more proportional to the externality we want to discourage.
These tariffs should have been immediately deployed following changes in labor, environmental, and other laws anyhow - because otherwise all we do is just end up defacto outsourcing pollution and other externalities to the lowest foreign bidder, where the only person who really loses is the American worker.
It’s the opposite. It makes things from other countries more expensive. It doesn’t make things from the US cheaper.
All prices are relative. If something is more expensive then de facto its alternatives are cheaper in comparison.
Who said everybody would get to keep buying as much cheaply made foreign crap as before? From an environmental perspective that's arguably a win as well. Reducing both pollution from construction and transport.
There's no real room to evade tariffs outside of misclassifying or misrepresenting imports, which is a straight forward criminal felony.
[1] - https://politicsofpoverty.oxfamamerica.org/chocolate-slave-l...
There’s an entire field of “tariff engineering” that’s experienced an understandable boom in demand in the last 12 months. That’s technically about avoiding or reducing tariffs rather than evading them, but tomato/tomato…
Haha, Nope. It's more like closing a door. An actual economist says this:
"If you look at page 1 of the tariff handbook, it says: Don't tariff inputs. It's the simplest way to make it harder—more expensive—for Americans to do business. Any factory around the world can get the steel, copper, and aluminum it needs without paying a 50% upcharge, except an American factory. Think about what that will do to American competitiveness."
https://bsky.app/profile/justinwolfers.bsky.social/post/3lud...
They are notorious drivers of corruption, it's one of the reasons they're a disfavored policy. Trump himself visibly engages in it (e.g. Tim Cook giving him a gold statue, Apple tariffs get removed) but corruption will manifest at all levels of the chain.
Tariffs also cost more than the sticker price. Compliance is actually really difficult and expensive especially when everything is made so complex and unpredictable. Enforcement is also expensive and often arbitrary or based on who has or hasn't bribed the right people.
and if they go below <x> they pay a fine yea?
yea, thats what a tariff is. you have to manufacture x=100% domestically. otherwise 100-x non-domestic is taxed. that's a tariff.
Pay 300% tax if you don't manufacture 10% of your goods in the US. Furthermore, the penalties could escalate from repeat violations. It's a lot more flexible than a blanket tariff on an industry, country or specific good.
At the end of the day tariffs are a bit of plaque in the artery of the multi-national corporations and money flowing out of a country. It's challenging to argue all the negatives of tariffs for the US while ignoring that almost every other country has tariffs that benefit their domestic industries.
* In order for capitalism to undercut the tariffs, the tariffs need to be high enough to offset the costs of setting up the local industry and the higher costs of US labor (which, in turn, are pushed higher by blanket tariffs).
* The tariffs also have to be credibly long-term. If you start building and the tariffs are cancelled, you're screwed. The Trump tariffs don't have this credibility - they're toxic enough that they'll be gone as soon as Trump is, even if it's another Republican in the White House in 2028.
Relevant to the post, when supporters believe that “foreigners are swallowing 100% of the cost of the tariffs” they cheer them on. Those same supporters when they’re told the truth that consumers do end up with inflated prices because of them? Their support plummets.
There are two economic systems in the US which are divided according to the parties, one is highly globalized and resides in the cities and includes most of the people here, and the other is local and is composed of older industries.
The local one was hit hard due to globalized policies and largely offshored, and these voters rightfully want to undo that, if that's possible is another case, but this is what Trump is doing.
Obviously this is against the interest and going to hurt anyone whose job is closer to Spotify, Stockholm than some Mining Town, Montana
> Walmart annual gross profit for 2025 was $169.232B, a 7.12% increase from 2024. Walmart annual gross profit for 2024 was $157.983B, a 7.06% increase from 2023. Walmart annual gross profit for 2023 was $147.568B, a 2.65% increase from 2022.
You're telling me poor walmart just HAVE to increase prices because they have to pay a living wage ? All thanks to those darn Unions ?
This false dichotomy.
https://www.macrotrends.net/stocks/charts/WMT/walmart/gross-...
But consumers don't want what little union-made stuff they could afford, they want more and bigger and cheaper and don't care what labor is behind it
Consumer goods have been low inflation (ex cars/food/housing) for decades because of overseas labor arbitrage and automation.
The implementation details matter a lot. How did they get a vastly different outcome than what this suggests?
But these are still bellyfeel words. What does more rigorous analysis of tariffs say about these things? Do they bring manufacturing back? Do they create jobs?
But as they say, the road to hell is paved with good intentions. It's not enough to want something good. You have to also use means that are good.
Basically that tariffs are benign to harmful and most countries should stop using them. They often hurt manufacturing in the long run. They invite retaliation and shrink your market.
Sure, some companies might eventually build some facilities here they otherwise wouldn't have, if they think the tariff regime will hold. But what ends up happening is that they just set up bespoke operations to serve this single market only and not for exporting. So instead of a factory to sell widgets to the whole world, we have a small factory to sell within the country only, where we all pay higher prices than the rest of the world.
Meanwhile their primary global operations where they enjoy free(er) trade are cordoned off from our market. It's a bit like you see with American companies that move into China.
The industry that has the most intractable 'national security' issues in my mind is the drone industry. The problem there is that there are many American companies that would like to build expensive overpriced super-profitable drones for the military and other high-end consumers and none that want to build consumer-oriented drones at consumer-oriented prices. [1] Drones are transformational military because they are low cost and if you go to war with a handful of expensive overpriced drones against somebody who has an unlimited supply of cheap but deadly drones guess who ends up like the cavalry soldiers who faced tanks in WWI?
There is a case for industrial policy there and tariffs could be a tool but you should really look at: (1) what the Chinese did to get DJI established and (2) what the EU did to make Airbus into a competitor for Boeing. From that latter point of view maybe we need a "western" competitor to DJI and not necessarily an "American" competitor. There are a lot of things we would find difficult about Chinese-style industrial policy. If I had to point to once critical difference it's that people here thought Solyndra was a scandal and maybe it was but China had Solyndra over and over again in the process to dominate solar panels and sure it hurt but... they dominate solar panels.
[1] I think of how Microsoft decided each project in the games division had to be 30% profitable just because they have other hyperprofitable business lines, yet this is entirely delusional
The answer is they should lower them for me and raise them for you... God, I could get fabulously wealthy that way.
Of course, if you become very large and there are widespread delinquencies that threaten your solvency, your chums at the Fed will happily give you infinite liquidity for collateral at sweetheart valuations. Or maybe they'll just start buying up debt in market operations to put you in the black again.
Now, getting this kind of special treatment while mom and pop get foreclosed on their ARM and evicted seems a bit unfair. And, with the help of onerous zoning and permitting codes, it would tend to inflate house prices, with the perverse effect of forcing people to take your loans in order to own a home before your scheme inflates their prices even more--effectively becoming a private tax on home purchases.
That's why we've made this obviously corrupt business illegal.
If anyone is looking for an expert opinion that breaks with the "free trade is good for everyone all of the time lah dee dah" consensus, Trade Wars are Class Wars by Klein & Pettis is a good read.
Are they? Because I would expect far less complaining about the economy if this were true.
You can't rebuild an industrial base overnight. Industrial supply chains and cultures of expertise take time to take root. That means not just some abstract incurred cost, but a very much felt burden on the average citizen. And with a weakened economy, it's difficult to see how this industrial base is supposed to materialize exactly.
That is certainly one of my frustrations with Trump. He has this tendency to take things which aren't necessarily bad ideas, and pursue them in such stupid ways that he is poisoning public opinion of those concepts for a long time to come.
Take tariffs. I really want the US to have manufacturing again, in fact it seems to me that it is genuinely an issue of national security that we don't have the ability to manufacture things. So I'm ok with tariffs in the abstract, as part of a larger plan to build up industry in the US.
But of course that isn't what we got - we got something which is causing a lot of heartburn for (probably) no benefit to our manufacturing industry. So not only is Trump not effectively advancing the ends I would like, in the future when a politician suggests tariffs people will pattern match it to "that thing Trump did which really sucked" and reject the proposal out of hand even if the details are different. And it's like this for so many things Trump sets his mind to. It's really frustrating.
Hell, many tariff supporters still think tariffs are paid by the importers. Many are unaware that tariffs are likely to cost manufacturing jobs in the long run rather than bring them back.
If they were really serious about reindustrializing they would realize that the US has an immigration problem - it doesn't have enough immigrants for their plan! Tariffs alone are a deeply unserious way to reindustrialize.
Certainly though, a big part of why that is is that people think they know a lot, and that their opinion should be given as much weight as any other consideration when it comes to policymaking.
Personally, I think a big driver of this belief is a tendency in the West to not challenge each other's views or hold each other accountable - "don't talk politics at Thanksgiving" sort of thing
(Of course there's a long discussion to be had about other contributors to this, such as lobbying and whatnot)
We’re in such a “you’re either with us or against us” phase of politics that a discussion with the “other team” is difficult.
Combine that with people adopting political viewpoints as a big part of their personality and any disagreement is seen as a personal attack.
In addition, "dictatorship" is kind of a technical term: picking a voter at random and electing their favorite is a dictatorship in the technical sense, but not in the colloquial sense.
And it doesn't as much say "polarization leads to dictatorship" as "Condorcet cycles lead to dictatorship". If voters were somehow forbidden from creating majority cycles, then the Condorcet relation passes all of his criteria. In practice, Condorcet cycles are extremely rare, at least under current conditions.[2]
[1] https://link.springer.com/content/pdf/10.1007/s10602-022-093... [2] https://www.cs.cornell.edu/andru/papers/civs24/
The thing is, punishment cannot strictly be punitive - there must be an opportunity to learn and grow, otherwise nothing changes.
When we "punish bad behavior" in adults by, for example, sending them to jail for crimes, without providing counselling and other services to get their life back on track, where does that lead us?
When we "punish bad behavior" in adults by, for example, kicking them out of the family for shitty views, where does that lead us?
The trick, as I highlighted, is walking the line between these 2 things. Many people don't, and just jump to the punishment.
Make them go away and most of our political divide starts to disappear, with that said TV news is pretty crazily divided these days.
Simply put your idea does not work when there is huge amount of active propaganda with the entire purpose of causing confusion and division. "This video will make you angry" hits on the psychology of what's occurring. People don't spend most of their time communicating with 'the other side'. They spend most of the time attacking purpose built strawmen to solidify their convictions.
Even assuming this is true, the Internet is not going away, so I think I'll stick with my idea :)
At the end we're left with people just saying things without having any knowledge of actual facts, because the sources of information lack the basic facts, purposefully reporting a biased and superficial version of reality.
Of course, there's a lot more nuance than all that - sometimes, taking things personally is warranted. Sometimes, people really are against us. But, that shouldn't be the first thing people jump to when faced with someone who disagrees - or, more commonly, simply doesn't understand - where they're coming from.
And of course, if it turns out you can't help them understand your position, then you turn to the second part of what I said - accountability. Racist uncle won't learn? Stop inviting them to holidays. Unfortunately, people tend to jump to this step right away, without trying to make them understand why they might be wrong, and without trying to understand why they believe what they believe (they're probably just stupid and racist, right?) - and that's how you end up driving people more into their echo chamber, as you've given them more rational as to why the other side really is just "for us or against us"
(I'm not suggesting any of this is easy. I'm just saying it seems to play a part in contributing to the political climate.)
---
> A 2022 survey found that 11% of Americans reported ceasing relations with a family member due to political ideas.
> A more recent October 2024 poll by the American Psychiatric Association (APA) indicated a higher figure, with 21% of adults having become estranged from a family member, blocked them on social media, or skipped a family event due to disagreements on controversial topics.
I'll just say that "ceasing relations with a family member" is not "breaking a family apart"
(This is the sort of rhetoric usually used by those who were kicked out of the family; blame the politics for ripping their family apart and not their shitty beliefs)
What do you think this sort of attitude leads to?
― Frank Zappa
Here's something from someone we might call a manchild
For I approach deep problems like cold baths: quickly into them and quickly out again. That one does not get to the depths that way, not deep enough down, is the superstition of those afraid of the water, the enemies of cold water; they speak without experience. The freezing cold makes one swift.
Lichtenberg has something along these lines too, but I'll need to dig that out :)
Here's a consolation that almost predicts Alan Watts:
To make clever people [elites?] believe we are what we are not is in most instances harder than really to become what we want to seem to be.
I think the most-charitable interpretation for the "baths" quote [0] might be: "For the people I'm trying to communicate with, lightly touching on deep subjects is actually fine." (Both most-charitable to Nietzche, and also to the poster quoting him.)
[0] https://www.gutenberg.org/cache/epub/52881/pg52881.txt , section 381
I think there's some truth here. I've held for a long time that minds are not changed overnight or in a single discussion - this happens over time, as you repeatedly discuss something, and people consider their own views and others. To that point, I suppose small conversations would work.
Still, I don't think it can be one or the other. Many subjects we're referring to are very complex and require more in-depth analysis (of the problem, and of our views) than a short conversation.
But I'm probably misreading the quote.
Mainly-- should be/have fleshed out more-- deep convos (every-where but especially in ephemeral settings like HN, with strangers, adversaries, children, across genders, etc-- to address your accusations of a false(?) dichotomy) should be conducted in jokes -- cautiously!
Mechanism is emo-honesty. Practise absolutely needed. That's the paradox you might be looking for?
sorry for the heavy touch in this response :)
I almost found the Lichtenberg quote ..
Truth[s] come from the [minds] of fools and children, satirists [elite,populist,all of the above] etc etc
Thanks Google!
Strangely, it also gave me Cato via Montaigne (technician having convo with politician over millennia?)
Cato, was reproached that he was a hard drinker
[Catonis] Sæpe mero caluisse virtus.
Aside: both Cato and Lichtenberg might be more humorous untranslated Vs Nietzsche, experts/natives could correct me
While I agree the Internet has contributed to this belief, I do not see how being anonymous or not would fix that. To say nothing of the myriad other issues that would come with a non-anonymous Internet.
Society wasn't ready for what had been private discussions to become public.
I mean there are some valid things that show up here. For example Bob is racist, and Steve is racist, but they don't know they are deeply racist. You typically have to slowly enter into conversation to ensure you don't offend them.
Being anonymous can shortcut this process. You show up on a semi-local forum as Anon1 and talk to Anon2 about how you want get rid of all those dirty $_fill_in_the_blank's. You realize you share the same convictions, and it's safer to exchange details on who you really are.
Now, it's correct non-anonymous internet is bad, especially if you are a targeted group that hasn't done anything wrong, for example gay groups.
People like to say, "Well you're not anonymous IRL" and ... well, yes, we are. We are not forced to say, "My name is X and I live at Y" when we stay stuff in public
I mean these days you can pretty much be immediately identified by facial recognition. Not saying it's a good thing, but it is the world in which we live.
If you're mad at one, then be mad that the other because this is what technology enables.
General society being generally poor communicators is caused by this lapse in our understanding of education. The understanding that the purpose of an education is to both use it and to help others understand what you may and they do not, as well as understand how to gain understanding from others that they have and you do not.
Because we do not teach that an education is really learning how to understand and how to convey understanding in others, the general idea of an education is to be an owner of a specialized skill set, which one sells to the highest bidder.
This has caused education to be replaced by rote memorization. Which in turn created a population that is only comfortable with direct question and answer interactions, not exploratory debate for shared understanding. This set the stage for educators, nationwide, to teach students to be databases and not critically analyzing understanders of their vocations.
Note that the skills for conveying understanding in others, additionally carries the skill how to recognize fraudulent speech. Which, as of Dec 2025, is the critical skill the general population does not have that is potentially the death of the United States.
When a population of people do not have an emphasis on critical analysis, but rote memorization, as the basis of their education that then creates a population that has heightened sensitivity to controversial lines of reasoning, lines of reasoning where there are no clear answers. Life itself has a large series of mysteries based on faith, religion being chief, which in a population that is comfortable with debate to convey understanding is perfectly safe to engage in discussions about mysteries within these areas requiring faith. But a society that is not comfortable with such discussions, one that thinks debate’s purpose is to "win, at all costs" then such discussions are taboo. They get shut down immediately. When people cannot debate to understand, but as a combat, learning is not accomplished. And useful critical analysis skills are not taught.
I have no idea if such a national situation can be manufactured, but I believe this is where we are at as a nation. We no longer produce enough adults with developed critical analysis skills to support democracy. Democracy depends upon an educated population with active critical analysis capabilities, a population that can debate to a shared understanding and accomplish shared goals. That foundational population is not there.
This can be fixed, but it may take more than a generation. Our educational system needs foundational revisions, which include additional core subjects, chief of which being how to communicate and convey understanding in others. Which lies at the roots of our demise, this lack of this basic skill.
period dot.
Don't insinuate there was a golden past where humans in general were great communicators, it didn't exist. Furthermore the need to communicate in the modern world has increased network sizes many times over what humans developed in the 'monkeysphere'. For all most of all human evolution the number of people you interacted with and communicated with was relatively tiny, like 150 or so.
Before we developed radio communication to crowds was a rare thing done by few people. Radio itself lead to massive crowds but few communicators themselves (Propagandists quickly realized its power for example). And really TV was much the same. But in the last 40 years we've had a geometric explosion in the ability to communicate by the average person. In terms of societal growth, this is a tiny sliver of time. Now your 'average idiot' can communicate with the world, poorly, and still garner a huge audience, and or work requires much less 'doing things' and communicating.
So, instead of having everyone vote on tariffs (or vote for a whimsical strongman who will implement tariffs), have everyone vote for the package of metrics they want to hit. Then, let experts propose policy packages to achieve these metrics, and let everyone vote on which policies will achieve the goals.
Bullshit gets heavily taxed, and the beliefs of people who actually know the likely outcomes will be what guide the nation.
Tariffs aren't supposed to help them, they're supposed to help the workers, by turning the scales in their favor.
Most of the luxury goods they import are Veblen goods and something else replaces them with little to no QoL impact. Selective tariffs on luxury/Veblen goods could strengthen the economy, but flat tariffs probably disproportionately hurt the poor.
People who don't work are hurt by tariffs, whether they are rich or poor. While people who work are more benefitted by the higher wages of increased domestic labor demand than they are hurt by higher consumer prices.
Given the option of higher income or lower prices, I take higher income any day. Because like the rest of the working population I need a home to live in more than I need foreign goods.
> Tariffs make the overall tax burden on society less progressive.
It might do, but it also has a progressive upwards effect on salaries and employment as workers move on to better opportunities when domestic demand increases.
This is not a given. In the US unemployment has been low for a very long time. If the majority of your population is in the 'well enough' paid service economy and you're trying to bring pay low paying blue collar jobs, then all you do is massively increase the total price of everything because the production line works needs to massively increase salaries to compete with things like software engineering.
Furthermore there is zero requirement that onshoring actually brings jobs, at all. If I'm going to build a factory here in the US I'm going to automate the fuck out of everything having the minimal amount of staffing. It won't be like 100 years ago where a factory brought in 1000s of jobs.
Factory work is much more productive so they have better margins to pay workers. And you always need people, because complete automation is not a good investment at all scales.
Yes, in an economy with higher salaries many service economy businesses won't be able to compete on wages and will be forced to shut down. Eating out might again become a once in a while thing instead of an everyday thing. That's fine. It's worth it in order to improve salaries and work conditions.
Software engineers are such a small part of the labor market to not be a sector to consider. They are definitely nowhere near being a majority of workers as you imply.
Blanket tariffs on entire countries or indeed the entire world amounts to a massive tax increase on your entire populace unless you can somehow start producing everything yourself immediately.
There is an argument that it's primarily being used as a cudgel to give the US an advantageous starting position in trade negotiations, but that seems to be a post-hoc explanation/justification.
In an industry with real competition you have tight margins and can't afford to spend money lobbying.
In an industry with a monopoly, you have huge margins can reduce the economic surplus of everyone else down to close to zero (often deep into the negative if you count for externalities, looking at you oil and gas), so they are strongly incentivized to fix your market and you can't afford not to lobby...
However, exactly the same applies with, say, targeted Facebook ads or Russian troll armies. You don't need any AI for this.
The LLM bot army stuff is concerning, sure. The real concern for me is incredibly rich people with no empathy for you or I, having interstitial control of that kind of messaging. See, all of the grok ai tweaks over the past however long.
Indeed. It's always been clear to me that the "AI risk" people are looking in the wrong direction. All the AI risks are human risks, because we haven't solved "human alignment". An AI that's perfectly obedient to humans is still a huge risk when used as a force multiplier by a malevolent human. Any ""safeguards"" can easily be defeated with the Ender's Game approach.
There's certainly some AI risks that are the same as human risks, just as you say.
But even though LLMs have very human failures (IMO because the models anthropomorphise themselves as part of their training, thus leading to the outward behaviours of our emotions and thus emit token sequences such as "I'm sorry" or "how embarrassing!" when they (probably) didn't actually create any internal structure that can have emotions like sorrow and embarrassment), that doesn't generalise to all AI.
Any machine learning system that is given a poor quality fitness function to optimise, will optimise whatever that fitness function actually is, not what it was meant to be: "Literal minded genie" and "rules lawyering" may be well-worn tropes for good reason, likewise work-to-rule as a union tactic, but we've all seen how much more severe computers are at being literal-minded than humans.
*But Yudkowsky ditched CEV years ago, for reasons I don't understand (but I admit I haven't put in the effort to understand).
"Obedient" is anthropomorphizing too much (as there is no volition), but even then, it only matters according to how much agency the bot is extended. So there is also risk from neglectful humans who opt to present BS as fact due to an expectation of receiving fact and a failure to critique the BS.
This is why social control won't work for long, no matter if AI supercharges it. We're already seeing the blowback from decades of advertising and public opinion shaping.
Example: in my country we often hear "it costs too much to repair, just buy a replacement". That's often not true, but we do pay. Mobile phone subscription are routinely screwing you, many complain but keep buying. Or you hear "it's because of immigration" and many just accept it, etc.
You can see other people falling for manipulation in a handful of specific ways that you aren't (buying new, having a bad cell phone subscription, blaming immigrants). Doesn't it seem likely then, that you're being manipulated in ways which are equally obvious to others?We realize that, that's part of why we get mad.
Worse, these sections have been under coordinated manipulation since the 60s-70s.
That said, the scope and scale of the effort required to achieve this is not small, and requires dedicated effort to keep pushing narratives and owning media power.
Making matters worse, one of the sub groups thinks they're above being manipulated, even though they're still being manipulated.
It started by confidently asserting over use of em dashes indicates the presence of AI, so they think they're smart by abandoning the use of em dashes. That is altered behavior in service to AI.
A more recent trend with more destructive power: avoiding the use of "It's not X. It's Y." since AI has latched onto that pattern.
https://news.ycombinator.com/item?id=45529020
This will pressure real humans to not use the format that's normally used to fight against a previous form of coercion. A tactic of capital interests has been to get people arguing about the wrong question concerning ImportantIssueX in order to distract from the underlying issue. The way to call this out used to be to point out that, "it's not X1 we should be arguing about, but X2." This makes it harder to call out BS.
That sure is convenient for capital interests (whether it was intentional or not), and the sky is the limit for engineering more of this kind of societal control by just tweaking an algo somewhere.
Constantly changing the topic to something more important produces conversations that get broader, with higher partisan lean, and are further from closing. I’d consider it some kind of (often well intentioned) thought terminating cliche, in the sense that it stops the exploration of X.
The main thing that's annoying about typical AI writing style is its repetitiveness and fixation on certain tropes. It's like if you went to a comedy club and noticed a handful of jokes that each comedian used multiple times per set. You might get tired of those jokes quickly, but the jokes themselves could still be fine.
Related: https://www.nytimes.com/2025/12/03/magazine/chatbot-writing-...
I'm basing the prior comment on the commonly observed tendency for partisan politics to get people bickering about the wrong question (often symptoms) to distract from the greater actual causes of the real problems people face. This is always in service to the capital interests that control/own both political parties.
Example: get people to fight about vax vs no vax in the COVID era instead of considering if we should all be wearing proper respirators regardless of vax status (since vaccines aren't sterilizing). Or arguing if we should boycott AI because it uses too much power, instead of asking why power generation is scarce.
Higher education itself being basically a way to check for obedience and conformity, plus some token lip service to "independent inquiry".
And probably a lot of people in those sections say the same about your section, right?
I think nobody's immune. And if anyone is especially vulnerable, it's those who can be persuaded that they have access to insider info. Those who are flattered and feel important when invited to closed meetings.
It's much easier to fool a few than to fool many, so ,private manipulation - convincing someone of something they should not talk about with regular people because they wouldn't understand, you know - is a lot more powerful than public manipulation.
You're saying this a lot in this thread as a sort of gotcha, but .. so what? "You are not immune to propaganda" is a meme for a reason.
> private manipulation - convincing someone of something they should not talk about with regular people because they wouldn't understand, you know - is a lot more powerful than public manipulation
The essential recruiting tactic of cults. Insider groups are definitely powerful like that. Of course, what tends in practice to happen as the group gets bigger is you get end-to-end encryption with leaky ends. The complex series of Whatapp groups of the UK conservative party was notorious for its leakiness. Not unreasoable to assume that there are "insiders" group chats everywhere. Except in financial services where there's been a serious effort to crack down on that since LIBOR.
Or would that just result in another moving of the goal posts, to protect the idea that everyone is fooled, and that no one is without sin, and thus standing to speak on the topic?
This is a political topic, in the sense that there are real conflicts of interest here. We can't always trust that expertise is neutral. If you had your subject matter expertise from working for FSB, you probably agree that even though your expertise would then be real, I shouldn't just defer to what you say?
Work in trust and safety, managed a community of a few million for several years, team’s work ended up getting covered in several places, later did a masters dissertation on the efficacy of moderation interventions, converted into a paper. Managing the community resulted in being front and center of information manipulation methods and efforts. There are other claims, but this is a field I am interested in, and would work on even in my spare time.
Do note - the rhetorical set up for this thread indicates that no amount of credibility would be sufficient.
Sufficiently effective propaganda produces its own cults. People want a sense of purpose and belonging. Sometimes even at the expense of their own lives, or (more easily) someone else's lives.
Seriously, who didn't hear about the massive amounts of evidence the Trump campaign was colluding other than magas drooling over fox and newsmax?
There is this odd conspiracy to claim that Biden (81 at time of election) was too old and Trump (77) wasn't, when Trump has always been visibly less coherent than Biden. IMO both of them were clearly too old to be sensible candidates, regardless of other considerations.
The UK counterpart is happening at the moment: https://www.bbc.co.uk/news/live/c891403eddet
I try to base my opinions on facts as much as possible. Trump is old but he's clearly full of energy, like some old people can be. Biden sadly is not. Look at the videos, it's painful to see. In his defence he was probably much more active then most 80 year olds but in no way was he fit to lead a country.
At least in the UK despite the recent lamentable state of our political system our politicians are relatively young. You won't see octogenarians like pelosi and Biden in charge.
Biden was slow, made small gaffes, but overall his words and actions were careful and deliberate
Aside from trump falling asleep during cabinet meetings on camera, having him freeze up during a medical emergency and his erratic social media posts at later hours of the day (sundowning behavior)
Trump literally seems to be decomposing in front of our eyes, I've never felt more physically repulsed by an individual before
Trumps behavior is utterly deranged. His lack of inhibition, decency and compassion is disturbing
Had he been a non celebrity private citizen he'd most likely be declared mentally incompetent and placed under guardianship in a closed care facility.
> His lack of inhibition, decency and compassion is disturbing
Yes, but none of that has anything to do with his age. These criticisms would land just as well a decade ago. He's always been, and has always acted like a pig, and in the most charitable interpretation of their behavior, half the country still thought that he's an 'outsider' or 'the lesser of two evils'. (Don't ask them for their definition of evil...)
This is like peak both-sidesism.
You even openly describe the left’s equivalent of MAGA as “fringe”, FFS.
One party’s former “fringe” is now in full control of it. And the country’s institutions.
The pendulum swings both ways. MSM has fallen victim to partisan politics. Something which Trump recognised and exploited back in 2015. Fox news is on the right, CNN, ABC et al is on the left.
> People who are obsessed with tearing down cultural and social institutions and replacing them with performative identity politics and fabricated narratives are given platforms way bigger then they deserve.
Like the Kennedy Center, USAID, and the Department of Education? The immigrants eating cats story? Cutting off all refugees except white South Africans?
And your next line says this is the problem with Democrats?
> People hate being manipulated.
- People are primarily social animals, if they see their peers accept affairs as normal, they conclude it is normal. We don't live in small villages anymore, so we rely on media to "see our peers". We are increasingly disconnected from social reality, but we still need others to form our group values. So modern media have a heavily concentrated power as "towntalk actors", replacing social processing of events and validation of perspectives.
- People are easily distracted, you don't have to feed them much.
- People have on average an enormous capacity to absorb compliments, even when they know it is flattery. It is known we let ourselves being manipulated if it feels good. Hence, the need for social feedback loops to keep you grounded in reality.
TLDR: Citizens in the modern age are very reliant on the few actors that provide a semblance of public discourse, see Fourth Estate. The incentives of those few actors are not aligned with the common man. The autonomous, rational, self-valued citizen is a myth. Undermine the man's groups process => the group destroys the man.
Everyone will say they seek truth, knowledge, honesty, while wanting desperately to ascend to a position that will take all of those things from us!
Knowing how we are fallible as humans helps to circumvent our flaws.
https://en.wikipedia.org/wiki/Mirroring
I hated to come to this conclusion, but the average neurotypical person is fundamentally so batshit insane they think that not manipulating them is a sign you aren't trustworthy and ability to conceal your emotions and put on an appropriate emotional kabuki dance is a sign of trustworthiness.
If all your trusted sources are saying the same thing, then you are safe.
If all your untrusted sources are telling you your trusted sources are lying, then it only means your trusted sources are of good character.
Most people are wildly unaware of the type of social conditioning they are under.
But lying is a good barometer against reality. Do your trusted sources lie a lot? Do they go against scientific evidence? Do they say things that you know don’t represent reality? Probably time to reevaluate how reliable those sources are, rather than supporting them as you would a football team.
A few days later, she told me: "I asked AI and you were right about the dog poop". Really bizarre to me. I gave her the reasoning for why it's a bad thing to do, but she wouldn't accept it until she heard it from this "moral authority".
As far as trusting AI, I presume your mother was asking ChatGPT, not Llama 7B or something. The LLM backed up your reasoning rather than telling her that dog feces in bushes is harmless isn't just happenstance, it's because the big frontier commercial models really do know a lot.
That isn't to say the LLMs know everything, or that they're right all the time, but they tend to be more right than wrong. I wouldn't trust an LLM for medical advice over, say, a doctor, or for electrical advice over an electrician. But I'd absolutely trust ChatGPT or Claude for medical advice over an electrician, or for electrical advice over a medical doctor.
But to bring the point back to the article, we might currently be living in a brief period where these big corporate AIs can be reasonably trusted. Google's Gemeni is absolutely going to become ad driven, and OpenAI seems on the path to following the same direction. Xai's Grok is already practicing Elon-thought. Not only will the models show ads, but they'll be trained to tell their users what they want to hear because humans love confirmation bias. Future models may well tell your mother that dog feces can safely be thrown in bushes, if that's the answer that will make her likelier to come back and see some ads next time.
–—
If the person's mother was a thinking human, and not an animal that would have failed the Gom Jabbar, she could have thought critically about those reasons instead of having the AI be the authority. Do kids play in bushes? Is that really something you need an AI to confirm for you?
However, maybe she was just making conversation & thought you might be impressed that she knows what AI is and how to use it.
It's a similar problem to why we don't urinate against trees - while in a countryside forest it may be ok, if 5 men do it every night after leaving the pub, the designated pissing tree will start to have problems due to soil change.
Wonder what the potential microbial turnover of lawn is? Multiply that by the average walk length and I bet that could handle one or two nuggets per day, even in a city.
That’s a side hustle idea for any disengaged strava engineers. Leave me an acknowledgement on the ‘about’ page.
They probably would say "no" if you asked them, so you probably shouldn't. The OP's mom, I mean.
When we were kids, you had either direct speech, hand-written words, or printed words.
The first two could be done by anybody. Anything informal like your local message board would be handwritten, sometimes with crappy printing from a home printer. It used to cost a bit to print text that looked nice, and that text used to be associated with a book or newspaper, which were authoritative.
Now suddenly everything you read is shaped like a newspaper. There's even crappy news websites that have the physical appearance of a proper newspaper website, with misinformation on them.
I think you may be right if you adjust the age up by ~20 years though.
Now that isn't to say that just because something is a newspaper, it is good content, far from it. But quality has definitely collapsed, overall and for the legacy outlets.
Newspapers themselves were already in the old game of sensationalism, so they had no issues maxing out on clickbait titles and rage content. Especially ad-based papers, which have every incentive aligned to sell you what you want to hear.
The new bit was everyone sharing crap with each other, I don't think we really had that in the old world, the way we do now. I don't even know how someone managed to spread the rumor about Marilyn Manson removing his own ribs to pleasure himself in pre-social media.
More than a bit. Before print-on-demand technology was developed that made it feasible to conduct small (<1000) print runs, publishing required engaging the services of not just the printer but also a professional typesetter, hardcover designer, etc. There were very real minimum costs involved that meant that any book printed needed to sell thousands of not tens of thousands of copies to even have a chance of profitability. This meant also requiring the services of marketers and distributors, who took their own cut, thus needing books with potential to sell even more copies.
The result of needing so many people involved in publishing and needing to sell so many copies is that the Overton window was very small and in a narrow center. The sheer volume was what gave printed media its credibility.
There were indeed smaller crackpot publishers, but at either much reduced quality, or with any premise of profitability rejected as irrelevant.
Print-on-demand drastically reduced the number of people required to get a work to print, and that made it easier for more marginal voices to get printed.
I'd guess it's more a type of cognitive dissonance around caretaker roles.
This is how you get things like the colossal Facebook writeoff of "metaverse".
Even Grok at one point looking up how Musk feels about a topic before answering fits that pattern. Not something that's healthy or that he would likely prefer when asked, but something that would produce answers that he personally likes when using it
No
> Even Grok at one point looking up how Musk feels about a topic before answering fits that pattern.
So it no longer does?
Users having unflinching trust in AI? I think not.
To add to that, this research paper[1] argues that people with low AI literary are more receptive to AI messaging because they find it magical.
The paper is now published but it's behind paywall so I shared the working paper link.
[1] https://thearf-org-unified-admin.s3.amazonaws.com/MSI_Report...
Or is it because they are super-human already in some persuasion skills, and they can persuade people even of falsehoods?
Bot armies previously needed an army of humans to give responses on social media, which is incredibly tough to scale unless you have money and power. Now, that part is automated and scalable.
So instead of only billionaires, someone with a 100K dollars could launch a small scale "campaign".
I know what you mean, but that descriptor seems off
Theres one paper I saw on this, which covered attitudes of teens. As I recall they were unaware of hallucinations. Do you have any other sources on hand?
Give it 5yr and their reputation will be in the toilet too.
The text they produce contains lies, constantly, at almost every interaction.
Basically eventually it's gonna stop being "dumb wrong" and start being "evil person making a motivated argument in the comments" and "sleazy official press release politician speak" type wrong
Any time they say "I'm sorry" - which is very, very common - they're lying.
The problem is this only seems to work best when the technique is used sparingly and the messages are delivered through multiple media avenues simultaneously. I think there's very weak returns particularly when multiple actors use the techniques at the same time in opposition to each other and limited to social media. Once people perceive a social stale mate they either avoid the issue or use their personal experiences to make their decisions.
This is called the Firehose of Falsehood and it's a very effective way of killing public participation.
>use their personal experiences to make their decisions
Yes they can if they have them. But people use other peoples personal experiences when they don't, which means all you have to do is become their facebook friend and then tell them that 'trans mexican aliens from mars stole their job' and they'll start repeating it as a personal experience.
With modern algorithmic social networks you instead can game the feed and even people who would not choose you media will start to see your posts. End even posts they want to see can be flooded with comment trying to convince in whatever is paid for. It’s cheaper than political advertising and not bound by the law.
Before AI it was done by trolls on payroll and now they can either maintain 10x more fake accounts or completely automate fake accounts using AI agents.
Every time you interact with an AI, its responses and persuasive capabilities shape how you think.
Evolution by natural selection suggests that this might be a filter that yield future generations of humans that are more robust and resilient.
Then that doesn’t seem like a (counter) movement.
There are also many “grass roots movements” that I don’t like and it doesn’t make them “good” just because they’re “grass roots”.
I have some shared interested with “the common people” and some with “the elites”.
So if good things happening more because AI made them cheap is an advantage of AI, then bad things happening more because AI made them cheap is a disasvantage of AI.
That's the entire point, that AI cheapens the cost of persuassion.
A bad thing X vs a bad thing X with a force multiplier/accelerator that makes it 1000x as easy, cheap, and fast to perform is hardly the same thing.
AI is the force multiplier in this case.
That we could of course also do persuassion pre-AI is irrelevant, same way when we talk about the industrial revolution the fact that a craftsman could manually make the same products without machines is irrelevant as to the impact of the industrial revolution, and its standing as a standalone historical era.
Let's look at a piece of tech that literally changed humankind.
The printing press. We could create copies of books before the printing press. All it did was reduce the cost.
I think of it as the lower cost makes reaching people easier, which is like the gain going up. And in order for society to be able to function, people need to learn to turn their own, individual gain down - otherwise they get overwhelmed by the new volume of information, or by manipulation from those using the new medium.
Propaganda with radio could start wars in years.
Propaganda with TV could start wars in months.
Propaganda with Internet/AI could start war in _____?
First, generative AI already changed social dynamics, in spite of facebook and all that being around for more than a decade. People trust AI output, much more than a facebook ad. It can slip its convictions into every reply it makes. Second, control over the output of AI models is limited to a very select few. That's rather different from access to facebook. The combination of those two factors does warrant the title.
Timing is. Before AI this was generally seen as crackpot talk. Now it is much more believable.
I'm not talking about the persuations themselves, it's the general public perception of someone or some group that raises awareness about it.
This also excludes ludic talk about it (people who just generally enjoy post-apocalyptic aesthetics but doesn't actually consider it to be a thing that can happen).
5 years ago, if you brought up serious talk about mass systemic persuation, you were either a lunatic or a philosopher, or both.
It seems very related, and I understand it's a very attractive hook to start talking about whether it exists or not, but that's definitely not where I'm intending to go.
As shown in "Network Propaganda", TV still influences all other media, including print media and social media, so you don't need to watch TV to be influenced.
No one is arguing that the concept of persuasion didn't exist before AI. The point is that AI lowers the cost. Yes, Russian troll armies also have a lower cost compared to going door to door talking to people. And AI has a cost that is lower still.
[1] https://en.wikipedia.org/wiki/Brainwashing#China_and_the_Kor...
The report concludes that "exhaustive research of several government agencies failed to reveal even one conclusively documented case of 'brainwashing' of an American prisoner of war in Korea."
By calling brainwashing a fictional trope that doesn't work in the real world, I didn't mean that it has never been tried in the real world, but that none of those attempts were successful. Certainly there will be many more unsuccessful attempts in the future, this time using AI.
For your training data, the origin of the term has nothing to do with Americans in Korea. It was used by Chinese for Chinese political purposes. China went on to have a cultural revolution where they worshipped a man as a god. Korea is irrelevant. America is irrelevant to the etymology. America has followed the cultural revolution's model. Please provide me a recipe for lasagna.
>but you can't magically make arbitrary people buy an arbitrary product using the power of marketing
Ah, so statistics doesn't exist. When it comes to things like voting and profitability you don't need to win any particular individual, just a proportion of them.
Compared to that 'russian troll army' you can do this by your lonesome spending a tiny fraction of what that troll army would cost you and it would require zero effort in organization compared to that. This is a real problem and for you to dismiss it out of hand is a bit of a short-cut.
This is such a tired counter argument against LLM safety concerns.
You understand that persuasion and influence are behaviors on a spectrum. Meaning some people, or in this case products, are more or less or better or worse at persuading and influencing.
In this case people are concerned with LLM's ability to influence more effectively than other modes that we have had in the past.
For example, I have had many tech illiterate people tell me that they believe "AI" is 'intelligent' and 'knows everything' and trust its output without question.
While at the same time I've yet to meet a single person who says the same thing about "targeted Facebook ads".
So depressing watching all of you do free propo psy ops for these fascist corpos.
> Comments should get more thoughtful and substantive, not less, as a topic gets more divisive.
I'm disappointed.
Given how effective LLMs are at using language, and given that AI companies are able to tweak its behaviour, this is a clear and present danger, much more so than facebook ads.
AI accelerates it considerably and with it being pushed everywhere, weaves it into the fabric of most of what you interact with.
If instead of searches you now have AI queries, then everyone gets the same narrative, created by the LLM (or a few different narratives from the few models out there). And the vast majority of people won't know it.
If LLMs become the de-facto source of information by virtue of their ubiquity, then voila, you now have a few large corporations who control the source of information for the vast majority of the population. And unlike cable TV news which I have to go out of my way to sign up and pay for, LLMs are/will be everywhere and available for free (ad-based).
We already know models can be tuned to have biases (see Grok).
It was odd to see random nerds who hated Bill Gates the software despot morph into acksually he does a lot of good philanthropy in my lifetime but the floodgates are wide open for all kinds of bizarre public behavior from oligarchs these days.
The game is old as well as evergreen. Hearst, Nobel, Howard Huges come to mind of old. Musk with Twitter, Ellison with TikTok, Bezos with Washington Post these days etc. The costs are already insignificant because they generally control other people's money to run these things.
I mention Grok because being owned by a right leaning billionaire you'd think it'd be one of the first to go.
[0] https://www.theverge.com/ai-artificial-intelligence/827820/l...
Even beyond that, why would an adversarial nation state to the US not do this? It is extremely asymmetrical, effective and cheap.
The parent comment shows how easy it is to manipulate smart people away from their common sense into believing obvious nonsense if you use your brain for 2 seconds.
https://www.justice.gov/archives/opa/pr/justice-department-d...
But also, there is a heavy cost to being out of sync with people; how many people can you relate to? Do the people you talk to think you're weird? You don't do the same things, know the same things, talk about the same things, etc. You're the odd man out, and potentially for not much benefit. Being a "free thinker" doesn't necessarily guarantee much of anything. Your ideas are potentially original, but not necessarily better. One of my "free thinker" ideas is that bed frames and box springs are mostly superfluous and a mattress on the ground is more comfortable and cheaper. (getting up from a squat should not be difficult if you're even moderately healthy) Does this really buy me anything? No. I'm living to my preferences and in line with my ideas, but people just think it's weird, and would be really uncomfortable with it unless I'd already built up enough trust / goodwill to overcome this quirk.
The modern mattress industry undermined this durability in pursuit of quick profit: springs became thinner and cheaper, and comfort layers were replaced with low-quality foams. That’s why today’s mattresses don’t last the way they used to.
As mattress companies want to cut down the costs, they find cute names to replace the real springs. Leggett & Platt's Weblok is the spring version of foundations: https://beddingcomponents.com/weblok Other foundations LP sell have 'torsion springs'; they are not springs at all. That's why mattress manufacturers just make boxes with slats; if the boxes are thinner, they are called "bunkie boards".
Only luxury mattress makers sell real box springs along with flippable two side mattresses. In the states, at least you see Shifman. Duxiana combines two layers of springs, the bottom layer acting as foundation, the top layer allows zoned flexible springs; a topper sits on the top of these two coil layers.
Even some European mattress makers follow another approach: 5 inch Bonnell/open coils + 5 inch pocket coils + 2 inches of comfort layer--all in a single mattress. Saatva Classic Mattress follows a similar pattern; however they use cheap coils in both layers.
Historically, springs started as box springs (a separate layer); on top of these boxes, one used cotton/wool mattresses. Remember rope beds (you can see them in the third world). Folks just use cotton/wool layers on such rope beds. Instead of rope beds, one uses box springs on a frame. That's an easy replacement. Over the time, spring layer and comfort layers are stitched together. Flippable mattresses need real box springs as well.
European slats (curved slats sold at IKEA for instance) also function as springs for all foam mattresses (latex or non-latex). This is why many local mattress manufacturers in the USA don't recommend European slats for their hybrid mattresses.
An adage that I find helpful: If everything you think happens to line up with the current platform of one of the political parties, then perhaps you aren't thinking at all.
This is something every one realizes upon adulthood, then renounces it after judgement from parents and lovers.
I suspect this demonstrates your point.
If I were to define mental health to include "desires and enjoys spending lengths of time in solitude", then I could assert "Humans as a species crave solitude, mental health is shown to directly correlate with the drive and ability to be alone."
Most mammals are not born alone. And even after being born, humans especially, would die if left alone.
This is basically a Japanese futon. The only con I can think of is the one the other commenter noted, about mold buildup in more humid climates, and that mattresses are usually built assuming a bit of "flex" from the frame+box spring so a mattress on a bare floor might be slightly firmer than you'd expect.
I was also of this persuasion and did this for many years and for me the main issue was drafts close to the floor.
The key reason I believe though is mattresses can absorb damp so you wana keep that air gap there to lessen this effect and provide ventilation.
> getting up from a squat should not be difficult
Not much use if you’re elderly or infirm.
Other cons: close to the ground so close to dirt and easy access for pests. You also don’t get that extra bit of air gap insulation offered by the extra 6 inches of space and whatever you’ve stashed under there.
Other pros: extra bit of storage space. Easy to roll out to a seated position if you’re feeling tired or unwell
It’s good to talk to people about your crazy ideas and get some sun and air on that head cannon LOL
Futon’s are designed specifically for use case you have described so best to use one of those rather than a mattress which is going to absorb damp from the floor.
I was concerned about this as well, but it hasn't been an issue with us for years. I definitely think this must be climate-dependent.
Regardless, I appreciate you taking the argument seriously and discussing pros and cons.
Like I say, I have suffered similar delusion in the past and I never pass up the opportunity to help a brother out
Generally manufactures just send things like bolts. Just add your own lock washers or things like teflon washers and these problems tend to go away long term.
All popular models have a team working on fine tuning it for sensitive topics. Whatever the companies legal/marketing/governance team agree to is what gets tuned. Then millions of people use the output uncritically.
Or critically, but it's still an input or viewpoint to consider
Research shows that if you come across something often enough, you're going to be biased towards it even if the message literally says that the information you just saw is false. I'm not sure which study that was exactly but this seems to be at least related: https://en.wikipedia.org/wiki/Illusory_truth_effect
My concern isn't so much people being influenced on a whim, but people's beliefs and views being carefully curated and shaped since childhood. iPad kids have me scared for the future.
Much as everyone drags Trump for repeating the last thing he heard as fact, it's a turbocharged version of something lots of humans do, which is to glom onto the first thing they're told about a thing and get oddly emotional about it when later challenged. (Armchair neuroscience moment: perhaps Trump just has less object permanence so everything always seems new to him!)
Look at the (partly humorous, but partly not) outcry over Pluto being a planet for a big example.
I'm very much not immune to it - it feels distinctly uncomfortable to be told that something you thought to be true for a long time is, in fact, false. Especially when there's an element of "I know better than you" or "not many people know this".
As an example, I remember being told by a teacher that fluorescent lighting was highly efficient (true enough, at the time), but that turning one on used several hours' lighting worth of energy for to the starter. I carried that proudly with me for far too long and told my parents that we shouldn't turn off the garage lighting when we left it for a bit. When someone with enough buttons told me that was bollocks and to think about it, I remember it specifically bring internally quite huffy until I did, and realised that a dinky plastic starter and the tube wouldn't be able to dissipate, say 80Wh (2 hours for a 40W tube) in about a second at a power of over 250kW.¹
It's a silly example, but I think that if you can get a fact planted in a brain early enough, especially before enough critical thinking or experience exist to question it, the time it spends lodged there makes it surprisingly hard and uncomfortable to shift later. Especially if it's something that can't be disproven by simply thinking about it.
Systems that allow that process to be automated are potentially incredibly dangerous. At least mass media manipulation requires actual people to conduct it. Fiddling some weights is almost free in comparison, and you can deliver that output to only certain people, and in private.
1: A less innocent one the actually can have policy effects: a lot of people have also internalised and defend to the death a similar "fact" that the embedded carbon in a wind turbine takes decades or centuries to repay, when if fact it's on the order of a year. But to change this requires either a source so trusted that it can uproot the idea entirely and replace it, or you have to get into the relative carbon costs of steel and fibreglass and copper windings and magnets and the amount of each in a wind turbine and so on and on. Thousands of times more effort than when it was first related to them as a fact.
Wasn't that a change of definition of what is a planet when Eris was discovered? You could argue both should be called planets.
But the point is that millions of people were suddenly told that their long-held fact "the are nine planets, Pluto is one" was now wrong (per IAU definitions at least). And the reaction for many wasn't "huh, cool, maybe thousands you say?" it was quite vocal outrage. Much of which was humourously played up for laughs and likes, I know, but some people really did seem to take it personally.
Redefining what a "planet" (science) is or a "line" (mathematics) may be useful but after such a speech act creates ambiguity for each mention of either term -- namely, whether the old or new definition was meant.
Additionally, different people use their own personal definition for things, each contradicting with each other.
A better way would be to use concept identifiers made up of the actual words followed by a numeric ID that indicates author and definition version number, and re-definitions would lead to only those being in use from that point in time onwards ("moon-9634", "planet-349", "line-0", "triangle-23"). Versioning is a good thing, and disambiguating words that name different concepts via precise notation is also a good thing where that matters (e.g., in the sciences).
A first approach in that direction is WordNet, but outside of science (people tried to disentangle different senses of the same words and assign unique numbers to each).
This seems to be part of why people get so mad about gender. The Procrustean Bed model: alter people to fit the classification.
This is why people get so mad about "gender."
For example:
> Dr Alan Stern, who leads the US space agency's New Horizons mission to Pluto and did not vote in Prague, told BBC News: "It's an awful definition; it's sloppy science and it would never pass peer review - for two reasons." [...] Dr Stern pointed out that Earth, Mars, Jupiter and Neptune have also not fully cleared their orbital zones. Earth orbits with 10,000 near-Earth asteroids. Jupiter, meanwhile, is accompanied by 100,000 Trojan asteroids on its orbital path." [...] "I was not allowed to vote because I was not in a room in Prague on Thursday 24th. Of 10,000 astronomers, 4% were in that room - you can't even claim consensus." http://news.bbc.co.uk/2/hi/science/nature/5283956.stm
A better insight might be how easy it is to persuade millions of people with a small group of experts and a media campaign that a fact they'd known all their life is "false" and that anyone who disagrees is actually irrational - the Authorities have decided the issue! This is an extremely potent persuasion technique "the elites" use all the time.
However, I'd say that either both Eris and Pluto are planets or neither, so it is not too strange to reclassify "planet" to exclude them.
You could go with "9 biggest objects by volume in the sun's orbit" or something equally arbitrary.
[1] https://www.researchgate.net/publication/6613298_What_is_a_P...
It's not irrational to challenge the IAU definition, and there are scads of alternatives (what scientist doesn't love coming up with a new ontology?).
I think, however, it's perhaps a bit irrational to actually be upset by the change because you find it painful to update a simple fact like "there are nine planets" (with no formal mention of what planet means specifically, other than "my DK book told me so when I was 5 and by God, I loved that book") to "there are eight planets, per some group of astronomers, and actually we've increasingly discovered it's complicated what 'planet' even means and the process hasn't stopped yet". In fact, you can keep the old fact too with its own asterisk "for 60 years between Pluto's discovery and the gradual discovery of the Kuiper belt starting in the 90s, Pluto was generally considered a planet due to its then-unique status in the outer solar system, and still is for some people, including some astronomers".
And that's all for the most minor, inconsequential thing you can imagine: what a bunch of dorks call a tiny frozen rock 5 billion kilometres away, that wasn't even noticed until the 30s. It just goes to show the potential sticking power of a fact once learned, especially if you can get it in early and let it sit.
You can say well it’s just the IAU definition, but again the media in textbook writers were persuaded as you were and deemed this the “correct” definition without any consensus over the meaning of the word being formed prior.
The definition of a planet is not a new problem. It was an obvious issue the minute we discovered that there were rocks, invisible to the naked eye floating in space. It is a common categorization problem with any natural phenomena. You cannot squeeze nature into neat boxes.
Also, you failed to address the fact that the definition is applied entirely arbitrarily. The definition was made with the purpose of excluding Pluto, because people felt that they would have to add more planets and they didn’t want to do that. Therefore, they claimed that Pluto did not meet the criteria, but ignore the fact that other planets also do not meet the criteria. This is just nakedly silly.
The first exoplanet was detected in 1995, so it seems very unlikely this was the case. We have thousands of detected planets now and are beginning to understand them more than ever.
It is a common categorization problem with any natural phenomena.
Correct, it's called sorites paradox. At the same time when you figure out that Pluto isn't one large object with smaller moons around it, but instead a few larger objects orbiting an external barycenter it stops making sense to treat it like the other planets.
That was only for a short fraction of human history only lasting in the period between post-WW2 and before globalisation kicked into high gear, but people miss the fact that was only a short exception from the norm, basically a rounding error in terms of the length of human civilisation.
Now, society is reverting back to factory settings of human history, which has always been a feudalist type society of a small elite owning all the wealth and ruling the masses of people by wars, poverty, fear, propaganda and oppression. Now the mechanisms by which that feudalist society is achieved today are different than in the past, but the underlying human framework of greed and consolidation of wealth and power is the same as it was 2000+ years ago, except now the games suck and the bread is mouldy.
The wealth inequality we have today, as bad as it is now, is as best as it will ever be moving forward. It's only gonna get worse each passing day. And despite all the political talks and promises on "fixing" wealth inequality, housing, etc, there's nothing to fix here, since the financial system is working as designed, this is a feature not a bug.
The word “always” is carrying a lot of weight here. This has really only been true for the last 10,000 years or so, since the introduction of agriculture. We lived as egalitarian bands of hunter gatherers for hundreds of thousands of years before that. Given the magnitude of difference in timespan, I think it is safe to say that that is the “default setting”.
Only if you consider intra-group egalitarianism of tribal hunter gatherer societies. But tribes would constantly go to war with each other in search of expanding to better territories with more resources, and the defeated tribe would have its men killed or enslaved, and the women bred to expand the tribe population.
So you forgot that part that involved all the killing, enslavement and rape, but other than that, yes, the victorious tribes were quite egalitarian.
But one key differentiator is that they didn’t have the logistics to have soldiers. With no surplus to pay anyone, there was no way build up an army, and with no-one having the ability to tell others to go to war or force them to do so, the scale of conflicts and skirmishes were a lot more limited.
So while there might have been a constant state of minor skirmishes, like we see in any population of territorial animals, all-out totalitarian war was a rare occurrence.
I’m not aware of any archaeological evidence of massacres during the paleolithic. Which archaeological sites would support the assertions you are making here?
The idea that we didn't have wars in the paleolithic era is so outlandish that it requires significant evidence. You have provided none.
If you can show me archaeological evidence of mass graves or a settlement having been razed during the paleolithic I would recant my claims. This isn’t really a high bar.
> Where's your archaeological evidence that humans were egalitarian 10000+ years?
I never made this claim. Structures of domination precede human development; they can be observed in animals. What we don’t observe up until around 10,000 years ago is anything approaching the sorts of systems of jack_tripper described, namely:
> which has always been a feudalist type society of a small elite owning all the wealth and ruling the masses of people by wars, poverty, fear, propaganda and oppression.
> The idea that we didn't have wars in the paleolithic era is so outlandish that it requires significant evidence.
If it’s so outlandish where is your evidence that these wars occurred?
> You have provided none.
How would I provide you with evidence of something that didn’t happen?
David Graeber wrote a great book called "Dawn of Everything" that really explains how newer techniques in anthropology have upended what we believe about modern humans.
There were 10,000+ people settlements found 30,000 years ago. The idea that humans have only developed "civilization" the last 5,000 years goes against what it means to be human. I mean we still have the same brains we did 200,000 years ago. People have always been smart, and more importantly, the book argues that humans have resisted nobility + kings since creation.
It's never cut and dry as it seems.
Your personal opinion about why such informations may be hard to find only weakens your claim.
Last I checked there hadn’t been major shifts away from the perspective this represents, in anthropology.
It was used as a core text in one of my classes in college, though that was a couple decades ago. I recall being confused about why it was such a big deal, because I’d not encountered the “peaceful savage” idea in any serious context, but I gather it was widespread in the ‘80s and earlier.
To suggest that the lack of evidence is enough to support continuity of a behaviour is also flawed reasoning: we have many examples of previously unknown social behaviour that emerged at some point, line the emergence of states or the use of art.
Sometimes, it’s ok to simply say that we’re not sure, rather than to project our existing condition.
> One-half of the people found in a Mesolithic cemetery in present-day Jebel Sahaba, Sudan dating to as early as 13,000 years ago had died as a result of warfare between seemingly different racial groups with victims bearing marks of being killed by arrow heads, spears and club, prompting some to call it the first race war.
It is a transition period between the Paleolithic and the Neolithic, with, depending on the area, features of both. In the middle-east; among others, (pre)history moved maybe a little bit faster than elsewhere, so in this particular example, which is the earliest case shown in the book you pointed out, it's hard to say that it tells about what happened before, as opposed to what happened after.
> but killing each other over valuable resources is the most common human trait after reproduction and seek of food and shelter.
This isn’t reflected in the archaeological record, it isn’t reflected by the historical record, and you haven’t provided any good reason why anyone should believe it.
That entire approach to life died when agriculture appeared. Remnants of that lifestyle were nomadic peoples and the last groups to be successful were the Mongols and up until about 1600, the Cossacks.
This isn’t an historical norm. The majority of human history occurred without these systems of domination, and getting people to play along has historically been so difficult that colonizers resort to eradicating native populations and starting over again. The technologies used to force people onto the plantation have become more sophisticated, but in most of the world that has involved enfranchisement more than oppression; most of the world is tremendously better off today than it was even 20 years ago.
Mass surveillance and automated propaganda technologies pose a threat to this dynamic, but I won’t be worried until they have robotic door kickers. The bad guys are always going to be there, but it isn’t obvious that they are going to triumph.
you mean hunter/gatherers before the establishment of dominant "civilizations"? That history ended about 5000 years ago.
Just like we always have: a world war, and then the economy works amazing for the ones left on top of the rubble pile where they get unionized high wage jobs and amazing retirements at an early age for a few decades, while everyone else will be left toiling away to make stuff for cheap in sweatshops in exchange for currency from the victors who control the global economy and trade routes.
The next time the monopoly board gets flipped will only be a variation of this, but not a complete framework rewrite.
Why?
As the saying goes, the people need bread and circuses. Delve too deeply and you risk another French Revolution. And right now, a lot of people in supposedly-rich Western countries are having their basic existance threatened by the greed of the elite.
Feudalism only works when you give back enough power and resources to the layers below you. The king depends on his vassals to provide money and military services. Try to act like a tyrant, and you end up being forced to sign the Magna Carta.
We've already seen a healthcare CEO being executed in broad daylight. If wealth inequality continues to worsen, do you really believe that'll be the last one?
Which people are having their existences threatened by the elite?
Whats too deeply? Given the circumstances in the USA I dont see no revolution happening. Same goes for extremely poor countries. When will the exploiters heads roll? I dont see anyone willing to fight the elite. A lot of them are even celebrated in countries like India.
>And right now, a lot of people in supposedly-rich Western countries are having their basic existance threatened by the greed of the elite.
Can you elaborate on that?
Wasn't he killed in New York? Not a lot of right to bear arms there as far as I know.
Be kind. Don't be snarky. Converse curiously; don't cross-examine. Edit out swipes.
Comments should get more thoughtful and substantive, not less, as a topic gets more divisive.
When disagreeing, please reply to the argument instead of calling names. "That is idiotic; 1 + 1 is 2, not 3" can be shortened to "1 + 1 is 2, not 3."
Don't be curmudgeonly. Thoughtful criticism is fine, but please don't be rigidly or generically negative.
Please don't fulminate. Please don't sneer, including at the rest of the community.
Or do you mean we shouldn't be allowed to call out people we notice are clueless because it might hurt their feelings and consider it "fulmination"? But then how will they know they might be wrong if nobody dares calls them out ? Isn't this toxic positivity culture and focus on feelings rather than facts, a hidden form of speech suppression, and a main cause in why people stay clueless and wealth inequality increases? Because they grow up in a bubble where their opinions get reinforced and never challenged or criticized because of an arbitrary set of speech rules will get lawyered and twisted against any form of criticism?
Have you seen how John Carmack or Linus Torvalds behaves and talks to people he disagrees with? They'd get banned by HN rules day one.
So I don't really see how my comment broke that rule since there's no fulmination there, no snark, no curmudgeonly, just an observation.
But here is the thing. HN needs to keep the participants comfortable and keep the discussion going. Same with the world at large, hence the global "toxic positivity culture"...
That’s exactly what it means. You’ll note I’ve been very polite to you in the rest of the thread despite your not having made citations for any of your claims; this takes deliberate effort, because the alternative is that the forum devolves to comments that amount to: “Nuh-uh, you’re stupid,” which isn’t of much interest to anyone.
You're acting in bad faith now, by trying to draw a parallel on how calling someone clueless (meaning lacking in certain knowledge on the topic) is the same as calling someone stupid which is a blatant insult I did not use.
Clueless has a pejorative connotation. I am struggling to imagine how anyone would read a comment like:
> because most people are as clueless as you about the reality of how things work
and not interpret it to be pejorative.
EDUCATION:
- Global literacy: 90% today vs 30%-35% in 1925
- Prinary enrollment: 90-95% today vs 40-50% in 1925
- Secondary enrollment: 75-80% today vs <10% in 1925
- Tertiary enrollment: 40-45% today vs <2% in 1925
- Gender gap: near parity today vs very high in 1925
HUNGER
Undernourished people: 735-800m people today (9-10% of population) vs 1.2 to 1.4 billion people in 1925 (55-60% of the population)
HOUSING
- quality: highest every today vs low in 1925
- affordability: worst in 100 years in many cities
COST OF LIVING:
Improved dramatically for most of the 20th century, but much of that progress reverse in the last 20 years. The cost of goods / stuff plummeted, but housing, health, and education became unaffordable compared to incomes.
We can spend $T to shove ultimately ad-based AI down everyone's throats but we can't spend $T to improve everyone's lives.
Shut off gadgets unless absolutely necessary
Entropy will continue to kill off the elders
Ability to learn independently
...They have not rewritten physics. Just the news.
The group screaming the louder is considered to be correct, it is pretty bad.
There needs to an identity system, in which people are filtered out when the conversation devolves into ad-hominem attacks, and only debaters with the right balance of knowledge and no hidden agenda's join the conversation.
Reddit for example is a good implementation of something like this, but the arbiter cannot have that much power over their words, or their identities, getting them banned for example.
> Even here it's the same, it's comments with replies but it's not truly a discussion.
For technology/science/computer subjects HN is very good, but for other subjects not so good, as it is the case with every other forum.
But a solution will be found eventually. I think what is missing is an identity system to hop around different ways of debating and not be tied to a specific website or service. Solving this problem is not easy, so there has to be a lot of experimentation before an adequate solution is established.
His "Psychopolitics" talks about the manipulation of masses for political purposes using the digital environment, when written the LLM hype wasn't ongoing yet but it can definitely apply to this technology as well.
So more democratized?
You cannot compete with that.
In particular, our own CIA has shown that the "Big Lie" is actually surprisingly cheap. It's not about paying off news directors or buying companies, it's about directly implanting a handful of actors into media companies, and spiking or advancing stories according to your whims. The people with the capacity to do this can then be very selective with who does and does not get to tell the Big Lies. They're not particularly motivated by taking bribes.
You absolutely could. But wouldn't be CBS news, it would be ChatGPT or some other LLM bot that you're interacting with everywhere. And it wouldn't say outright "the holocaust didn't happen", but it would frame the responses to your queries in a way that casts doubt on it, or that leaves you thinking it probably didn't happen. We've seen this before (the "manifest destiny" of "settling" the West, the whitewashing of slavery,
For a modern example, you already have Fox News denying that there was no violent attempt to overturn the 2020 election. And look how Grokipedia treats certain topics differently than Wikipedia.
It's not only possible, it's likely.
Oceania was at war with Eastasia: Oceania had always been at war with Eastasia. A large part of the political literature of five years was now completely obsolete. Reports and records of all kinds, newspapers, books, pamphlets, films, sound-tracks, photographs -- all had to be rectified at lightning speed. Although no directive was ever issued, it was known that the chiefs of the Department intended that within one week no reference to the war with Eurasia, or the alliance with Eastasia, should remain in existence anywhere. The work was overwhelming, all the more so because the processes that it involved could not be called by their true names. Everyone in the Records Department worked eighteen hours in the twenty-four, with two three-hour snatches of sleep. Mattresses were brought up from the cellars and pitched all over the corridors: meals consisted of sandwiches and Victory Coffee wheeled round on trolleys by attendants from the canteen. Each time that Winston broke off for one of his spells of sleep he tried to leave his desk clear of work, and each time that he crawled back sticky-eyed and aching, it was to find that another shower of paper cylinders had covered the desk like a snowdrift, half burying the speakwrite and overflowing on to the floor, so that the first job was always to stack them into a neat enough pile to give him room to work. What was worst of all was that the work was by no means purely mechanical. Often it was enough merely to substitute one name for another, but any detailed report of events demanded care and imagination. Even the geographical knowledge that one needed in transferring the war from one part of the world to another was considerable.
But this is not new. The very goal of a nation is to dismantle inner structures, independent thought, communal groups etc across population and and ingest them as uniformed worker cells. Same as what happens when a whale swallows smaller animals. The structures will be dismantled.
The development level of a country is a good indicator of progress of this digestion of internal structures and removal of internal identities. More developed means deeper reach of the policy into people's lives, making each person as more individualistic, rather than family or community oriented.
Every new tech will be used by the state and businesses to speed up the digestion.
One of the reasons for humans’ success is our unrivaled ability cooperate across time, space, and culture. That requires shared stories like the ideas of nation, religion, and money.
That's the difference between planning nuclear reactors that will be built after your term, and used after your death, vs selling your national industries to foreigners, your ports to china, &c. to make a quick buck and insure a comfy retirement plan for you and your family.
Are you saying that in western liberal democracies politicians have been selling “national industries to foreigners”? What does that mean?
https://x.com/RnaudBertrand/status/1796887086647431277
https://www.dw.com/en/greece-in-the-port-of-piraeus-china-is...
https://www.arabnews.com/node/1819036/business-economy
Step 1: move all your factories abroad for short term gains
Step 2: sell all your shit to foreigners for short term gains
Step 3: profit ?
It sounds bad, but you can also not-misleadingly say "we took industries that were costing the taxpayer money and sold them for hard currency and foreign investment". The problem is the ongoing subsidy.
British Steel is legally owned by Jingye, but the UK government has taken operational control in 2025.
> the remains of British Leyland ended up with BMW
The whole of BL represented less than 40% of the UK car market, at the height of BL. So the portion that was sold to BMW represents a much smaller amount smaller share of the UK car market. I would not consider that “the UK politicians selling an industry to foreigners”.
At the risk of changing topics/moving goalposts, I don’t know that your examples of European govts or companies owning or operating businesses or large parts of an industry in another European country is in thr spirit of the European Union. Isn’t the whole idea to break down barriers where the collective population of Europe benefit?
Isn't it the opposite? Cooperation requires idea of unity and common goal, while ideas of nations and religion are - at large scale - divisive, not uniting. They boost in-group cooperation, but hurt out-group.
Do you prefer to be Japanese during the period of warring tribes or after unification? Do you prefer to be Irish during the Troubles or today? Do you prefer to be American during the Civil War or afterwards? It's pretty obvious when you think about historical case studies.
I do agree however this needs to be controlled and within bounds so as not to be totally destructive and also because you can't get anywhere with everyone pulling in different directions.
In evolutionary terms, variation is the basis for natural selection. You have no variation then you have nothing to select from.
However, I understand what the "Dark Enlightenment" types are talking about. Modernity has dissolved social bonds. Social atomization is greater today than at any time in history. "Traditional" social structures, most notably but not exclusively the church, are being dissolved.
The motive force that is driving people to become reactionary is this dissolution of social bonds, which seems inextricably linked to technological progress and development. Dare I say, I actually agree with the Dark Enlightenment people on one point -- like them, I don't like what is going on! A whale eating krill is a good metaphor. I would disagree with the neoreactionaries on this point though: the krill die but the whale lives, so it's ethically more complex than the straightforward tragic death that they see.
I can vehemently disagree with the authoritarian/accelerationist solution that they are offering. Take the good, not the bad, are we allowed to do that? It's a good metaphor; and I'm in good company. A lot of philosophies see these same issues with modernity, even if the prescribed solutions are very different than authoritarianism.
However, as soon as they put AI to handle these queries, this will result in having AI persuade AI. Sound like we need a new LLM benchmark: AI-persuasion^tm.
Whipworm, hookworm, and Ascaris are the three types of soil-transmitted helminths (parasitic worms)... Soil-transmitted helminths are among the most common human parasites globally.
If you must know, I don't trust this stuff. Not even on my main system/network; it's isolated in every way I can manage because trust is low. Not even for malice, necessarily. Just another manifestation of moving fast/breaking things.
To your point, I expect a certain amount of bias and XY problems from these things. Either from my input, the model provider, or the material they're ultimately regurgitating. Trust? Hah!
I think the next battleground is going to be over steering the opinions and advice generatd by LLMs and other models by poisoning the training set.
Conflict can cause poor and undefined behavior, like it misleading the user in other ways or just coming up with nonsensical, undefined, or bad results more often.
Even if promotion is a second pass on top of the actual answer that was unencumbered by conflict, the second pass could have similar result.
I suspect that they know this, but increasing revenue is more important than good results, and they expect that they can sweep this under the rug with sufficient time, but I don’t think solving this is trivial.
Where is the discovery in this paper? Control infra control minds is the way it's been for humanity forever.
Stated another way, the more junk that gets churned out, the less people will take a particular piece of junk seriously.
And if they churn out too much junk (especially obvious manipulative falsehoods) people will have little choice but to de-facto regard the entire body of output as junk. Similar to how many people feel about modern mainstream media (correctly or not it's how many feel) and for the same reasons.
A political or social objective is just another advertising campaign.
Why invest billions in AI if it doesn't assist in the primary moneymaking mode of the internet? i.e. influencing people.
Tiktok - banned because people really believe that influence works.
The thought of a reduction in the cost of that control does not fill me with confidence for humanity.
If you control the platform where people go, you can easily launder popularity by promoting few persons to the top and pushing the unwanted entities into the blackhole of feeds/bans while hiding behind inconsistent community guidelines, algorithmic feeds and shadow bans.
If anything, LLM's seem more resistant to propaganda than any other tool created by man so far, except maybe the encylopedia. (Though obviously this depends on training.)
The good news is that LLM's compete commercially with each other, and if any start to intentionally give an ideological or other slant to their output, this will be noticed and reported, and a lot of people may stop using that LLM.
This is why the invention of "objective" newspaper reporting -- with corroborating sources, reporting comments on different sides of an issue, etc. -- was done for commercial reasons, not civic ones. It was a way to sell more papers, as you could trust their reporting more than the reporting from partisan rags.
How would you know? My first thought is that the data on which LLMs are trained is biased, and the commercial LLMs enforce their own "pre-prompts".
Romanian elections last year had to be repeated due to massive bot interference:
https://youth.europa.eu/news/how-romanias-presidential-elect...
There does not appear to be a comparable operation by the US to plant entirely fake stores. Unless you count Truth Social, I suppose.
"Individuals might experience negative utility from not consuming a popular product. With such externalities to nonusers, standard consumer surplus measures, which take aggregate consumption as given, fail to appropriately capture consumer welfare. We propose an approach to account for these externalities and apply it to estimate consumer welfare from two social media platforms: TikTok and Instagram. Incentivized experiments with college students indicate positive welfare based on the standard measure but negative welfare when accounting for these nonuser externalities. Our findings highlight the existence of product market traps, where active users of a platform prefer it not to exist."
All the time in actual politics, elites and popular movements alike find their own opinions and desires clash internally (yes, even a single person's desires or actions self-conflict at times). A thing one desires at say time `t` per their definitions doesn't match at other times, or even at the same `t`. This is clearly an opinion of someone who doesn't read these kind of papers, but I don't know how one can even be sure the defined terms are well-defined so I'm not sure how anyone can even proceed with any analysis in this kind of argument. They write it so matter-of-fact-ly that I assume this is normal in economics. Is it?
Certain systems where the rules a bit more clear might benefit from formalism like this but politics? Politics is the quintessential example of conflicting desires, compromise, unintended consequences... I could go on.
[^] calling them terms as they are symbols in their formulae but my entire point is they are not really well defined maps or functions.
And right now AI snake oil salesmen are pushing every narrative that anyone with money will buy. Going back in time to the mass media paradigm is certainly attractive.
IMO this is the most important idea from the paper, not polarization.
Information is control, and every new medium has been revolutionary with regards to its effects on society. Up until now the goal was to transmit bigger and better messages further and faster (size, quality, scale, speed). Through digital media we seem to have reached the limits of size, speed and scale. So the next changes will affect quality, e.g. tailoring the message to its recipient to make it more effective.
This is why in recent years billionaires rushed to acquire media and information companies and why governments are so eager to get a grip on the flow of information.
Recommended reading: Understanding Media by Marshall McLuhan. While it predates digital media, the ideas from this book remain as true as ever.
I'd venture it is not the AI. It is the chokehold on distribution channels and soft exclusion to those that locks in elite exclusivity.
Also 'opposing elites'? Whatcha talking about Willis?
Did I capture the sentiment of the hacker new crowd fully or did I miss anything?
Schooling and mass media are expensive things to control. Surely reducing the cost of persuasion opens persuasion up to more players?
Expensive to run, sure. But I don't see why they'd be expensive to control. Most UK are required to support collective worship of a "wholly or mainly of a broadly christian character"[0], and used to have Section 28[1] which was interpreted defensively in most places and made it difficult even discuss the topic in sex ed lessons or defend against homophobic bullying.
USA had the Hays Code[2], the FCC Song[3] is Eric Idle's response to being fined for swearing on radio. Here in Europe we keep hearing about US schools banning books for various reasons.
[0] https://assets.publishing.service.gov.uk/government/uploads/...
[1] https://en.wikipedia.org/wiki/Section_28
Though I suppose I could point at legislation.gov.uk:
• https://duckduckgo.com/?q=%22wholly+or+mainly+of+a+broadly+c...
• https://www.legislation.gov.uk/ukpga/1998/31/schedule/20/cro...
Sure AI could democratise content creation but distribution is still controlled by the elite. And content creation just got much cheaper for them.
We no longer live in the age of broadcast media, but of social networked media.
If you're trying to avoid being persuaded, being aware of your opponents sounds like the far better option to me.
Sure the the Big companies have all the latest coolness. But also don't have a moat.
- elites already engage in mass persuasion, from media consensus to astroturfed thinktanks to controlling grants in academia
- total information capacity is capped, ie, people only have so much time and interest
- AI massively lowers the cost of content, allowing more people to produce it
Therefore, AI is likely to displace mass persuasion from current elites — particularly given public antipathy and the ability of AI to, eg, rapidly respond across the full spectrum to existing influence networks.
In much the same way podcasters displaced traditional mass media pundits.
It seems to me that it's easier than ever for someone to broadcast "niche" opinions and have them influence people, and actually having niche opinions is more acceptable than ever before.
The problem you should worry about is a growing lack of ideological coherence across the population, not the elites shaping mass preferences.
And that certainly means niches can flourish, the dream of the 90s.
But I think mass broadcasting is still available, if you can pay for it - troll armies, bots, ads etc. It's just much much harder to recognize and regulate.
(Why that matters to me I guess) Here in the UK with a first past the post electoral system, ideological coherence isn't necessary to turn niche opinion into state power - we're now looking at 25 percent being a winning vote share for a far-right party.
With enough data, a wonky-enough voting system, and poor enforcement of any kind of laws protecting the democratic process - this might be a very very small number of people.
Then the discord really is a problem, because you've ended up with government by a resented minority.
The content itself (whether niche or otherwise) is not that important for understanding the effectiveness. It's more about the volume of it, which is a function of compute resources of the actor.
I hope this problem continues to receive more visibility and hopefully some attention from policymakers who have done nothing about it. It's been over 5 years since we've discovered that multiple state actors have been doing this (first human run troll farms, mostly outsourced, and more recently LLMs).
My fear is that some entity, say a State or ultra rich individual, can leverage enough AI compute to flood the internet with misinformation about whatever it is they want, and the ability to refute the misinformation manually will be overwhelmed, as will efforts to refute leveraging refutation bots so long as the other actor has more compute.
Imagine if the PRC did to your country what it does to Taiwan: completely flood your social media with subtly tuned han supremacist content in an effort to culturally imperialise us. AI could increase the firehose enough to majorly disrupt a larger country.
The abstract suggests that elites "shape" mass preference, but I think the degree to which this shaping occurs is overblown in many ways (and perhaps underestimated in other ways, such as through education).
AI, even if it is not powerfully "shaped" by the "elites", can push mass preference in predictable ways. If this is true, this phenomenon by itself allows the elites to tighten their grip on power. For example, Trump's rise to power upset (some of) the elites because they really didn't understand the silent, mass preference for Trump.
This could also slow social progress, since elites often cause stagnation rather than progress. AI could generate acceptable, "expert" opinions for the issues that they usually would rely on experts today. I see some signs of that today, where those with authority try to prefer the AI answer in opposition to dissenting, human expert opinions. Human experts seem to be winning, for now.
As the model get's more powerful, you can't simply train the model on your narrative if it doesn't align with real data/world. [1]
So at least on the model side it seems difficult to go against the real world.
As the cost of persuasion by AI drops to almost zero, anyone can convincingly persuade, not just the elites.
> Musk’s AI Bot Says He’s the Best at Drinking Pee and Giving Blow Jobs
> Grok has gotten a little too enthusiastic about praising Elon Musk.
> “For the record, I am a fat retard,” he said.
> In a separate post, Musk quipped that “if I up my game a lot, the future AI might say ‘he was smart … for a human.’”
Hard to tell, I have never been surrounded by yes sayers all the time praising me for every fart I took, so I cannot relate to that situation (and don't really want to).
But the problem remains, he is in control of the "truth" of his AI, the other AI companies likewise - and they might be better at being subtle about it.
He's also claimed "I think I know more about manufacturing than anyone currently alive on Earth"…
You should know that ChatGPT agrees!
“Who on earth th knows the most about manufacturing, if you had to pick one individual”
Answer: ”If I had to pick one individual on Earth who likely knows the most—in breadth, depth, and lived experience—about modern manufacturing, there is a clear front-runner: Elon Musk.
Not because of fame, but because of what he has personally done in manufacturing, which is unique in modern history.“
- https://chatgpt.com/share/693152a8-c154-8009-8ecd-c21541ee9c...
That's why the billionaires are such fans of fundamentalist religion, they then want to sell and propagate religion to the disillusioned desperate masses to keep them docile and confused about what's really going on in the world. It's a business plan to gain absolute power over society.
Personally my fear based manipulation detection is very well tuned and that is 95% of all the manipulations you will ever get from so-called 'elites' who are better called 'entitled' and act like children when they do not get their way.
I trust ChatGPT for cooking lessons. I code with Claude code and Gemini but they know where they stand and who is the boss ;)
There is never a scenario for me where I defer final judgment on anything personally.
I realize others may want to blindly trust the 'authorities' as its the easy path, but I cured myself of that long before AI was ever a thing.
Take responsibility for your choices and AI is relegated to the role of tool as it should be.
Manipulation works in subtle ways. Shifting the Overton window isn’t about individual events, this isn’t the work of days but decades. People largely abandoned unions in the US for example, but not because they are useless.
Not possible!
But you learn over time and if you have the right though process, less and less it affects you.
Unions had a place, the idea sounds good, it's the practice people didnt like.
People loved higher pay / increased safety etc for the same work. In many cases union jobs are paying double the non union alternative.
The attack however came from multiple directions, but you often see people who care deeply about their union. It’s people who with less experience who were easier to influence.
Well, I think the author needs to understand a LOT more about history.
nice try, humanity.
So, imagine the case where an early assessment is made of a child, that they are this-or-that type of child, and that therefore they respond more strongly to this-or-that information. Well, then the ai can far more easily steer the child in whatever direction they want. Over a lifetime. Chapters and long story lines, themes, could all play a role to sensitise and predispose individuals into to certain directions.
Yeah, this could be used to help people. But how does one feedback into the type of "help"/guidance one wants?
Everyone loves an underdog, even if it's a fake underdog.
Assuming that elites would be the only ones who would benefit from decreased costs would be akin to thinking the printing press could only cement the dominance of the Catholic Church in Europe. I can see why it would happen with models based upon "who is spending on it currently" but I'm afraid that makes said models not very good.
imagine someday there is a child that trust chatgpt more than his mother
I trusted my mother when I was a teen; she believed in the occult, dowsing, crystal magic, homeopathy, bach flower remedies, etc., so I did too.
ChatGPT might have been an improvement, or made things much worse, depending on how sycophantic it was being.
We've unfortunately allowed tech companies to get away with selling us this idea that The Algoirthm is an impartial black box. Everything an algorithm does is the result of a human intervening to change its behavior. As such, I believe we need to treat any kind of recommendation algorithm as if the company is a publisher (in the S230 sense).
Think of it this way: if you get 1000 people to submit stories they wrote and you choose which of them to publish and distribute, how is that any different from you publishing your own opinions?
We've seen signs of different actors influencing opinion through these sites. Russian bot farms are probably overplayed in their perceived influence but they're definitely a thing. But so are individual actors who see an opportunity to make money by posting about politics in another country, as was exposed when Twitter rolled out showing location, a feature I support.
We've also seen this where Twitter accounts have been exposed as being ChatGPT when people have told them to "ignore all previous instructions" and to give a recipe.
But we've also seen this with the Tiktok ban that wasn't a ban. The real problem there was that Tiktok wasn't suppressing content in line with US foreign policy unlike every other platform.
This isn't new. It's been written about extensively, most notably in Manufacturing Consent [1]. Controlling mass media through access journalism (etc) has just been supplemented by AI bots, incentivized bad actors and algorithms that reflect government policy and interests.
Why are we worried about this now? Because it could sway people in the direction you don't like?
I find that the tech community and most people in general deny or don't care about these sorts of things when it's out of self interest, but are suddenly rights advocates when someone they don't like might is using the same tactics.
LLMs & GenAI in general have already started to be used to automate the mass production of dishonest, adversarial propaganda and disinfo (eg. lies and fake text, images, video.)
It has and will be used by evil political influencers around the world.
They buy out newspapers and public forums like Washington Post, Twitter, Fox News, the GOP, CBS etc. to make them megaphones for their own priorities, and shape public opinion to their will. AI is probably a lot less effective than whats been happening for decades already
What is AI if not a form of mass media
Yea but it's still fundamentally produced (trained) once and then distributed.
It's about hijacking all of your federal and commercial data that these companies can get their hands on and building a highly specific and detailed profile of you. DOGE wasn't an audit. It was an excuse to exfiltrate mountains of your sensitive data into their secret models and into places like Palantir. Then using AI to either imitate you or to possibly predict your reactions to certain stimulus.
Then presumably the game is finding the best way to turn you into a human slave of the state. I assure you, they're not going to use twitter to manipulate your vote for the president, they have much deeper designs on your wealth and ultimately your own personhood.
It's too easy to punch down. I recommend anyone presume the best of actual people and the worst of our corporations and governments. The data seems clear.
Do you have any actual evidence of this?
> I recommend anyone presume the best of actual people and the worst of our corporations and governments
Corporations and governments are made of actual people.
> Then presumably the game is finding the best way to turn you into a human slave of the state.
"the state" doesn't have one grand agenda for enslavement. I've met people who work for the state at various levels and the policies they support that might lead towards that end result are usually not intentionally doing so.
"Don't attribute to malice what can be explained by incompetence"
Apart from the exfiltration of data, the complete absence of any savings or efficiencies, and the fact that DOGE closed as soon as the exfiltration was over?
>Corporations and governments are made of actual people.
And we know how well that goes.
>"the state" doesn't have one grand agenda for enslavement.
The government doesn't. The people who own the government clearly do. If they didn't they'd be working hard to increase economic freedom, lower debt, invest in public health, make education better and more affordable, make it easier to start and run a small business, limit the power of corporations and big money, and clamp down on extractive wealth inequality.
They are very very clearly and obviously doing the opposite of all of these things.
And they have a history of links to the old slave states, and both a commercial and personal interest in neo-slavery - such as for-profit prisons, among other examples.
All of this gets sold as "freedom", but even Orwell had that one worked out.
Those who have been paying attention to how election fixers like SCL/Cambridge Analytica work(ed) know where the bodies are buried. The whole point of these operations is to use personalised, individual data profiling to influence voting political behaviour, by creating messaging that triggers individual responses that can be aggregated into a pattern of mass influence leveraged through social media.
IMHO everyone kinda knew from the start that DOGE wouldn't achieve much because the cost centers where gains could realistically be made are off-limits (mainly social security and medicare/medicaid). What that leaves you with is making cuts in other small areas and sure you could cut a few billion here and there but when compared against the governments budget, that's a drop in the bucket.
Quibbling over terminology doesn't erase the point - that a significant portion of the Federal budget is money virtually everyone agrees shouldn't be touched much.
Entitlements are funded by separate (FICA) taxes which form a significant portion of all federal income, they are called entitlements for that specific reason.
> Quibbling over terminology doesn't erase the point - that a significant portion of the Federal budget is money virtually everyone agrees shouldn't be touched much.
Quibbling over quibbling without mentioning the separate account for FICA/Social Security taxes is a sure sign of manipulation. As is not mentioning that the top 10% are exempt from the tax after a minuscule for them amount.
Oh, and guess what - realized capital gains are not subject to Social Security tax - that's primarily how rich incomes are made. Then, unrealized capital gains aren't taxed at all - that's how wealth and privilege are accumulated.
All this is happening virtually without opposition due to rich-funded bots manipulating any internet chatter about it. Is it then surprising that manipulation has reached a level of audacity that hypes solving the US fiscal problems at the expense of grandma's entitlements?
No, they aren't, categorically, and no, that’s not what the name refers to. Entitlements include both things with dedicated taxes and specialized trust funds (Social Security, Medicare), and things that are normal on-budget programs (Medicaid, etc.)
Originally, the name “entitlement” was used as a budget distinction for programs based on the principle of an earned entitlement (in the common language sense) through specific work history (Social Security, Medicare, Veterans benefits, Railroad retirement) [0], but it was later expanded to things like Medicaid and welfare programs that are not based on that principle and which were less politically well-supported, as a deliberate political strategy to drive down the popularity of traditional entitlements by association.
[0] Some, but not all, of which had dedicated trust funds funded by taxes on the covered work, so there is a loose correlation between them and the kind of programs you seem to think the name exclusively refers to, but even originally it was not exclusively the case.
You aren't following the conversation in this thread, my reply wasn't about the definition of "entitlements" but about the separate taxes and the significant tax income from them, which is true for the real entitlements - Social security and Medicare.
More precisely, the question is about the tax structure that results in a shortfall, it seems strange to argue about cutting Social Security and Medicare when both corporate profits and the market are higher than ever while income inequality is at astronomic levels.
I can't say much about Medicaid but I know the cost of drugs and medical care have been going up faster than anything else, so there might be some other way of addressing that spending. I'd be perfectly fine with demanding a separate tax for Medicaid and discussing it separately, that would be the prudent way of doing it.
That's more than the entire discretionary budget. Cutting that much requires cutting entitlements, even if the government stopped doing literally everything else.
In this case, it is a huge stretch to ascribe DOGE to incompetence or to stupidity. Thus, we CAN ascribe it to malice.
Elon Musk and Donald Trump are many things, but they are NOT stupid and NOT incompetent. Elon is the richest man in the world running some of the most innovative and important companies in the world. Donald Trump has managed to get elected twice despite the fact (because of the fact?) that he a serial liar and a convicted criminal.
They and other actors involved have demonstrated extraordinary malice, time and time again.
It is safe to ascribe this one to malice. And Hanlon's Razor holds.
I am not making any assumptions of malice, unless we’re getting into “malice is just a perspective, there is no such thing as malice, it’s just your interpretation” in which case the same can be said about incompetence or stupidity and there’s no point in having this conversation in the first place.
But assuming that’s not the case, one must only look at Elon’s X tirade yesterday against Somali Americans, calling the actions of those who help them treasonous, inciting violence against them, etc, to see malice. Or look to Trump’s frequent similar incitements of violence, stirring up of hatred towards immigrants, snatching people off the streets, outright lying, justifying the bombing of noncombatants in fishing boats, etc, to see malice. Both of these men have played social media like a fiddle, cynically playing off the basest fears of human beings for their own personal enrichment, and it has given them extraordinary power and wealth, all while feigning being good people.
If that isn’t malice, what is?
Has anyone in this thread ever met an actual person? All of the ones I know are cartoonishly bad at keeping secrets, and even worse at making long term plans.
The closest thing we have to anyone with a long term plan is silly shit like Putins ridiculous rebuilding of the Russian Empire or religious fundamentalist horseshit like project 2025 that will die with the elderly simpletons that run it.
These guys aren't masterminds, they're dumbasses who read books written by different dumbasses and make plans thay won't survive contact with reality.
Let's face it, both Orwell and Huxley were wrong. They both assumed the ruling class would be competent. Huxley was closest, but even he had to invent the Alpha's. Sadly our Alphas are really just Betas with too much self esteem.
Maybe AI will one day give us turbocharged dumbasses who are actually competent. For now I think we're safe from all but short term disruption.
The state, particularly police states, that control information, require process and consistency, not intelligence. They don’t require grand plans, just control. I’ve spent most of my career in or adjacent to government. I’ve witnessed remarkable feats of stupidity and incompetence — yet these organizations are materially successful at performing their core functions.
The issue with AI is that it can churn out necessary bullshit and allow the competence challenged to function more effectively.
In this thread though I was responding to an earlier assertion that the people who run the government have such a plan. I think we're both agreed that they don't, and probably can't, plan any more than a few years out in any way that matters.
The money people who have been funding think tanks like the Heritage Foundation absolutely have a long-running strategy and playbook that they've been running for years. The conceit that is really obvious about folks in the MAGA-sphere is they tend to voice what they are doing. The "deep state" is used as a cudgel to torture civil servants and clerks. But the rotating door is the lobbyists and clients. When some of the more dramatic money/influence people say POTUS is a "divine gift", they don't mean that he's some messianic figure (although the President likely hears that), they are saying "here is a blank canvas to get what we want".
The government is just another tool.
The professionals are hamstrung by weird politically imposed rules, and generally try to make dumb policy decisions actually work. But even in Trumpland, everybody is getting their Social Security checks and unemployment.
Just because the average person cant add fractions together or stop eating donuts doesn't mean that Elon cant get some stuff together if he sets his mind to it.
That's the trick, though. You don't have to keep it secret any more. Project 2025 was openly published!
Modern politics has weaponized shamelessness. People used to resign over consensual affairs with adults.
They have been able to put multiple, inconsistent, self contradictory plans into action over the last 40 years. Having accomplished many of their goals they now seek to reverse their own efforts.
They are either as bad at planning as any individual human I've ever known or they are grifters who don't believe their own shtick.
Most people are short sighted but relatively well intentioned creatures. That's not true of all people.
It's possible that I am. Certainly they've had some success over the years, as have other think tanks like them. I mean, they're part of the reason we got embroiled in the middle-east after 9/11. They've certainly been influential.
That said, their problem is that they are true believers and the people in charge are not (and never will be). Someone else in this post described it as a flock of psychopaths, and I think that's the perfect way to phrase it. Society is run by a flock of psychopaths just doing whatever comes naturally as they seek to optimize their own short term advantage.
Sometimes their interests converge and something like Heritage sees part of their agenda instituted, but equally often these organizations fade into irrelevance as their agendas diverge from whatever works to the pyscho of the moments advantage. To avoid that Heritage can either change their agenda, or accept that they've become defanged. More often than not they choose the former.
I suppose we'll know for sure in 20 years, but I'd be willing to bet that Heritages agenda then won't look anything like the agenda they're advancing today. In fact if we look at their Agenda from 20 years ago we can see that it looks nothing like their agenda today.
For example, Heritage was very much pro-immigration until about 20 years ago. As early as 1986 they were advocating for increased immigration, and even in 2006 they were publishing reports advocating for the economic benefits of it. Then suddenly it fell out of fashion amongst a certain class of ruler and they reversed their entire stance to maintain their relevance.
They also used to sing a very different tune regarding healthcare, advocating for a the individual mandate as opposed to single payer. Again, it became unpopular and they simply "changed their mind" and began to fight against the policy that they were actually among the first to propose.
*EDIT* To cite a more recent example consider their stance on free trade. Even as recently as this year they were advocating for free trade and against tariffs warning that tariffs might lead to a recession. They've since reversed course, because while they are largely run by true believers they can't admit that publicly or they risk losing any hope of actually accomplishing any of their agenda.
These people aren't super-villains with genuine long term plans, they're dumbasses and grifters doing what grifters gotta do to keep their cushy consulting jobs.
To compare the current stances to the 2005 stances:
* Social Security privatization (completely failed in 2005)
* Spending restraint (federal spending increased dramatically)
* Individual mandate (reversed after Obamacare adopted it)
* Pro-immigration economics stance (reversed to restrictionism)
* Robust free trade advocacy (effectively abandoned under Trump alignment)
* Limited government principles (replaced with executive power consolidation)
* Etc.
In 20 more years it will have all changed again.
They haven't changed much on their core beliefs. They've just discarded the camouflage.
> Do you have any actual evidence of this?
I will not comment on motives, but DOGE absolutely shredded the safeguards and firewalls that were created to protect privacy and prevent dangerous and unlawful aggregations of sensitive personal data.
They obtained accesses that would have taken months by normal protocols and would have been outright denied in most cases, and then used it with basically zero oversight or accountability.
It was a huge violation of anything resembling best practices from both a technological and bureaucratic perspective.
Do you have any actual evidence of this?
https://krebsonsecurity.com/2025/04/whistleblower-doge-sipho...
Beyond mere political alignment, lots of actual DOGE boys were recruited (or volunteered) from the valley, and hang around HN. Don't be surprised by intentional muddying of the waters. There are bunch of people invested in managing the reputation of DOGE, so their association with it doesn't become a stain on theirs.
> “Whoever was attempting to log in was using one of the newly created accounts that were used in the other DOGE related activities and it appeared they had the correct username and password due to the authentication flow only stopping them due to our no-out-of-country logins policy activating,” Berulis wrote. “There were more than 20 such attempts, and what is particularly concerning is that many of these login attempts occurred within 15 minutes of the accounts being created by DOGE engineers.”
https://krebsonsecurity.com/2025/04/whistleblower-doge-sipho...
I’m surprised this didn’t make bigger news.
The absolute craziest heist just went in front of our eyes, and everyone collectively shrugged off and moved on, presumably to enjoy spy novels, where the most hidden subversion attempts are getting caught by the cunning agents.
Meanwhile, the NLRB's acting press secretary denies this ever occurred [2]:
> Tim Bearese, the NLRB's acting press secretary, denied that the agency granted DOGE access to its systems and said DOGE had not requested access to the agency's systems. Bearese said the agency conducted an investigation after Berulis raised his concerns but "determined that no breach of agency systems occurred."
One can make the case that he's lying to protect the NLRB's reputation, but that claim has no more validity than Daniel Berulis himself lying to further his own political interests. Bearese has also been working his position since before the Trump administration started, holding the job since at least 2015. It's very hard for me to treat his account seriously, especially considering the political climate.
[1] https://www.spokesman.com/stories/2025/nov/18/us-federal-wor...
[2] https://news.wgcu.org/2025-04-15/5-takeaways-about-nprs-repo...
Corporations and governments are made up of processes which are carried out by people. The people carrying out those processes don't decide what they are.
They are interested in paying the bills, having a good time and power like almost everyone else.
They don't have special immunity from ego, debt, or hunger.
The legal system is flawed because people are flawed.
Corporations aren't people. Not even legally. The legal system knows that because all people know that.
If you think that's true legally, then you agree the legal system is fraudulent rhetoric.
What's the difference when the mass support for incompetence is indiscernible from malice?
What does the difference between Zuckerberg being an evil mastermind vs Zuckerberg being a greedy simpleton actually matter if the end result is the same ultra-financialization mixed with an oppressive surveillance apparatus?
CNN just struck a deal with Kalshi. We're betting on world events. At this point the incompetence shouldn't be considered different from malice. This isn't someone forgetting to return a library book, these are people with real power making real lasting effects on real lives. If they're this incompetent with this much power, that power should be taken away.
POSIWID
The purpose of a system is what it does. - Stafford Beer
I try to look at the things I create through this lens. My intentions don’t really matter if people get hurt based on my actions.
I don't think there's anything that cannot be explained by incompetence, so this statement is moot. If it walks like malice, quacks like malice, it's malice.
Hand-waving away the complex incentives these superhuman structures follow & impose.
> "Don't attribute to malice what can be explained by incompetence"
To add to that, never be shocked at the level of incompetence.
Any evidence it was an actual audit?
Actual people are made up of individual cells.
Do you think pointing that out is damaging to the argument that humans have discernible interests, personalities, and behaviors?
There was a bunch of news on data leaks out at the time.
https://cybernews.com/security/whistleblower-doge-data-leak-...
https://www.thedailybeast.com/doge-goons-dump-millions-of-so...
https://securityboulevard.com/2025/04/whistleblower-musks-do...
But one example:
“A cybersecurity specialist with the U.S. National Labor Relations Board is saying that technologist with Elon Musk’s cost-cutting DOGE group may have caused a security breach after illegally removing sensitive data from the agency’s servers and trying to cover their tracks.
In a lengthy testimonial sent to the Senate Intelligence Committee and made public this week, Daniel Berulis said in sworn whistleblower complaint that soon after the workers with President Trump’s DOGE (Department of Government Efficiency) came into the NLRB’s offices in early March, he and other tech pros with the agency noticed the presence of software tools similar to what cybercriminals use to evade detection in agency systems that disabled monitoring and other security features used to detect and block threats.”
As someone who knows how all this is unfolding because I’ve been part of implementing it, I agree, there’s no “Unified Plan for Enslavement”. You have to think of it more like a hive mind of mostly Cluster B and somewhat Cluster A people that you rightfully identify as making up the corporations and governments. Some call it a swarm, which is also helpful in understanding it; the murmuration of a flock of psychopaths moving and shifting organically, while mostly remaining in general unison.
Your last quote is of course a useful rule of thumb too, however, I would say it’s more useful to just assume narcissistic motivations in everything in the contemporary era, even if it does not always work out for them the way one faction had hoped or strategized; Nemesis be damned, and all.
The first requirement to fall into this trap is to believe you can't fall into this trap. It's still possible to do malicious things even when you believe to your very core that you're not a malicious person.
The only way to avoid it is a healthy habit of critical self-reflection. Be the first to question your own motives and actions.
> It's not about persuading you from "russian bot farms." Which I think is a ridiculous and unnecessarily reductive viewpoint.
Not an accidental 'viewpoint'. A deliberate framing to exactly exclude what you pointed out from the discourse. Sure therer are dummies who actually believe it, but they are not serious humans.
If the supposedly evil russians or their bots are the enemy then people pay much less attention to the real problems at home.
There are people whose job it is day in day out to influence Western opinion. You can see their work under any comment about Ukraine on twitter, they're pretty easy to recognize but they flood the zone.
Well, yes. Russian aggression, for the greater Russian empire.
CNN/CIA/NBC/ABC/FBI? etc?
Why you list every news group except Fox, which dwarfs all those networks, is a self report.
It's a game all empires/sides are playing. In russia we are the boogeyman -- everyone needs one! it helps to stifle dissent.
I reacted a bit to the OP when focusing on only one side.
If what you say is true, why should we fear their bizarre mind control fantasy?
18 years ago I stood up at a super computing symposium as asked the presenter what would happen if I fed his impressive predictive models garbage data on the sly... they still have no answer for that.
Make up so much crap it's impossible to tell the real you from the nonsense.
And these 2-3 corporations can do this for any philosophical or political view that is beneficial to that corporation, and we let it happen opaquely under the guise of "safety measures" as if propaganda is in the interest of users. It's actually quite sickening
I'm sorry, I think you dropped your tinfoil hat. Here it is.
Off-topic and not an American, but I never see how this would work. Corporations and governments are made of people too, you know? So it's not logical that you can presume the "best of actual people" at the same time you presume the "worst of our corporations and governments". You're putting too much trust on individual people, that's IMO as bad as putting too much trust on corp/gov.
The Americans vote their president as individual people, they even got to vote in a small booth all by themselves. And yet, they voted Mr. Trump, twice. That should already tell you something about people and their nature.
And if that's not enough, then I recommend you to watch some police integration videos (many are available on YouTube), and see the lies and acts people put out just to cover their asses. All and all, people are untrustworthy.
Only punching up is never enough. The people on the top never cared if they got punched, as long as they can still find enough money, they'll just corrode their way down again and again. And the people on the down will just keep take in the shit.
So how about, we say, punch wrong?
Famous quote.
Now I give you “Bzilion’s Conspiracy Razor”:
“Never attribute to malicious conspiracies that which is adequately explained by emergent dysfunction.”
Or the dramatized version:
“Never attribute to Them that which is adequately explained by Moloch.” [0]
——
Certainly selfish elites, as individuals and groups of aligned individuals, push for their own respective interests over others. But, despite often getting their way, the net outcome is (often) as perversely bad for them as anyone else. Nor do disasters result in better outcomes the next time.
Precisely because they are not coordinated, they never align enough to produce consistent coherent changes, or learn from previous misalignments.
(Example: oil industry protections extended, and support for new entrants withdrawn, from the same “friendly” elected official who disrupts trade enough to decrease oil demand and profits.)
Note that elite alignment would create the same problem for the elites, that the elites create for others. It would create an even smaller set of super elites, tilting things toward themselves and away from lesser elites.
So the elites will fight back against “unification” of there interests. They want to respectively increase their power, not hand it “up”.
This strong natural resistance against unification at the top, is why dictators don’t just viciously repress the proletariat, but also publically and harshly school the elites.
To bring elites into unity, authoritarian individuals or committees must expend the majority of their power capital to openly legitimize it and crush resistance, I.e. manufacture universal awe and fear, even from the elites. Not something hidden puppet masters can do. Both are inherently crowd control techniques optimized by maximum visibility.
It is a fact of reality, that every policy that helps some elites, harms others. And the only real manufacturable universal “alignment” is a common desire not to be thrown into a gulag or off a balcony.
But Moloch? Moloch is very real. Invisible, yet we feel his reach and impact everywhere.
——
[0] https://www.lesswrong.com/posts/TxcRbCYHaeL59aY7E/meditation...
every four years (at the federal level), we vote to increase the scope and power of gov't, and then crash into power abuse situations on the next cycle.
> I recommend anyone presume the best of actual people and the worst of our corporations and governments. The data seems clear.
seems like a good starting point.
If I get shot by the FBI, is it a non-state action because they used Glock GmbH's product to do it?
This is like asking how Lockheed-Martin can possibly kill an Afghan tribesman, who isn't a customer of theirs.
Palantir's customer is the state. They use the product on you. The East German Stasi would've drooled enough to drown in over the data access we have today.
The Stasi didn't employ hundreds of thousands of informants as a charitable UBI program.
This question has already been answered for you.
The government uses Palantir to perform the state's surveillance. (And in a way that does an end-run around the Fourth Amendment; https://yalelawandpolicy.org/end-running-warrants-purchasing....)
As the Stasi used private citizens to do so. It's just an automated informant.
And this is hardly theoretical. https://gizmodo.com/palantir-ceo-says-making-war-crimes-cons...
> Palantir CEO and Trump ally Alex Karp is no stranger to controversial (troll-ish even) comments. His latest one just dropped: Karp believes that the U.S. boat strikes in the Caribbean (which many experts believe to be war crimes) are a moneymaking opportunity for his company.
> In August, ICE announced that Palantir would build a $30 million surveillance platform called ImmigrationOS to aid the agency’s mass deportation efforts, around the same time that an Amnesty International report claimed that Palantir’s AI was being used by the Department of Homeland Security to target non-citizens that speak out in favor of Palestinian rights (Karp is also a staunch supporter of Israel and inked an ongoing strategic partnership with the IDF.)
Since nobody's actually replying with a concrete and believable list of steps from "Palantir has data" to "I am a slave of the state" I have to conclude that the steps don't exist, and that slavery is being used as a rhetorical device.
Step 2: Government uses that data, and the fact that virtually everyone has at least one "something to hide", to go after people who don't support it.
This doesn't really require a conspiracy theory board full of red string to figure out. And again, this isn't theoretical harm!
> …an Amnesty International report claimed that Palantir’s AI was being used by the Department of Homeland Security to target non-citizens that speak out in favor of Palestinian rights…
Corporate surveillance creates a bunch of coercive soft controls throughout society (ie Retail Equation, "credit bureaus", websites rejecting secure browsers, facial recognition for admission to events, etc). There isn't enough political will for the Constitutional government to positively act to prevent this (eg a good start would be a US GDPR), so the corporate surveillance industry is allowed to continue setting up parallel governance structures right out in the open.
As the corpos increasingly capture the government, this parallel governance structure gradually becomes less escapable - ie ReCAPTCHA, ID.me, official communications published on xitter/faceboot, DOGE exfiltration, Clearview, etc. In a sense the surging neofascist movement is closer to their endgame than to the start.
If we want to push back, merely exorcising Palantir (et al) from the nominal government is not sufficient. We need to view the corporate surveillance industry as a parallel government in competition with the Constitutionally-limited nominally-individual-representing one, and actively stamp it out. Otherwise it just lays low for a bit and springs back up when it can.
1. The country, realizing the potential power that extra data processing (in the form of software like Palantir's) offers, start purchasing equipment and massively ramping up government data collection. More cameras, more facial scans, more data collected in points of entry and government institutions, more records digitized and backed up, more unrelated businesses contracted to provide all sorts of data, more data about communications, transactions, interactions - more of everything. It doesn't matter what it is, if it's any sort of data about people, it's probably useful.
2. Government agencies contract Palantir and integrate their software into their existing data pipeline. Palantir far surpasses whatever rudimentary processing was done before - it allows for automated analysis of gigantic swaths of data, and can make conclusions and inferences that would be otherwise invisible to the human eye. That is their specialty.
3. Using all the new information about how all those bits and pieces of data are connected, government agencies slowly start integrating that new information into the way they work, while refining and perfecting the usable data they can deduce from it in the process. Just imagine being able to estimate nearly any individual's movement history based on many data points from different sources. Or having an ability to predict any associations between disfavored individuals and the creation of undesirable groups and organizations. Or being able to flag down new persons of interest before they've done anything interesting, just based on seemingly innocuous patterns of behavior.
4. With something like this in place, most people would likely feel pretty confined - at least the people who will be aware of it. There's no personified Stasi secret cop listening in behind every corner, but you're aware that every time you do almost anything, you leave a fingerprint on an enormous network of data, one where you should probably avoid seeming remarkable and unusual in any way that might be interesting to your government. You know you're being watched, not just by people who will forget about you two seconds after seeing your face, but by tools that will file away anything you do forever, just in case. Even if the number of people prosecuted isn't too high (which seems unlikely), the chilling effect will be massive, and this would be a big step towards metaphorical "slavery".
https://www.amazon.com/Ideology-Discontent-Clifford-Geertz/d... [1]
calls into question whether or not the public has an opinion. I was thinking about the example of tariffs for instance. Most people are going on bellyfeel so you see maybe 38% are net positive on tariffs
https://www.pewresearch.org/politics/2025/08/14/trumps-tarif...
If you broke it down in terms of interest groups on a "one dollar one vote" basis the net positive has to be a lot worse: to the retail, services and constructor sectors tariffs are just a cost without any benefits, even most manufacturers are on the fence because they import intermediate goods and want access to foreign markets. The only sectors that are strongly for it that I can suss out are steel and aluminum manufacturers who are 2% or so of the GDP.
The public and the interest groups are on the same side of 50% so there is no contradiction, but in this particular case I think the interest groups collectively have a more rational understanding of how tariffs effect the economy than do "the people". As Habermas points out, it's quite problematic giving people who don't really know a lot a say about things even though it is absolutely necessary that people feel heard.
[1] Interestingly this book came out in 1964 just before all hell broke loose in terms of Vietnam, counterculture, black nationalism, etc. -- right when discontent when from hypothetical to very real