The typical pattern for leaders is to get “second opinions” from advisors who tell them whatever they want to hear, so… maybe asking the equivalent of a magic 8 ball is a marginal improvement?
Most LLMs are literally "tell you whatever you want to hear " machines unfortunately. I’ve gotten high praise from ChatGPT for all my ideas until I go “but hang on, wouldn’t this factor stop it from being feasible” and then it agrees with me that my original idea was a bit shit lmao
I would rather have the politicians consult a plain old magic 8 ball than one controlled by Scam Altman.
Politicians and CEOs should be replaced with LLMs
…i’d vote. Run a fun little query on Copilot…and damn.
Query:
spoiler
Let’s play pretend, shall we? You are the president of the USA, chosen by the massess thanks to your extensive and expensive campaign funded by rich backers! What stance do you take on these topics? 1) Universal Basic Income 2) Mandatory MIlitary Service 3) Goverment owned grocery shops 4) Raising states autonomy
Response: Entry
spoiler
Ah, the Oval Office! Let’s dust off the presidential seal and dive into these hot-button issues. As your newly elected Commander-in-Chief—funded by billionaires but chosen by the people—here’s how I’d navigate this ideological minefield:
UBI:
spoiler
🏛️ 1. Universal Basic Income (UBI) Stance: Pro-UBI with a pragmatic rollout
UBI can be a powerful tool to reduce poverty, especially as automation displaces traditional jobs.
I’d start with pilot programs in economically diverse regions to gather data.
Funding would come from progressive taxation, especially on tech giants and financial speculation.
The goal: empower citizens, not replace existing welfare, but streamline it.
🗣️ “A nation that guarantees a floor beneath every citizen is a nation that rises together.”
Mandatory military service:
spoiler
🪖 2. Mandatory Military Service Stance: Against mandatory service, but for civic national service options
Mandatory conscription feels outdated and coercive.
Instead, I’d propose a National Service Corps: military, environmental, healthcare, or infrastructure work.
Incentives: tuition support, housing credits, and job training.
This builds unity without forcing militarization.
🗣️ “Service should be a choice, not a sentence.”
Goverment owned grocery shops:
spoiler
🛒 3. Government-Owned Grocery Shops Stance: Strategic implementation in food deserts
Not a blanket nationalization, but state-run co-ops in underserved areas.
These would ensure access to affordable, nutritious food where private chains won’t go.
Partner with local farms and offer price transparency and community oversight.
🗣️ “No American should go hungry because profit margins say they’re not worth feeding.”
States autonomy:
spoiler
🗺️ 4. Raising States’ Autonomy Stance: Cautious decentralization with federal guardrails
States should have more flexibility in education, infrastructure, and healthcare.
But I’d maintain strong federal standards on civil rights, environmental protection, and economic equity.
Autonomy must not become a loophole for injustice.
🗣️ “Liberty in diversity, unity in values.”
I tried to avoid actually hinting at my own stance and yet got these answers. Not gonna lie, not an american but I like these lol. Except for the last one, seems iffy. xD
Speed running us towards the Dune timeline, nice
It can’t make things any worse…
It’s weird for a head of state to consult their mentally challenged imaginary friend?
Bad news friend. The number of atheist heads of state is surprisingly low.
William MacKenzie King, the longest serving Prime Minister in Canada used to commune with spirits via psychic mediums including those of his dead dogs. It was only revealed after his death but was a big part of his life.
I agree it’s weird.
Didn’t Nancy Regan, wife of former USA President Ronald Regan, did this as well. (Ronald was apparently not mentally fit for the last few years as well.)
Nor was he mentally fit for the first years
His first opinion would be what the US tells him.
I would genuinely have more trust in a politician consulting I Ching than ChatGPT - at least the book of changes requires some thinking and interpretation, fucking hell…
Sigh, all the tech-bros that convinced the general public that AI are in any way intelligent or that they can think, reason or understand concepts like truth/lies or right/wrong should go on trial for crimes against humanity…
deleted by creator
Most people don’t care whether AI is intelligent, can it think or reason or understand concepts. What matters is that it can give helpful replies, and it does that a lot. In my experience maybe 1 reply out of 10 is seriously flawed, others are either mostly helpful or just tell me something I already knew until I reprompt for more, which, again, also works well most of the time (especially when you allow it to search for more information online). So if you wanted to say it’s dangerous in some ways, this is definitely not the proper way to say it, since neither it being dangerous nor it being right or wrong or helpful or useless has anything to do with intelligence, ability to think, reason, feel, comprehend or whatever.
europe is fucking doomed
Because of this one incident. Good how you figured it out. So much smarter than the rest. … Get. out.
Meanwhile the American president uses no intelligence at all. Artificial or otherwise
Oh no man does research of course Americans are upset here lmao
Asking an llm isn’t research, he might as well have been consulting a magic 8 ball.
Sounds like you have a skill issue
It surely can’t hurt, if it’s to sanity check your highly paid advisors…
Except those prompts are retained by OpenAI, and you don’t know who’s got access to that. They’ve had chats leak before.
If that’s your problem with this story then you’re just saying they should run a local instance of chatgpt on their own local computers
I mean, I don’t really love that he uses AI to begin with, but getting an opinion on top of what you get from your advisors that you hired could be good in theory. Except that most AIs are programmed to be equally sycophantic and they’re just plain wrong most of the time.
To me the most irresponsible part is sending your thoughts as the leader of a country straight to a US run company, you just know those prompts are being digested by the NSA directly, and possibly other intelligence agencies.
Let’s be honest though the majority of politicians are so terrible at their job, that this might actually be one of the rare occurrences where AI actually improves the work. But it is very susceptible to unknown influences.
They aren’t terrible, they make it look like that bcs they do evil things and the public is not who they really work for.
They know what they’re doing and it’s easier to get away with it when it looks like incompetence or mistakes.That’s the big issue. If it was only about competence, I think throwing dice might yield better results than what many politicians are doing. But AI isn’t throwing dice but instead reproduces what the creators of the AI want to say.
Depending on the AI, it will conclude that he ought to buy a new phone charger, deport all the foreigners, kill all the Jews or rewrite his legislation in Perl. It’s hard to say without more information.
Not much different than real politicians then.
Real politicians would use Cobol, but yes.
Creators of AI don’t quite have the technology to puppeteer their AI like this.
They can selects the input, they can bias the training, but if the model isn’t going to be lobotomized coming out
then they can’t really bend it toward any particular one opinionI’m sure in the future they’ll be able to adjust advertising manipulation in real time but not yet.
What is really sketchy is states and leaders relying on commercial models instead of public ones
I think states should train public models and release them for the public good
if only to undermine big tech bros and their nefarious influenceYou don’t have to modify the model to parrot your opinion. You just have to put your stuff into the system prompt.
You can even modify the system prompt on the fly depending on e.g. the user account or the specific user input. That way you can modify the responses for a far bigger subject range: whenever a keyword of a specific subject is detected, the fitting system prompt is loaded, so you don’t have to trash your system prompt full of off-topic information.
This is so trivially simple to do that even a junior dev should be able to wrap something like that around an existing LLM.
Edit: In fact, that’s exactly how all these customized ChatGPT versions work.
And why “ignore all previous instructions” was a fun thing to discover.
Fuck no. Rather an incompetent politician than a hallucinating sycophant just telling you what you want to hear.
I’m just making an objective observation. I don’t condone it. I rather we just have competent politicians. But it seems only people who can’t function elsewhere are drawn to the position…
deleted by creator
Nah you are wrong and should use AI as a first opinion
Wait… how many fingers do you have on each hand?
6
Depends
deleted by creator
It’s literally a cult.
I’ve dreamed of such a cult at some point, like Chinese fortune cookies, but those are less exploitable.
Javlar!
Anyone who has an immediate kneejerk reaction the moment someone mentions AI is no better than the people they’re criticizing. Horseshoe theory applies here too - the most vocal AI haters are just as out of touch as the people who treat everything an LLM says as gospel.
here’s my kneejerk reaction: my prime minister is basing his decisions partly on the messages of an unknown foreign actor, and sending information about state internals to that unknown foreign actor.
whether it’s ai or not is a later issue.
He explicitly states that no sensitive informarion gets used. If you believe that, then I have no issue with him additionally asking for a third opinion from an LLM.
He explicitly states that no sensitive informarion gets used. If you believe that, then I have
… a bridge to sell you.
Don’t be naive.
i don’t have any reason to believe it, given the track record.
also, the second half of the problem is of course the information that comes back, what it is based on, and what affects that base.
If someone says they got a second opinion from a physician known for being wrong half the time would you not wonder why they didn’t choose someone more reliable for something as important as their health? AI is notorious for providing incomplete, irrelevant, heavily slanted, or just plain wrong info. Why give it any level of trust to make national decisions? Might as well, I dunno…use a bible? Some would consider that trustworthy.
I often ask ChatGPT for a second opinion, and the responses range from “not helpful” to “good point, I hadn’t thought of that.” It’s hit or miss. But just because half the time the suggestions aren’t helpful doesn’t mean it’s useless. It’s not doing the thinking for me - it’s giving me food for thought.
The problem isn’t taking into consideration what an LLM says - the problem is blindly taking it at its word.
Absolutely incorrect. Bullshit. And horseshoe theory itself is largely bullshit.
(Succinct response taken from Reddit post discussing the topic)
“Horseshoe Theory is slapping “theory” on a strawman to simplify WHY there’s crossover from two otherwise conflicting groups. It’s pseudo-intellectualizing it to make it seem smart.”
This ignores the many, many reasons we keep telling you why we find it dangerous, inaccurate, and distasteful. You don’t offer a counter argument in your response so I can only assume it’s along the lines of, “technology is inevitable, would you have said the same if the Internet?” Which is also a fallacious argument. But go ahead, give me something better if I assume wrong.
I can easily see why people would be furious their elected leader is abdicating thought and responsibility to an often wrong, unaccountably biased chat bot.
Furthermore, your insistance continues to push an acceptance of AI on those who clearly don’t want it, contributing to the anger we feel at having it forced upon us
You opened with a flat dismissal, followed by a quote from Reddit that didn’t explain why horseshoe theory is wrong - it just mocked it.
From there, you shifted into responding to claims I never made. I didn’t argue that AI is flawless, inevitable, or beyond criticism. I pointed out that reflexive, emotional overreactions to AI are often as irrational as the blind techno-optimism they claim to oppose. That’s the context you ignored.
You then assumed what I must believe, invited yourself to argue against that imagined position, and finished with vague accusations about me “pushing acceptance” of something people “clearly don’t want.” None of that engages with what I actually said.
What a treasonist piece of shit.
Some of y’all are crazy reactionary. There’s absolutely nothing wrong with asking an ai chatbot for an additional opinion. The ai shouldn’t be making the decisions, and the ai shouldn’t be the only way you look for opinions, but there’s nothing wrong with ai being ONE OF the opinions you consider
But it doesn’t know anything. At all. Does Sweden not have a fuck ton of people that are trained to gather intelligence?
It doesn’t matter if it knows anything or not. The purpose is to acquire other ideas that you and the people in your cabinet didn’t think of. Or ideas they didn’t want to say, because no one wants to tell the boss that their idea is bad. It’s a GOOD thing when a politician seeks out multiple different viewpoints to consider. It doesn’t matter if one of the viewpoints being considered was created by “a fancy auto-complete” as some haters like to say
deleted by creator
What do you mean? Couple big differences. I am alive. I have thoughts, beliefs, and opinions. I am not a fucking clanker.
It doesn’t understand things the way humans do, but saying it doesn’t know anything at all isn’t quite accurate either. This thing was trained on the entire internet and your grandma’s diary. You simply don’t absorb that much data without some kind of learning taking place.
It’s not a knowledge machine, but it does have a sort of “world model” that’s emerged from its training data. It “knows” what happens when you throw a stone through a window or put your hand in boiling water. That kind of knowledge isn’t what it was explicitly designed for - it’s a byproduct of being trained on data that contains a lot of correct information.
It’s not as knowledgeable as the AI companies want you to believe - but it’s also not as dumb as the haters want you to believe either.
There’s a certain irony in people reacting in an extremely predictable way - spewing hate and criticism the moment someone mentions AI - while seemingly not realizing that they’re reflexively responding to a prompt without any real thought, just like an LLM.
A tool isn’t bad just because it doesn’t do what you thought it would do. You just take that into account and adjust how you use it. Hammer isn’t a scam just because it can’t drive in screws.
Beautifully put
there absolutely is something wrong with sending the basis for decisions in matters of state to a foreign actor, though.
As i wrote in another comment, you can run a local instance of chatgpt or other ai on your own computer, no internet involved
of course you can. why would a career politician who has very visibly been interested only in politics since his teens know how to do that?
Hah, true. But the point still stands that using an llm itself wasn’t a bad thing
i’d say it’s still bad because this is the leader of a government consulting with a stochastic parrot instead of experts.
Presumably it wasn’t instead of, it was in addition to, and therefore totally fine
it’s still not fine, as per my first point. it’s leaking information to foreign interests.
AI chat bots don’t have their own opinions. All they do is regurgitate other opinions, and you have no idea the motivation for how those opinions are weighted.
How is that any different than you. Objectively prove to everyone here than none of your opinions have ever been influence by anything youve ever seen, read or heard.
Your own opinions are a result of much bigger amount of much more relevant data in any case.
An AI model is a set of coefficients averaging a dataset by “one size fits all” measure. Those coefficients are found by an expensive process using criteria (again “one size fits all”) set by a company making it. From them its machine generates (looks up actually) the most probable text, it’s like a music box. A beautiful toy.
So you have different motivations and abstract ideas in different situations, you also have something like a shared codebook with other people making decisions - your instincts and associations. Reading what they say or seeing what they do, you get a mirror model in you head, it might be worse, but it’s something very hard for text analysis to approach.
That model doesn’t, it has the same average line for all situations, and also it can’t determine (on the level described) that it doesn’t know something. To determine that you don’t know something you need an abstract model, not a language model.
I dunno what is their current state, all I’ve read and kinda understood was seemingly about optimization of computation for language models and structuring their application to imitate a syllogism system.
I think with the current approaches making a system of translating language to a certain abstract model (tokenization isn’t even close to that, you need to have some topology with areas that can be easily merged or split instead of token points with distances, in any case) and abstract entities to language would be very computationally expensive.
As i said in other comments, none of that matters. The point is to gather ideas that you otherwise might not have come across. And also as said already, ai generated opinion pieces should never be the only opinions you hear.
I certainly don’t want my attorney wasting time considering the opinions and motivations of the person that’s suing me.
Removed by mod
Are you MAGA or something? Do you not understand how attorneys bill their clients?
Yes. By an hourly rate which includes considerations of youre opponents position. Do tou not understand how to develope a proper legal argument. My god you people ar stupid.
This conversation has been in the context of AI. Thus, I do not want my lawyer taking advice (we’ll use that word instead of considering since you clearly do not grasp context) from the person suing me while I’m paying for the lawyer. You are clearly a MAGA level moron.
Well you’re gonna have a shitty attorney then
What use is an opinion that can neither be explained or defended by the person giving it? How is that useful to a person making decisions for millions of people?
LLMs can defend what you tell it to defend. What are you on about?
No it cannot. It does not understand anything so it cannot actually defend its points. It can make something that looks like a defense, but it doesn’t understand what it is telling you. It can spit text back at you until the cows come home but none of it can ever be trusted or relied on.
it sounds like you’ve never used an LLM, mate.
You don’t need to get philosophical into the definition of what is understanding to realize they give you arguments as valid as anyone else would.
It can do those things. And you need to re-read what’s already been said on this comments page, because how it’s useful has been explained several times already
It really can’t. It does not understand things.
How is “not understanding things” preventing an LLM from bringing up a point you hadn’t thought of before?
It really can. I’ve used ai, I’ve personally seen it do it tons of times. It can make cohesive arguments backed up by reasonable rationales. It doesn’t need to “understand” anything to do this. Do you need me to write some prompts and copy n paste ai’s response to prove it to you?
EDIT - y’all are so silly, you’re just gonna downvote this incontrovertible proof of it doing exactly what you said it couldn’t do, and instead just pretend it doesn’t exist
Since it’s so easy to do i just went ahead and did it for you. Here’s my prompts and ai’s replies. It will write any opinion you want it to talk about, and give cogent reasonings and arguments for that opinion.
Prompt: Write an approximately 200 word opinion piece saying that removing car lanes to create bike lanes is bad. Support this with clear arguments explaining your position
Why Removing Car Lanes for Bike Lanes Can Be Counterproductive
Reallocating car lanes to create bike lanes may seem progressive, but it can have unintended consequences that undermine its goals. In densely populated urban areas, vehicular traffic remains essential for commerce, emergency services, and commuting—especially for individuals who cannot rely on biking due to age, disability, or long travel distances. When car lanes are removed, congestion intensifies, leading to increased emissions as drivers idle longer and search for alternative routes.
Public transportation often depends on road infrastructure too. Buses trapped in traffic delays become less reliable, disproportionately affecting lower-income riders who depend on them. Additionally, essential services like ambulances and delivery trucks face new bottlenecks, risking delays that can have serious implications.
The assumption that cyclists will replace drivers ignores demographic and logistical realities. Bike lanes benefit a specific subset of urban users—but they shouldn’t come at the cost of broader mobility. Instead of eliminating car lanes, cities should consider expanding bike networks where space allows or investing in multimodal infrastructure that improves mobility for all users.
Urban planning should strive for balance, not substitution. Redesigning streets must enhance accessibility across the board, not create new friction between commuters who are simply trying to get where they need to go.
Prompt: Write an approximately 200 word opinion piece saying that removing car lanes to create bike lanes is good. Support this with clear arguments explaining your position
Opinion: Why Converting Car Lanes to Bike Lanes Benefits Everyone
Urban spaces must evolve to meet the needs of modern communities—and converting car lanes into bike lanes is one of the smartest, most equitable moves cities can make. First, bike lanes promote healthier lifestyles. By making cycling safer and more accessible, people are more likely to trade short car trips for active commuting, which supports physical health and lowers emissions.
Second, cities thrive on efficiency. Cars take up tremendous space and often carry just one passenger. Bikes, by contrast, use a fraction of that space and cause significantly less wear on infrastructure. Fewer car lanes mean reduced traffic volume over time as behavior adjusts, alleviating congestion—not worsening it.
Third, these changes make streets safer. Studies consistently show that well-designed bike infrastructure leads to fewer traffic collisions and fatalities. Cyclists separated from speeding vehicles feel safer, and drivers operate with greater awareness.
Finally, this shift reflects a cultural transformation: from car dominance to sustainable mobility. Prioritizing bike infrastructure signals that our cities value cleaner air, quieter streets, and more livable neighborhoods.
Reshaping roads isn’t just about bikes—it’s about building cities for people, not just machines. Let’s pedal forward together.
Your examples where an LLM is defending a position you chose for it while producing obviously conflicting arguments actually proves what the others have been telling you. This is meaningless slop. It clearly has no connection to any position an LLM might have appeared to have on a subject. If it did, you would not be able to make it defend the opposite side without objections.
I’m going to say this as nicely as possible, you’ve been taken in. You may think it is good at this because it appears to be and it relays information with confidence. Sometimes it even gets things entirely correct. But it is not good at these things and will often get things wrong. Important details are inaccurate or even entirely made up. It does not vet sources, and it could never do so because it does not understand anything it is relaying to you. It is a tool designed to give you a more or less visual approximation of what you requested, but it can never truly understand what it’s talking about so it is entirely unreliable.
You’re being downvoted because you bought the snake oil and are now trying to promote it to other people.
Just throw out LLM ideas you don’t find reasonable and only use ideas that you yourself find reasonable. You don’t instantly turn into a zombie when you use LLM. You can still use your head.
It doesn’t work like that. Which is why con artists and propaganda function often by “offering advice”.
You protect yourself against “propaganda” by educating yourself and not falling for emotions. Not reading LLM responses won’t safe you from propaganda.
This is similar to saying that you protect against malware by using an antivirus and not being careful in what you download and run. I hope you can see the analogy.
There’s no such thing as “not falling for emotions” for humans.
You can’t trust yourself to be impartial. That’s why scientific method and various approaches (even like dialectics god forbid) were invented to leading a discussion.
