Sweden prime minister under fire after admitting that he regularly consults AI tools for a second opinion
-
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..
-
We don't NEED any particular technology to exist. That's a weird distinction to make.
inspiration? They are more of an inspiration killer imo.
Different minds work differently.
No, mankind certainly needs a lot of techonologies (maybe just out of built dependency) either to mantain our living standards or just plainly to ensure that we produce and distribute enough resources for everyone to survive.
We need LLMs as much as we needed 3D movies or augmented reality.
-
Maybe it shouldn't be a business model then.
it is what it is: a very expensive toy.
-
Of common, you justifying stealing by this bullshit?
i'm generally fine with stealing as practice in the daily class struggle. i mean the owning class has the legal right to do so. and in doubt they just exercise it, judges will later find it to be fair use. no need to justify, it's description of societies' order.
-
No, mankind certainly needs a lot of techonologies (maybe just out of built dependency) either to mantain our living standards or just plainly to ensure that we produce and distribute enough resources for everyone to survive.
We need LLMs as much as we needed 3D movies or augmented reality.
We need LLMs as much as we needed 3D movies or augmented reality.
als brechmittel.
-
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.
-
One thing I struggle with AI is the answers it gives always seem plausable, but any time I quiz it on things I understand well, it seems to constantly get things slightly wrong. Which tells me it is getting everything slightly wrong, I just don't know enough to know it.
I see the same issue with TV. Anyone who works in a compicated field has felt the sting of watching a TV show fail to accurate represent it while most people watching just assume that's how your job works.
This is where you have to check out the reference links it gives as if they were search results and the less you know the more you have to do it. I mean people have been webMDing for a long time. None of these things allow folks to stop critical thinking. If anything it requires it even more. This was actually one of my things with ai and work. The idea is for it to allow people with less knowledge to do things and to me its kinda the reverse.
-
No, mankind certainly needs a lot of techonologies (maybe just out of built dependency) either to mantain our living standards or just plainly to ensure that we produce and distribute enough resources for everyone to survive.
We need LLMs as much as we needed 3D movies or augmented reality.
Take any of those technologies that we depend on today, and go back to the decade they were invented. Practically none of them would have been considered 'needed' either. It takes time for technology to mature and be adopted. I'll grant that the crazy pro-AI shills aren't helping things any
-
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.
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.
-
This post did not contain any content.
Politicians and CEOs should be replaced with LLMs
-
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.
-
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.
-
I really don't get it. These things are brand new. How can anyone get so into these things so quickly. I don't take advice from people I barely know, much less ones that can be so easily and quickly reprogrammed.
Because that's what it is really trained for: to produce correct grammar and plausible sentences. It's really an unbelievable leap from computer-generated text from preceding approaches where, in a matter of a few years, you went from little more than gibberish to stuff that's so incredibly realistic that it can be mistaken for intelligent conversation, easily passing the Turing Test (I had to actually go to Wikipedia to check and, indeed, this was verified this year - note that this in particular is for recent models)
So you have something that is sufficiently realistic that it can appear to be a human conversation partner. Human beings aren't (yet) well-equipped to deal with something which appears to be human but whose behaviour diverges from typical human behaviour so radically (most relevantly, it won't readily admit to not knowing something).
-
Because that's what it is really trained for: to produce correct grammar and plausible sentences. It's really an unbelievable leap from computer-generated text from preceding approaches where, in a matter of a few years, you went from little more than gibberish to stuff that's so incredibly realistic that it can be mistaken for intelligent conversation, easily passing the Turing Test (I had to actually go to Wikipedia to check and, indeed, this was verified this year - note that this in particular is for recent models)
So you have something that is sufficiently realistic that it can appear to be a human conversation partner. Human beings aren't (yet) well-equipped to deal with something which appears to be human but whose behaviour diverges from typical human behaviour so radically (most relevantly, it won't readily admit to not knowing something).
Its more than that. It takes the input and tries to interpret the bad grammar and sentences into search terms and finds link the correlate the highest to its interpretation and then gives back the response that summarizes the results with good grammar and plausible sentences. Again this is why I stress that you have to evaluate its response and sources. The sources are the real value in any query. Im actually not sure how much the chatbots give sources by default though as I know I have not gotten them and then asked for them and now I get them as a matter of course so im not sure if it learns that I want them or if they did a change to provide them when they had not before.
-
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.
-
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?
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.
-
Fuck no. Rather an incompetent politician than a hallucinating sycophant just telling you what you want to hear.
Nah you are wrong and should use AI as a first opinion
-
Politicians and CEOs should be replaced with LLMs
It can't make things any worse...
-
Nah you are wrong and should use AI as a first opinion
Wait... how many fingers do you have on each hand?
-
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.
-
-
-
-
Large majority of French, German and Spanish public back tough EU stance on Big Tech, despite risk to Trump relations
Technology1
-
China New Internet ID System a Threat to Online Expression: Netizens will require IDs to go on the internet. For now this is voluntary, but there are signs it will not remain that way for long.
Technology1
-
-
-