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
Right, but we already addressed that above. If it’s done on a local pc’s ai that doesn’t operate using a net connection, and is used in addition to rather than instead of consulting with people, then it’s totally fine
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 it’s a viewpoint created by “a fancy auto-complete” as some haters like to say
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.
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.
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.
You protect yourself against “propaganda” by educating yourself and not falling for emotions. Not reading LLM responses won’t safe you from propaganda.
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 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
Since it’s so easy to do i just went ahead and did it. 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.
Dude you’re saying nonsense. You said ai can’t defend its arguments. I provided incontrovertible evidence that it can. I’m going to say this as nicely as possible - you want to think that LLMs are unable to do anything useful so that you can hold onto a false belief about ourselves. And that is the reason why my comment is being half downvoted
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?
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.
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.
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
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 that doesn’t use a net connection
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.
Right, but we already addressed that above. If it’s done on a local pc’s ai that doesn’t operate using a net connection, and is used in addition to rather than instead of consulting with people, then it’s totally fine
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 it’s a viewpoint created by “a fancy auto-complete” as some haters like to say
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.
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.
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.
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.
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.
Since it’s so easy to do i just went ahead and did it. 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
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
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.
Dude you’re saying nonsense. You said ai can’t defend its arguments. I provided incontrovertible evidence that it can. I’m going to say this as nicely as possible - you want to think that LLMs are unable to do anything useful so that you can hold onto a false belief about ourselves. And that is the reason why my comment is being half downvoted
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?
I certainly don’t want my attorney wasting time considering the opinions and motivations of the person that’s suing me.
Well you’re gonna have a shitty attorney then
Lmao. You people are fucking idiots.
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.
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.