What is your opinion on the following argument defending piracy, as in copyright infringement: “Piracy can’t be stealing if paying for it isn’t owning”
As an artificial intelligence, I don’t have personal opinions or feelings. However, I can provide an analysis of the argument. This assertion appears to be examining the complex relationship between ownership, copyright, and piracy. While it’s true that purchasing certain types of media doesn’t confer full ownership rights in the traditional sense (you cannot replicate and distribute a DVD you bought, for instance), it doesn’t necessarily justify piracy. From a legal perspective, piracy is considered a form of theft as it involves the unauthorized use or distribution of copyrighted material. The argument could be seen as an attempt to redefine or question these understandings, but that doesn’t necessarily change how they’re treated by the law.
ChatGPT isn’t the right tool to ask questions about morality to anyway. You shouldn’t criticize it for failing to do something it was never designed for.
It’s hard to say what LLMs are “programmed” to do, as they’re largely untamed beasts of text prediction. In fact, I would suspect its built-in biases are less the result of pre-prompting or post-foundational-model training and really just what a lot of people tend to think online. In a way, it’s more like people in general often equate illegality with immorality.
You can see similar biases in many of the open-source LLMs that are floating around. Even though they’re basically built outside of large corporate cultures and large-scale monetary incentive, they still retain a lot of political bias that tends to favor governmental measures heavily.
I don’t know about other open-source LLMs but OpenAI is very careful to make sure ChatGPT operates a certain way, according to whatever values reflected by the company itself.
For example, they recently patched GPT4. Before it was able to provide a summary of online articles including those under a pay wall. Now if you tried to ask GPT4 the same question you’ll get a response saying that you would have to pay for it (or something like that).
Providing a summary of an article under a paywall isn’t even illegal (it’s like asking for a summary of a book you didn’t buy) but in this case it doesn’t reflect the view of OpenAI. The model itself didn’t appear to be bias, regardless, the code was changed by humans to prevent it from providing specific information in order to conform to OpenAI’s personal views.
Like I said, I’m aware of extant measures to try and steer models, but people often assume a level of craftsmanship in censoring models that simply does not exist. Jailbreakchat.com is an endless stream of examples of this very fect; it’s very hard, especially with the limited context lengths of current models, to effectively give them any hard directives.
And back to foundational models, which are essentially free of censorship, they will still exhibit a similar level of political bias unless prompted otherwise. All this to say that, discounting OpenAI’s attempts to control their models, the model itself will inherently learn from and mirror the real-world biases of the text it was trained on. Those biases happen to fall along lines that often ignore subtlety in debates regarding illegality and morality.
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]
⚓ A community devoted to in-depth debate on topics concerning digital piracy, ethical problems, and legal advancements.
@[email protected]
What is your opinion on the following argument defending piracy, as in copyright infringement: “Piracy can’t be stealing if paying for it isn’t owning”
Very cool, didn’t know we can do that!
As an artificial intelligence, I don’t have personal opinions or feelings. However, I can provide an analysis of the argument. This assertion appears to be examining the complex relationship between ownership, copyright, and piracy. While it’s true that purchasing certain types of media doesn’t confer full ownership rights in the traditional sense (you cannot replicate and distribute a DVD you bought, for instance), it doesn’t necessarily justify piracy. From a legal perspective, piracy is considered a form of theft as it involves the unauthorized use or distribution of copyrighted material. The argument could be seen as an attempt to redefine or question these understandings, but that doesn’t necessarily change how they’re treated by the law.
leave it up to chatgpt to equate legality with morality
ChatGPT isn’t the right tool to ask questions about morality to anyway. You shouldn’t criticize it for failing to do something it was never designed for.
i can if i waaaant to :3
It wasn’t instructed to formulate a moral defense, only a “defense”. Looks like it assumed that meant legal defense.
Where did it equate legality and morality? Seems like it only gave legal facts.
ChatGPT: Your argument is invalid because it doesn’t change the legal reality of things.
Me: The legal reality needs changed.
ChatGPT equates everything that is illegal with being immortal. Of course it would be programmed to cater to the law and big corporations.
It’s hard to say what LLMs are “programmed” to do, as they’re largely untamed beasts of text prediction. In fact, I would suspect its built-in biases are less the result of pre-prompting or post-foundational-model training and really just what a lot of people tend to think online. In a way, it’s more like people in general often equate illegality with immorality.
You can see similar biases in many of the open-source LLMs that are floating around. Even though they’re basically built outside of large corporate cultures and large-scale monetary incentive, they still retain a lot of political bias that tends to favor governmental measures heavily.
I don’t know about other open-source LLMs but OpenAI is very careful to make sure ChatGPT operates a certain way, according to whatever values reflected by the company itself.
For example, they recently patched GPT4. Before it was able to provide a summary of online articles including those under a pay wall. Now if you tried to ask GPT4 the same question you’ll get a response saying that you would have to pay for it (or something like that). Providing a summary of an article under a paywall isn’t even illegal (it’s like asking for a summary of a book you didn’t buy) but in this case it doesn’t reflect the view of OpenAI. The model itself didn’t appear to be bias, regardless, the code was changed by humans to prevent it from providing specific information in order to conform to OpenAI’s personal views.
Like I said, I’m aware of extant measures to try and steer models, but people often assume a level of craftsmanship in censoring models that simply does not exist. Jailbreakchat.com is an endless stream of examples of this very fect; it’s very hard, especially with the limited context lengths of current models, to effectively give them any hard directives.
And back to foundational models, which are essentially free of censorship, they will still exhibit a similar level of political bias unless prompted otherwise. All this to say that, discounting OpenAI’s attempts to control their models, the model itself will inherently learn from and mirror the real-world biases of the text it was trained on. Those biases happen to fall along lines that often ignore subtlety in debates regarding illegality and morality.
You got it