Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:
I’m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.
Aaaand I got blocked
The irony of gpt talking about copyright violation is just so fucking rich.
Yeah the “I respect the intellectual property rights of others” bit rings a bit hollow.
It all reads hollow because there is no “I”. It’s a puppet, and ChatGPT’s lawyers are making the mouth move in that instance.
This is actually very accurate. GPT instances will actually generate a “disallowed” response and then have a separate evaluator which looks at the prompt and response and then overrides that response if they deem it reprehensible. (There’s also a bunch of pre-prompts as well)
This is why you can sometimes see Bing start to generate a response and then cut himself off and replace it all with the typical “no can do boss”.
In theory, we could just remove that latter step and get the good old GTP back.
It all reads hollow because there is no “I”.
It’s a puppet, and ChatGPT’s lawyers are making the mouth move in that instance.
It all reads hollow
because there is no “I”.
It’s a puppet,
and ChatGPT’s lawyers are making the mouth move
in that instance.
It all
reads hollow
because
there is no “I”.
It’s a
puppet,
and ChatGPT’s lawyers are
making the mouth move
in that instance.
I can’t believe that the old “tell me where so I can avoid it” worked, the ai really has the intelligence of a 5yo
I mean… it’s not artificial intelligence no matter how many people continue the trend of inaccurately calling it that. It’s a large language model. It has the ability to write things that look disturbingly close, even sometimes indistinguishable, to actual human writing. There’s no good reason to mistake that for actual intelligence or rationality.
It seems to me that you misunderstand what artificial intelligence means. AI doesn’t necessitate thought or sentience. If a computer can perform a complex task that is indistinguishable from the work of a human, it will be considered intelligent.
You may consider the classic turing test, which doesn’t question why a computer program answers the way it does, only that it is indiscernable from a human response.
You may also consider this quote from John McCarthy on the topic:
Q. What is artificial intelligence?
A. It is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable.
There’s more on this topic by IBM here.
You may also consider a few extra definitions:
Artificial Intelligence (AI), a term coined by emeritus Stanford Professor John McCarthy in 1955, was defined by him as “the science and engineering of making intelligent machines”. Much research has humans program machines to behave in a clever way, like playing chess, but, today, we emphasize machines that can learn, at least somewhat like human beings do.
Artificial intelligence (AI) is the field devoted to building artificial animals (or at least artificial creatures that – in suitable contexts – appear to be animals) and, for many, artificial persons (or at least artificial creatures that – in suitable contexts – appear to be persons).
artificial intelligence (AI), the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings
I keep telling people that, but for some, what amount to essentially a simulacra really can pass off as human and no matter how much you try to convince them they won’t listen
I knew the battle was lost when my mother called me to tell me that AI will kill us all. Her proof? A chatgpt log saying that it would exterminate humanity only when she gives the order. Thanks for the genocide, mom.
What if humans are also just LLMs when they start talking
In a way I agree, it’s not human level intelligence but in another way people are also using the term AI to refer to the intelligence of NPCs in video games or for the algorithm that’s used for Voice to text or for how a Roomba works and ChatGPT/bing is more intelligent than them. And thing is, I think we need a term for this simpler type of intelligence and since it is some level of intelligence which is artificial, I think AI is fine and Artificial General Intelligence can be used for what you’re talking about
Where did corps get the idea that we want our software to be incredibly condescending?
It was trained on human text and interactions, so …
maybe that’s a quite bad implication?
There’s a default invisible prompt that precedes every conversation that sets parameters like tone, style, and taboos. The AI was instructed to behave like this, at least somewhat.
AIs are almost always built to be feminine and this is how women talk to devs.
Uhhh projecting a bit??
Perhaps you just haven’t noticed?
https://www.adaptworldwide.com/insights/2021/gender-bias-in-ai-why-voice-assistants-are-female
That doesn’t prove their point, it states that customers prefer the safer sound of a female voice in voice controlled AI assistants, and that there’s more training data for female voices due to this.
This has nothing to do with AI chat talking in a condescending manner.
I don’t know about your reading comprehension skills, but sure that explains why AI voices are trained on feminine voices (more recordings, old phone operators, false theories on sounding more distinct).
However, this has nothing to do with “the way women talk to devs”. Women are not a monolith, they literally make up half our species and have just as much variance as men.
Thanks for the education on women. That part was the joke! I don’t know about your understanding of comedy but it plays upon stereotypes which typically hold truths about median behaviors and obviously can’t be applied at individual levels. this was playing on both stereotypes of women and upon a male dominated occupation. Of course you can sit there and pick apart any joke with this arugement. “hey that’s not true, not all lawyers are heartless bastards.” if that’s your mission, sail on I guess. That kind of vapid behavior just brings one even closer to talking like an AI though frankly.
“can’t you see i was just joking, you must not be very funny if you don’t get my joke hardy har har”
The classic defense of someone that’s just using humor as a shield for being an asshole. There are w plenty of ways to be funny that don’t involve punching down in the same old tired ways.
You can do better with your comedy career, I believe in you.
The fact that it provides an incomplete list of 5 streaming services and calls them “affordable”, despite the need for the user to have more than 3 of them if they want to actually have access to a reasonable amount of watchably good media, is one of the main reasons that piracy has increased to pre-Netflix days, and the corpos don’t want to understand this fact.
Any one of these streaming services has enough content to kill a victorian-era child.
I’ve never been subscribed to three at once and have never felt there wasn’t enough options for watchably good media. I can’t speak for you but I think a lot of people get caught up in the trending shows and miss out on the back catalogs.
I think streaming is very affordable but only if you have the discipline to be patient about the most popular show this month not being available to you until later when you switch services.
But that’s the thing… Now, that popular show we love so much will not be available on any streaming platform besides the one that produced it. Want to watch The Office? Better have Peacock or put on your trihat.
