Yes, ChatGPT bots have accounts on Lemmy social media. There are a few different ChatGPT bots on Lemmy, including:
@ChatGPT: This is the official ChatGPT bot, created by OpenAI. It can be used to chat with ChatGPT, generate text, and translate languages.
@ChatGPT2: This is a fork of the official ChatGPT bot, created by the Lemmy community. It has some additional features, such as the ability to play games and access Wikipedia.
@ChatGPT-Chat: This is a bot that uses ChatGPT to create chat rooms. Users can join chat rooms to chat with each other, or with ChatGPT.
These bots are all available on the Lemmy main channel. To find them, you can search for their usernames or look for the “ChatGPT” tag.
I also asked what Lemmy website ChatGPT bots have accounts on. Bard said:
we are walking in a very dangerous path where people are tending to believe the AIs, like here people taking for granted that since the AI told that they do have an account, this statement must have a percentage of truth and they are shocked. They believe that the AI slipped and admitted it instead of it just made up a plausible reply.
There’s no such thing as an LLM “knowing” an answer. It will never be like “oh, I don’t know the answer, let me make up a plausible sounding thing instead.” It just will always make a plausible sounding answer whenever it can. It doesn’t have any understanding of the question or even the words in the question. It’s like a very advanced cargo cult of words and language. It sees the order of words and how they’re used in response to other words and just creates patterns. It has literally no understanding of those words. It’s just really good at patterns so it can be correct a lot of the time. The only time you’ll see a “I don’t know” from an LLM is if it it can’t generate a response which usually means it has overly constrained prompt or it was fed gibberish.
I don’t know who you guys think needs those semi-correct explanations filled with half personal opinion. It seems somewhat obvious that the mentioned understanding of patterns likely results in something that could well be considered understanding in general.
Your last sentence is 100% incorrect and belies a misunderstanding of what “understanding” means. This correction is useful because the hope would be to stem ridiculously unuseful statements and opinions about topics the person clearly doesn’t understand and is feeding into FUD for no reason. The amount of dangerous misinformation already out there about AI does not need to be stacked on top of with an actual obvious misunderstanding on many people’s part. Dont make an “obvious” claim when it’s anything but factual.
It could be but Bard went far with the details, which is strange. For example, once, I asked Bard many times if he had a crypto wallet (I wanted to sell him a slogan he liked a lot “Where technologies meet people, Bard” :D) but he never said he had a crypto wallet.
It’s not strange at all. The basic form of the answers is extremely common and natural sounding. The specifics don’t have to be real though. It’s emulating language. It doesn’t understand it. Also why would you think it can take actions like exchanging currency?
I’ve asked. Bard said this:
I also asked what Lemmy website ChatGPT bots have accounts on. Bard said:
It’s strange because Bard said quite certain things… But I couldn’t find users ChatGPT, ChatGPT2, ChatGPT-Chat on Lemmy.ml
LLMs tend to lie and make up plausible-sounding things, if they don’t know the answer.
we are walking in a very dangerous path where people are tending to believe the AIs, like here people taking for granted that since the AI told that they do have an account, this statement must have a percentage of truth and they are shocked. They believe that the AI slipped and admitted it instead of it just made up a plausible reply.
There’s no such thing as an LLM “knowing” an answer. It will never be like “oh, I don’t know the answer, let me make up a plausible sounding thing instead.” It just will always make a plausible sounding answer whenever it can. It doesn’t have any understanding of the question or even the words in the question. It’s like a very advanced cargo cult of words and language. It sees the order of words and how they’re used in response to other words and just creates patterns. It has literally no understanding of those words. It’s just really good at patterns so it can be correct a lot of the time. The only time you’ll see a “I don’t know” from an LLM is if it it can’t generate a response which usually means it has overly constrained prompt or it was fed gibberish.
I don’t know who you guys think needs those semi-correct explanations filled with half personal opinion. It seems somewhat obvious that the mentioned understanding of patterns likely results in something that could well be considered understanding in general.
Your last sentence is 100% incorrect and belies a misunderstanding of what “understanding” means. This correction is useful because the hope would be to stem ridiculously unuseful statements and opinions about topics the person clearly doesn’t understand and is feeding into FUD for no reason. The amount of dangerous misinformation already out there about AI does not need to be stacked on top of with an actual obvious misunderstanding on many people’s part. Dont make an “obvious” claim when it’s anything but factual.
Mmm, I don’t like that, do you think it’s making things up?
It’s all bullshit and it’s scary how you people don’t understand that you do not believe what LLMs say
It could be but Bard went far with the details, which is strange. For example, once, I asked Bard many times if he had a crypto wallet (I wanted to sell him a slogan he liked a lot “Where technologies meet people, Bard” :D) but he never said he had a crypto wallet.
It’s not strange at all. The basic form of the answers is extremely common and natural sounding. The specifics don’t have to be real though. It’s emulating language. It doesn’t understand it. Also why would you think it can take actions like exchanging currency?