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
One of the things I hate the most about current AI is the lecturing and moralising. It’s so annoyingly strict, even when you’re asking for something pretty innocent.
So just like people then 🤣
zing
Well, it’s not too surprising; if people are like that, and AIs learn from people…
They are literally trained on human generated content, so …
Well, it did do a lot of its learning on reddit and Twitter. Garbage in, garbage out
They are programmed to do that to cover the companies ass. They are also set up to not trust anything you tell them. I once tried to get chatGPT to accept that Russia might have invaded Ukraine in 2022, and it refused to believe anything not in the training data. (Might be different now, they seem to be updating it, just find a new recent event)
Well, of course. Who would in their right mind would set it up so random input from random people online gets included into the model?
The model is trained on known data and the web interface only lets you use the model, not contribute to train it.
Its not training the model, it’s the model using the context you provide it (in that instance). If you use an unfiltered LLM it will run with anything you say and go from there, for example you could tell it Mexico reclaimed Texas and it would carry on as if that’s true. But only until you close it down its not permanently changing the model it is just changing the context in which that instance is running.
The big tech companies are going to huge lengths to filter and censor their LLMs when used by the public both to prevent negative PR and because they dont want people to have unrestricted access to them.
And for good reason. If they trusted user input and took it at face value even for just the current conversation, the user could run wild and get it saying basically anything.
Also chatGPT not having current info is a problem when trying to feed it current info. It will either try to daydream with you or it will follow its data that has hundreds of sources saying they haven’t invaded yet.
As far as covering the companies ass, I think AI models currently have plenty of problems and I’m amazed that corporations can just let this run wild. Even being able to do what OP just did here is a big liability because more laws around AI aren’t even written yet. Companies are fine being sued and expect to be through this. They just think that will cost less than losing out on AI. And I think they’re right.
So true! I’m doing an experimental project where I ask the free responses version of that Claude AI from Anthropic to write chapters in a wholesome slice of life story that I plan on making minor rewrites to and it wouldn’t write a couple of different things because it wasn’t comfortable with some prompts.
Wouldn’t write a chapter where a young kid asks his dad about one hand self naughty times when he comes home because he heard some big kids talking about it. Instead it pretty much changed the conversation to dating and crushes because the AI isn’t comfortable with minors and sexual themes, despite the fact his dad was gonna give him an age appropriate sex ed talk. That one is understandable, so I kinda let that slide.
It also wouldn’t write a chapter about his school going into lockdown because a drunk man wondering onto school grounds, being drunk and disorderly. Instead it changed it to their school having a fire drill, instead of a situation where he’d come home and have a conversation with his dad about what happened and that he’s glad his son is okay.
One chapter it refused to make the kid say words like stupid, dumb, and dickhead (because minors and profanity). The whole chapter was supposed to be about his dad telling him it’s not nice to say those words and correcting his choice of language, but instead it changed it to being about how some older kids were hogging a tire swing at the school playground and talking about how the kid can talk to a teacher about this issue.
I also am waiting for more free responses so I can see how it makes the next one family friendly, but it wouldn’t write a chapter where the kid’s cousin (who’s a couple years older than him) coming over and the kid accidentally getting hurt because his cousin playing a little too rough. Also said he’s a little bit of a bad influence. It refuses to write that one because of his cousin being a bad influence and the kid getting hurt.
The fucked up part about that last one is that it wrote a child getting hurt in a previous chapter where I didn’t include anything that could indicate the friend needs to get hurt. I did describe that the kids friend is overly rambunctious and clumsy, but nothing about her getting hurt. Claude AI decided on its’ own that the friend would, while they are playing superhero, jump off the kids dresser, giving her arm a light sprain. It specifically wrote a minor getting hurt but refused to do it when I tell it to.
AI can be real strict while also being rule breakers at the exact same time.
I understand where the strictness comes from. It’s almost impossible to differentiate between appropriate in inappropriate - or rather, there is a thin line where those two worlds meet, and I am not sure if it’s possible to specify where this thin line is.
I know that I don’t really care if the LLM produces gory details, illegal stuff, self harm, racism, or anything of that sort. But does Google / Facebook / others want to be associated with it? “Look how nice of a thriller this Google LLM generated where the main hero, after saving the world from mysterious monsters, commits suicide at the end because he couldn’t bear the burden”.
Society is fucked, and this is where we got to - overappropriation. Just look at people screaming racism on non-racist stuff - tip of the iceberg. And it’s been happening more and more over the last few years. People are bored and want to outraged at SOMETHING.
I think it’s more accurate to say that the company running the ai has a set of keywords that when spotted in a prompt reject the prompt
I agree, I didn’t ask for its ethical viewpoint and also i don’t care. it’s incredibly annoying when it tells me it’s wrong to depfake my dead grandmother.
That’s only true with the corporate controlled ones, they filter all the results extensively to avoid it giving any answer that goes even slightly against American corporate norms. If you host your own LLM you get entirely unfiltered answers.
Which model do you find works best?
Entirely depends what you are wanting to use it for. Unless you have a beast of a machine you cant run huge generalist models like chatGPT so you have to look for smaller models tuned to your use case. I’ve been liking mythomax for story telling and wizard coder for coding based tasks.
It sure is annoying, but it’s understandable. With these first few iterations you can imagine opponents frothing at the mouth about skynet if a chatbot can be used for something even vaguely inappropriate.
Jeez, they must be on Lemmy fulltime.
One day of using lemmy and I realized that what I hate about reddit isn’t (only) the corporation that runs it, it’s the fucking obnoxious people. And … who is on Lemmy? The same people. It’s a vicious cycle.