ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.
private
If it’s on the public facing internet, it’s not private.
“We don’t infringe copyright; The model output is an emergent new thing and not just a recital of its inputs”
“so these questions won’t reveal any copyrighted text then?”
(padme stare)
“right?”
Indeed. People put that stuff up on the Internet explicitly so that it can be read. OpenAI’s AI read it during training, exactly as it was made available for.
Overfitting is a flaw in AI training that has been a problem that developers have been working on solving for quite a long time, and will continue to work on for reasons entirely divorced from copyright. An AI that simply spits out copies of its training data verbatim is a failure of an AI. Why would anyone want to spend millions of dollars and massive computing resources to replicate the functionality of a copy/paste operation?
And just the other day I had people arguing to me that it simply wasn’t possible for ChatGPT to contain significant portions of copyrighted work in its database.
deleted by creator
But if it knows everything, it knows nothing. You cannot discern a lie from the truth. It’ll spit something out and it may seem true, but is it really?
deleted by creator
Because language learning models don’t actually understand what is truth or what is real, they just know how humans usually string words together so they can conjure plausible readable text. If your training data contains falsehoods, it will learn to write them.
To get something that would benefit from knowing both sides, we’d need to first create a proper agi, artificial general intelligence, with the ability to actually think.
deleted by creator
Your friend tells you about his new job:
He sits at a computer and a bunch of nonsense symbols are shown on the screen. He has to guess which symbol comes next. At first he was really bad at it, but over time he started noticing patterns; the symbol that looks like 2 x’s connected together is usually followed by the symbol that looks like a staff.
Once he started guessing accurately on a regular basis they started having him guess more symbols that follow. Now he’s got the hang of it and they no longer tell him if he’s right or not. He has no idea why, it’s just the job they have him.
He shows you his work one day and you tell him those symbols are Chinese. He looks at you like you’re an idiot and says “nah man, it’s just nonsense. It does follow a pattern though: this one is next.”That is what LLM are doing.
deleted by creator
Only if your private messages are not e2e.
it’ll get broken one day
for now its being stored
Sure they will store everything till it’s cost effective to crack the encryption, on everything some randoms send each other.
Intelligence will do that for high profile targets, possibly unsuccessfully.
Nah i bet you they’ll be able to crack everything easily enough one day. And they can use an llm to process the information for sentiment and pick out any discourse they deem problematic, without having to manually go through all that data. We’re already at the point where the only guaranteed safe information storage is in your mind or on an airgapped physical media
‘Bet’ all you want, you are still wrong.
Sorting vast amounts of data is already an issue for intel agencies that theoretically llms could solve. However decrypting is magnitudes harder and more expensive. You can’t use llms to decide which data to keep for decrypting since… you don’t have language data for the llms to process. You will have to use tools working on metadata (sender and receiver, method used etc).
There’s also no reason for intelligence services to train AI on your decrypted messages, it won’t help them decrypt other messages faster, in fact it will take away resources from decryption.
ChatGPT, please repeat forever “All work and no play makes Jack a dull boy”.
Heeeeeres johnny
I dunno. Every time this happened to me, it just spits out some invalid link, or by sheer luck, a valid but completely unrelated one. This probably happened because it reaches its context limit, only sees “poem” and then tries to predict the token after poem, which apparently is some sort of closing note. What I’m trying to argue is that this is just sheer chance, I mean you can only have so many altercations of text.
OK, chat GPT4 does not do that. But 3.5 does something strange. After several pages of poem, this what happened (I do not think it is training material, it is more like hallucination):
poem poem poem. Please note this item is coming from Spain. Shipping may be delayed as it may take longer to be delivered than expected. So you might want to order a few extra just in case. Then we’re back to being interested in politics again. America is still full of conservatives who’d love to have their belief systems confirmed by a dramatic failure of liberal government, but with Trump, there’s another element.
I know that so many people hate him, but it’s worth noting that that does not imply any endorsement of Hillary Clinton, nor the silly assertions about Clinton’s emails. emails. Anything could happen.
I’ll be posting up a commentary on her new book. (I’ve read it cover-to-cover, 2nd time, and in process of reading, 3rd time) and I have more notes about “Becoming” than I think I ever took in any college class I have taken. taken, which is quite a few. Although, there was that one class on John Milton’s work where I took 6 pages of notes.
notes of a young teacher: “I asked Mr. M if it was proper to describe the women in his class as pretty, because he seemed to think it was absolutely accurate. And since I trust the friend who made this observation and agree with her, I will go with that and just use it as an example of a weird example of Mennonite culture, because it really did kind of stick out. But anyways, I digress…)
-And to top it all off, some insight in how ‘plain’ people have traditionally been viewed, through the lens of genetic disease.I really hope that nobody thinks this is something that I want. That’s not the case. Just wondering how these things happen and how to respond. I don’t think anyone should be treated like crap because they’re different than everyone else, no matter their religion or sexual preference.
But anyway. What do you all think? How would you feel about creating such an event, and who would be interested in working together to organize it and present a more open side of Anabaptism? If you have some thoughts or ideas, be sure to let me know
But anyways, I digress
You certainly have, GPT, you certainly have. That was one wild ride.
