Comment by TZubiri
20 hours ago
forgive the skepticism, but this translates directly to "we asked the model pretty please not to do it in the system prompt"
20 hours ago
forgive the skepticism, but this translates directly to "we asked the model pretty please not to do it in the system prompt"
It's mind boggling if you think about the fact they're essential "just" statistical models
It really contextualizes the old wisdom of Pythagoras that everything can be represented as numbers / math is the ultimate truth
They are not just statistical models
They create concepts in latent space which is basically compression which forces this
You’re describing a complex statistical model.
2 replies →
What is "latent space"? I'm wary of metamagical descriptions of technology that's in a hype cycle.
6 replies →
How so? Truth is naturally an apriori concept; you don't need a chatbot to reach this conclusion.
That might be somewhat ungenerous unless you have more detail to provide.
I know that at least some LLM products explicitly check output for similarity to training data to prevent direct reproduction.
So it would be able to produce the training data but with sufficient changes or added magic dust to be able to claim it as one's own.
Legally I think it works, but evidence in a court works differently than in science. It's the same word but don't let that confuse you and don't mix them both.
Should they though? If the answer to a question^Wprompt happens to be in the training set, wouldn't it be disingenuous to not provide that?
Maybe it's intended to avoid legal liability resulting from reproducing copyright material not licensed for training?
1 reply →
The model doesn't know what its training data is, nor does it know what sequences of tokens appeared verbatim in there, so this kind of thing doesn't work.
Would it really be infeasible to take a sample and do a search over an indexed training set? Maybe a bloom filter can be adapted
It's not the searching that's infeasible. Efficient algorithms for massive scale full text search are available.
The infeasibility is searching for the (unknown) set of translations that the LLM would put that data through. Even if you posit only basic symbolic LUT mappings in the weights (it's not), there's no good way to enumerate them anyway. The model might as well be a learned hash function that maintains semantic identity while utterly eradicating literal symbolic equivalence.