The models are essentially a giant lossy compression applied to the training data.
They don’t store the loseless version of the training data sure, but that doesn’t mean it can’t reproduce something close enough to it, it’s literally how the whole thing works.
It’s long been proven that LLMs can produce exact copies of their training data. Not every piece of training data, of course, but enough where spitting out exact replicas of proprietary code is a legitimate concern. Not to mention that copies don’t need to be exact in order to be a problem.
The models don’t store access to their training data. So no, there’s no source code in the model to retrieve.
The models are essentially a giant lossy compression applied to the training data.
They don’t store the loseless version of the training data sure, but that doesn’t mean it can’t reproduce something close enough to it, it’s literally how the whole thing works.
It’s long been proven that LLMs can produce exact copies of their training data. Not every piece of training data, of course, but enough where spitting out exact replicas of proprietary code is a legitimate concern. Not to mention that copies don’t need to be exact in order to be a problem.
So why can they recreate entire articles from the New Yorker and complete functions from the training set? Don’t fall for the slop laundering.