I am of the general understanding that this paper became less about the LLMs & more of a insinuating hit piece against Alphabet. At least, some of the controversial nuggets got Gebru (and later M Mitchell) fired.
From a technical standpoint, there is little new stuff that I found this paper offered in understanding why LLMs can have unpredictable nature, or what degree of data will get exposed by clever hacks (or if there are systematic ways to go about it). It sounded more like a collection of verifiable anecdotes for easy consumption (which can be a good thing by itself if you want capsule understanding in a non-technical way)
From a technical standpoint, there is little new stuff that I found this paper offered in understanding why LLMs can have unpredictable nature, or what degree of data will get exposed by clever hacks (or if there are systematic ways to go about it). It sounded more like a collection of verifiable anecdotes for easy consumption (which can be a good thing by itself if you want capsule understanding in a non-technical way)