“Summarizing Books with Human Feedback” was published on OpenAI.com. It is a quick read, very clear and well written. They share some examples from on how they had AI summarizing books. In the article they give the example of the classic “Alice’s Adventures in Wonderland”, by Lewis Carroll which they used to test it.
They briefly explain their recursive approach and how they include human feedback during the process evaluating the AI’s summarys.
They also include a link to their official research paper written by Jeff Wu, Long Ouyang, Daniel M. Ziegler, Nisan Stiennon, Ryan Lowe, Jan Leike, Paul Christiano.
In my opinion it is an impressive task that has been achieved so far. Though there is still lots to improve from briefly looking at the summaries, to have AI summarizing books is still impressive.
It is a remarkable work that I think can have great application especially for technical texts in my opinion, though for fiction texts I think it will not be as applicable. I wish I had had this tool when I was studying to double check my summaries.
I believe that the summaries lack some human touch but this is logic. However this is very subjective though from my side.