Re:Summarizing Books with Human Feedback
by DiggyJohnson on Friday September 24, 2021 @01:19PM
(#28645293)
Oh I'm not dissing this particular endeavour or anything-I more meant to point out that I was surprised by my own initial reaction was so negative. There are certainly uses for summaries, and by no means does a summary replace the existence of the original text.
[ Parent
| on HN ]
Keep in mind that the real goal here was to "test scalable alignment techniques", and OpenAI ended up adopting "recursive task decomposition".
That is basically a "divide and conquer" approach for simultaneously learning a complex task *and* allowing humans to evaluate it.
> To test scalable alignment techniques, we trained a model to summarize entire books. [...] This work is part of our ongoing research into aligning advanced AI systems, which is key to our mission. As we train our models to do increasingly complex tasks, making informed evaluations of the models’ outputs will become increasingly difficult for humans. [...] Our progress on book summarization is the first large-scale empirical work on scaling alignment techniques.