flâneur — a map of the web's best reading

The novelty quotient - LessWrong

lesswrong.com · 989 words · saved by 1 readers

Comment by gwern - Some relevant links: https://ahrm.github.io/jekyll/update/2022/04/14/using-languge-models-to-read-faster.html [https://ahrm.github.io/jekyll/update/2022/04/14/using-languge-models-to-read-faster.html] https://www.gwern.net/docs/psychology/novelty/index [https://www.gwern.net/docs/psychology/novelty/index] https://arxiv.org/abs/2210.14140 [https://arxiv.org/abs/2210.14140] https://arxiv.org/abs/2109.00698#eleutherai [https://arxiv.org/abs/2109.00698#eleutherai]

x The novelty quotient — LessWrong Creativity Rationality Frontpage 4 The novelty quotient by River Lewis 7th Dec 2022 3 min read 7 4 This is a linkpost for https://heytraveler.substack.com/p/the-novelty-quotient I. The Device Imagine a device that listens to all of your conversations. It has a single purpose: live-running your utterances through text-davinci-003 to evaluate how surprising each token is, given its preceding context. [1] Users could chart their verbal novelty throughout the day; highlight and share their most unusual turns of phrase; note which friends put them on well-worn pat

Explore this link on the map →

related reading