[Linkpost] Value extraction via language model abduction

[Paul Bricman]

Link post

This is my first post on lesswrong. I’ll merely be linkposting content on epistemics and alignment here while getting more familiar with the culture.

tl;dr:

We attempt to automatically infer one’s beliefs from their writing in three different ways. Initial results based on Twitter data hint at embeddings and language models being particularly promising approaches.