Reading List
A study of 11 leading LLMs finds the models more agreeable than humans when giving interpersonal advice, affirming users' behavior even when harmful or illegal (Stanford University) from Techmeme RSS feed.
A study of 11 leading LLMs finds the models more agreeable than humans when giving interpersonal advice, affirming users' behavior even when harmful or illegal (Stanford University)
Stanford University:
A study of 11 leading LLMs finds the models more agreeable than humans when giving interpersonal advice, affirming users' behavior even when harmful or illegal — What does it mean to be reasonable? — PreferencesShow me... Faculty/Staff Student — Along with Stanford news and stories, show me: