This blog post comes basically in two parts: the role which LLM assistants are trained for is horribly undefined and ontologically hella strange, and AI safety “””researchers””” are basically goading LLMs into misalignment without any concern for the consequences.

Yay, LLM-induced psychosis! Man, the posts and articles of this genre do not stop flowing…

Really heartfelt piece that cuts through the noise imo. It deals with it quite fairly.

Web review of Ervin