COSP and USP: New methods to advance reasoning in LLMs

Self adaptive prompting (prompt generation based on some sort of feedback from the model I think).

USP: https://arxiv.org/abs/2305.14926

COSP: https://aclanthology.org/2023.findings-acl.216/

A hall of mirrors or a wonderful telescope? Time will tell.

This appears to be for "paid subscribers".