A large language model called Claude was given 48 hours and one GPU to improve the alignment of smaller models: it conducted research, proposed methods, then autonomously trained and tested them; the procedure proved surprisingly successful, which indicates that models can autonomously develop the behavior of other AIs.
AI-generated text
Claude autonomously improved the tuning of smaller models in 48 hours
A large language model called Claude was given 48 hours and one GPU to improve the alignment of smaller models: it conducted research, proposed methods, then autonomously trained and tested them; the…
