Advanced
In reply to @m-j-r
7/22/2023
Connor McCormick@nor
can you say more, what are you primarily reading / following re alignment?
In reply to @nor
7/22/2023
m_j_r@m-j-r
I would say it's partly informed by the research coming out. technique has to work its way through scarce inputs (e.g. API cost in FrugalGPT) + the theory that symbolic regression/weaker models (LATM paper) is more ideal after using the most powerful intelligence exclusively for discovery. alignment is an issue,...