Re:GPTs Are GPTs: An Early Look at the Labor Market Impact P...
by og_kalu on Monday March 20, 2023 @07:18AM
(#35229955)
Literally LLMs get much better with chain of thought, feedback, and/or consensus.
Gpt-3 performance on MultiArith goes from 18% to 92% with all three. This isn't some hackneyed anthropomizing. Countless research papers showing massive improvement with these processes.
Gpt-3 performance on MultiArith goes from 18% to 92% with all three. This isn't some hackneyed anthropomizing. Countless research papers showing massive improvement with these processes.