|
|
|
|
|
|
by famouswaffles
1191 days ago
|
|
|
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. |
|
|