|
|
|
|
|
|
by filoeleven
526 days ago
|
|
|
Check out this video at the 22:20 mark. The goal he’s pursuing is to have the LLM recognize when it’s attempting to make a factual statement, and to quote its training set directly instead of just going with the most likely next token. https://youtu.be/b2Hp0Jk9d4I?si=SwfKJrck5_0LPgTH |
|
|