|
|
|
|
|
|
by Charon77
47 days ago
|
|
|
Ironically I used AI for this question, and what came out is 'Echo prompt' apparently it's a thing: repeating LLM instructions twice increases accuracy. Another idea was Chain of Thought leakage. It's like as if a chef saying "Now I am adding salt because the customer requested so" |
|
|