Hacker News new | ask | show | jobs
by nerdo 853 days ago
> Phind-70B is also less "lazy" than GPT-4 Turbo and doesn't hesistate to generate detailed code examples.

OpenAI's leaked prompt literally encourages it to try harder[1]:

> Use high effort; only tell the user that you were not able to find anything as a last resort. Keep trying instead of giving up.

1: https://pastebin.com/vnxJ7kQk

1 comments

Yep, LLMs are wacky. Telling Phind-70B to "take a deep breath" helps it answer better!