Hacker News new | ask | show | jobs
by helsinkiandrew 823 days ago
> If I ask an LLM a very complex and specific question 500 times, if it just doesn't know the facts you'll still get the wrong answer 500 times.

Think the commenter meant use another model/LLM which could give a different answer, then let them vote on the result. Like "old fashioned AI" did with ensemble learning.