News for hackers. Stuff that matters.
Re:CriticGPT: Finding GPT-4's mistakes with GPT-4 by upwardbound on Friday June 28, 2024 @05:06AM (#40818909)
You make a good point so I should clarify that Iterated Amplification is an idea that was first proposed as a technique for AGI safety, but happens to also be applicable to LLM safety. I study AGI safety which is why I recognized the technique.

There are no comments on this comment yet.