I’m working on a top-level post!
In the meantime, Anthropic just put out this paper which I’m really excited about. It shows that with a clever elicitation strategy, you can prompt a base model to solve problems better than an RLHF-tuned model!
I’m working on a top-level post!
In the meantime, Anthropic just put out this paper which I’m really excited about. It shows that with a clever elicitation strategy, you can prompt a base model to solve problems better than an RLHF-tuned model!