News for hackers. Stuff that matters.
Re:GPT-Prompt-Engineer by larodi on Tuesday July 11, 2023 @07:59AM (#36679741)
it seems to me also, that this is very much some sort of snake oil for the llm era. prompt generation varies from llm-to-llm and I doubt gpt4 can do reasonable evaluation, provided that it does not know at all about other models.
Re:GPT-Prompt-Engineer by londons_explore on Tuesday July 11, 2023 @08:03AM (#36679788)
The various leaderboards show that, in aggregate, LLM's acting as evaluators match other LLM's and humans remarkably closely.