I spent months building an AI evaluator. Then I realised I had no idea if it worked.
中文摘要
花数月构建AI评估器后，作者发现无法确定其有效性。核心问题是谁来评估评估器本身？
English Summary
After months building an AI evaluator, the creator questioned its effectiveness. The fundamental challenge: who evaluates the evaluator itself?
Original Excerpt
Who evaluates the evaluator? Continue reading on AI Advances »