原文整理页

Madhu Guru 建议不要将复杂的模型评估结果简化为单一分数,并透露 Gemini 早期也曾因此踩坑

来源作者:Madhu Guru (@realmadhuguru)原始来源:https://x.com/realmadhuguru/status/2090930137885774324

中文导读

Madhu Guru 建议不要将复杂的模型评估结果简化为单一分数,并透露 Gemini 早期也曾因此踩坑。

正文 Markdown

How to build great evals - part 5 Stop dumbing down the results from your beautiful, complex eval suite into one single score. This often happens because some senior wants a simplified number to make decisions. Happened to us in the early days of Gemini. And I see it happening