为什么看起来大型语言模型总是高估实施时间？
2 分•作者: bridgettegraham•大约 2 个月前
我有所怀疑：他们估计实现某个功能需要多长时间，是因为他们接受过这类数据的训练。我经常看到他们估算需要 2 周/3 周或 5 天等等。但实际上，使用 Claude/GPT 中的智能体，最多只需要一两天就能完成。除非我遗漏了什么？其他人也注意到这一点了吗？
查看原文
I have my suspicion: they estimate how long people would have taken to implement some feature, becasue they were trained on such data. I consistently see estimates of 2 week/3 weeks or 5 days, etc. But then implementation takes a day or 2 max using agents within Claude/GPT. Unless I am missing something? Anybody else notice this?