AI 导读
仅仅 2.5 年前，AI 实验室还会炫耀其前沿 LLM 在小学水平数学基准（GSM8K）上的表现。我迫不及待想看到再过 2.5 年我们会走到哪里。
正文
Only 2.5 years ago, AI labs would brag about their frontier LLM performance on grade school math benchmarks (GSM8K). I can't wait to see where we'll be in another 2.5 years.
It just never gets old在 X 查看被引用的帖子
来源：Noam Brown · x.com