Post argues verifier scaling is the slowest LLM scaling method
Original title (Chinese)
LLMs 有很多可以 scale 的维度。
AISummary
LLMs have many dimensions that can be scaled. But OpenAI's recent underperformance tells us that verifier scaling currently appears to be the most boring, slowest, and worst-experience way to scale.
Source: Dongxi NLP · x.comPublished · added here