OpenAI 的 Ted Sanders 分享选择合适 GPT 模型的经验法则
原标题：OpenAI's Ted Sanders shares a rule of thumb for picking the right GPT-model
AI 摘要
OpenAI 的 Ted Sanders 介绍了公司语言模型的命名逻辑，并给出选择 GPT 模型的经验法则。他指出模型性能是多维的，多数性能差距主要取决于模型规模，但规模并非全部，新模型可通过更好的训练数据和架构超越旧的大模型。他按质量与价格敏感度给出建议：只看质量选 Astra，稍在意价格选 Sol，非常在意价格选 Terra 或 Luna。
正文节选
OpenAI's Ted Sanders shares a rule of thumb for picking the right GPT-model OpenAI's Ted Sanders has categorized the new GPT-6.1 Terra and explained how the company names its language models. According to Sanders, model performance is multidimensional. A model that's great at math won't automatically be good at jokes. Still, most performance gaps come down to one variable: model size. Sanders says OpenAI's model names are difficult to simplify because model size, reasoning effort, and multi-agen