Sherwin Wu· @sherwinwu · X·· 1 天前AI 评分56
AI 导读
Sherwin Wu 转引 @OpenAIDevs 消息并评论：当模型推理基本即时后，期待看到人们接下来抱怨什么新瓶颈。其引用的内容称 Codex 中的 Ultrafast 是迄今最快的 Astra 构建方式，比 Astra Standard 快至 8 倍、比 Astra Fast 快至 4 倍。作者称这是一种 Divinely discontent（神圣的不满足）。
正文
Excited to see what new bottlenecks people complain about next when model inference is ~basically instant 🙃
Divinely discontent!
Ultrafast is our fastest way to build with Astra yet: in Codex, it runs up to 8x faster than Astra Standard and 4x faster than Astra Fast. Bring your ideas to life as fast as you can type them.在 X 查看被引用的帖子
来源：Sherwin Wu · x.com