Elvis Saravia(DAIR.AI)称他如今很少直接向智能体提示,而是依靠循环(loops)让智能体自主完成大部分工作。他转而花更多时间编写验证器(verifiers),通过文本、音频、图像提供丰富指令弥补智能体知识缺口。引用推文补充,2026年6月起应放弃手动编辑提示词,改用语音听写10分钟,将碎片、警示、示例和氛围直接灌给模型——大语言模型最擅长从语言中重构潜在意图。这标志着AI智能体交互正从精细提示转向循环+口述+验证器的新范式。
I don't even prompt/speak to agents that much anymore.
With loops, agents do most of it for me now.
I do spend more time writing verifiers to provide additional rich instructions (text+audio+images) that help fill in gaps.
What's next? Hard to tell!