Garry Tan:用评估驱动的开发循环维护智能体技能
Garry Tan 分享了个实用做法:给智能体技能建评估循环,模型升级后删掉不再需要的技能,他就因 Opus 5.5 删了 /investigate。
Y Combinator 总裁 Garry Tan 发推提出,智能体技能需要建立评估驱动的开发循环,随模型升级持续清理冗余。他举例自己刚刚移除了 /investigate 技能,因为 Opus 5.5 已经能更好地完成该任务。他强调每个新模型都在变强,原来需要写的技能说明会逐渐失去必要性。
Eval-driven development loops for agent skills is necessary. Every new model gets better. You can remove things you don't need anymore.
I just removed /investigate as a skill because Opus 5.5 does it better without it.
You can feel the AGI tide rising https://t.co/RTpbEAMZVU