personal-agentPOST
观点:AI 模型更适合代理而非直接给人用
作者认为最有效的 AI 产品靠大量持久代理互相协作,Grok Bot、Muse 都是如此;人类应退到与个人助理对话的更高抽象层。
Ejaaz
@cryptopunk721314 天前收录原推发布于 2026.10.25
Ejaaz @cryptopunk7213原推发布于 2026.10.25
hot take: ai models aren’t suited for humans, they’re suited for agents, think about it: - to date the most effective AI products leverage swarms or 100s of persistent agents talking to each other. grok bot, muse etc all do this too. - 99% humans don’t really know what to do with a model, an agent built on your context tho? does. this isn’t me saying humans aren’t in the equation, they’re just at a higher abstraction (talking to personal agents) assume every human has multiple agents running 24/7 talking to one another that’s the future to expect
这条是引用着另一条写的:x.com/elonmusk/status/2114036686870982681
x.com/cryptopunk7213/status/2114230696403173385采集于 2026.10.26 10:43