一篇论文让 100 个 LLM 智能体在 Pokhara Lakeside 的真实地理上运行城镇经济 26 个模拟周,共 91 次运行、244 万次决策,发现资金停止流动。
X:Elvis Saravia
@omarsar0 · X
切换来源
@omarsar0@omarsar0AI 评分5353 
@omarsar0@omarsar0AI 评分4444 
@omarsar0@omarsar0AI 评分3434 
@omarsar0@omarsar0AI 评分3030 @omarsar0@omarsar0AI 评分2525 @omarsar0@omarsar0AI 评分2626 Elvis Saravia 呼吁开发者自建并掌控自己的 Agent harness,认为即使是最小化的 harness 也能带来更好的代码、输出、成本和写作效果。
@omarsar0@omarsar0AI 评分2121 @omarsar0@omarsar0AI 评分5959 
@omarsar0@omarsar0AI 评分2121 @omarsar0@omarsar0AI 评分5656 
@omarsar0@omarsar0AI 评分4646 @omarsar0@omarsar0AI 评分3232 
@omarsar0@omarsar0AI 评分1717 @omarsar0@omarsar0AI 评分4646 
@omarsar0@omarsar0AI 评分5151 
@omarsar0@omarsar0AI 评分3131 @omarsar0@omarsar0AI 评分2323 @omarsar0@omarsar0AI 评分2020 @omarsar0@omarsar0AI 评分5454 @omarsar0@omarsar0AI 评分2323
@omarsar0@omarsar0AI 评分55 @omarsar0@omarsar0AI 评分6161 
@omarsar0@omarsar0AI 评分3535 微软的一篇超酷论文。 他们证明,无需从前沿模型进行传统知识蒸馏,也能构建出有竞争力的小型编程智能体。https://t.co/fiYxQkGV0A
@omarsar0@omarsar0AI 评分4646 @omarsar0@omarsar0AI 评分2121 
@omarsar0@omarsar0AI 评分2828 
@omarsar0@omarsar0AI 评分3737 @omarsar0@omarsar0AI 评分2929 @omarsar0@omarsar0AI 评分4949 
@omarsar0@omarsar0AI 评分4646 
@omarsar0@omarsar0AI 评分1515 
@omarsar0@omarsar0AI 评分66 @omarsar0@omarsar0AI 评分3838 
@omarsar0@omarsar0AI 评分4545
引用@finkd@finkdIntroducing Muse, the personal agent that understands your goals and works 24/7 to get things done for you.
@omarsar0@omarsar0AI 评分99 借助 AI 在数学领域取得的最新进展,正将我们推入一个无可否认的、令人振奋的新弧线——AI 赋能的科学发现与理解。然而,感觉我们才刚刚触及表面。保持谦逊,保持好奇,专注于最重要的事。
@omarsar0@omarsar0精选AI 评分7272 引用@OpenAI@OpenAIWe’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics. The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra. The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.
推荐理由:转述 OpenAI 关于千禧年数学难题证明的说法,读者可借此了解其下一代模型与智能体协作的定位。
@omarsar0@omarsar0AI 评分4747 
@omarsar0@omarsar0AI 评分33