开启时会模糊预览图，关闭后正常显示
RT @nextjs: Next.js 16.1: Turbopack filesystem caching for 𝚍𝚎𝚟 is now enabled by default. Example field test in an open-source app: 3.7s →…
找工作、找面试题、改简历、模拟面试。关注： 创业（冷启动） ｜ 认知心理学｜智能体 ｜ 强化学习 building：https://t.co/A4YmEz90B8
We know we are even farther from AGI than we were told, when @demishassabis has to publicly disagree with @ylecun as to what the heck it really is anyways.. 🙄#AIAphorisms
AI researcher & teacher @SCAI_ASU. Former President of @RealAAAI; Chair of @AAAS Sec T. Here to tweach #AI. YouTube Ch: https://t.co/4beUPOmf6y Bsky: rao2z
Meanwhile, EU grew 0.3% in Q3. Literally less than a tenth! Whatever Europe is doing, it's not working. But I'm sure some more criminal prosecutions for wrong think online will fix that any minute now!
Father of three, Creator of Ruby on Rails + Omarchy, Co-owner & CTO of 37signals, Shopify director, NYT best-selling author, and Le Mans 24h class-winner.
RT @SawyerMerritt: NEWS: Waymo has just released an official statement following the massive power outage in San Francisco this week and th…
Subscribe https://t.co/Xm1OaUU8jk • seed investing • writing • ॐ •🙏• I use '—' • tweets saved 90 days • 📷
2小时辩论2个案例：AI 智能体要依赖内部知识还是彻底搜索？这没有标准答案，正是「上下文工程」能够成为 AI 模型之上最大价值层的原因！ Aaron Levie 分享了一个实际经历：团队花了2小时讨论一个具体问题——对于某种类型的问题，AI 智能体应该何时依赖自身内置知识直接回答，何时去外部数据中搜索相关上下文。结果只讨论了数百个测试案例中的2个。即使参与 脑暴的人类专家们，也无法完全一致地判断人类在类似情况下会怎么做。这表明，没有绝对正确的答案，一切都高度依赖具体情境，且因客户而异。 Levie 的核心观点是：上下文工程本质上充满权衡。需要同时考虑多个维度，例如： · 智能体回答的速度（越快越好，但可能牺牲准确性）； · 用户需要多少互动来澄清问题； · 智能体在回答前应该做多少前期工作（如搜索数据）； · 如何判断已获取足够全面的源材料； · 错误回答的风险有多高（在高风险场景中，更倾向于彻底搜索）。 这些维度相互影响：优化一个方面，往往会牺牲另一个。没有完美的“免费午餐”。这使得构建可靠的 AI 智能体变得异常复杂和有趣。 最后，他强调，这也突显了「上下文工程」在 LLM 基础层之上的巨大价值空间。正确处理这些权衡决策，直接决定了产品的核心价值和用户体验。
邵猛，中年失业程序员 😂 专注 - Context Engineering, AI Agents. 分享 - AI papers, apps and OSS. ex Microsoft MVP 合作 - 私信/邮箱：shaomeng@outlook.com 📢 公众号/小红书: AI 启蒙小伙伴
RT @staticmaker1: "boring" online testimonial software. fully bootstrapped. built to scratch his own itch. monetization via subscription…
Discovering "boring" businesses at https://t.co/VrB2vWopEc. Sharing "boring" business opportunities at https://t.co/1qQOVZrUXW.