跳到正文

全部动态

今日 122 条
9月18日周五
9月17日周四
  1. Latent Space(RSS)47

    AINews:Yegge 关停 Gas Town,Databricks 用 GPT-6 Astra 后编码支出增 60%

    Steve Yegge 关停了 Gas Town,并承认每月花费数千美元订阅编码智能体,却只做出了 Gas Town 这一个项目。Databricks 向约 3500 名工程师铺开 GPT-6 Astra,其在高复杂度系统设计与长周期任务上"明确"优于 Opus 5 / Sol 5.6,但整体编码支出增加约 60%,公司为此设立专门的 Astra 子预算。

  2. Greg Brockman59

    Greg Brockman 转发 Databricks 工程负责人 Peter Wendell 的推文:Databricks 已将 Astra 部署给全部约 3500 名工程师。引用内容称 Astra 在高度复杂任务(如高层系统设计、长程横向任务)上明显优于此前最高端模型 Opus 5 和 Sol 5.6,使用 Astra 的工程师整体编码支出较基线增加约 60%;中低复杂度任务上提升不明显,疑似已被现有模型饱和。此前通过约 200 名用户的试点验证质量与成本,使用 Unity Gateway 做分组实验,并为 Astra 设置专项子预算鼓励在复杂任务上选择性使用;Astra 与 Fable 尚无可靠对比,因数据保留政策未广泛推出 Fable。

    引用Patrick Wendell@pwendell

    Today we rolled out Astra to every engineer at Databricks (N=~3500). Some notes that may be helpful to others: 1. Astra unambiguously out performs our previous highest-end models (Opus 5, Sol 5.6) on highly complex tasks, especially those related to high level system design or long range horizontal tasks. 2. Engineers given Astra increased overall coding spend by around 60% compared to baseline. 3. It is not clear Astra meaningfully improves on medium/low complexity coding tasks compared to earlier models. We suspect those tasks are mostly saturated (i.e. perfectly executed) by existing models. 4. We learned above by piloting Astra with around 200 users to gain signal on both quality and cost. We use Unity Gateway to do cohort-based experiments for all new models. 5. We give engineers a sub-budget specific to Astra to encourage them to use Astra selectively on complex tasks while preferring lower cost models for everyday tasks. Our engineers are able to mix-and-match tools and models within their overall budget envelope (we also allow for increased budgets through various mechanisms). These budgets are defined in Unity Gateway and regularly revisited. Note: We do not have robust comparisons of Astra-vs-Fable because we have net yet rolled out Fable widely due to data retention policies.

  3. Microsoft:Official Blog(RSS)45

    Microsoft 发布教育 AI 五项原则:与 AFT 达成协议并推出学校隐私与安全标准

    Microsoft 公布教育领域 AI 五项原则,并与美国教师联合会(AFT)签署协议、推出面向学校产品的 Privacy & Safety Standard,限制学生和教师数据使用并要求对重大决策保留人工监督。Microsoft 称这是大型科技公司与美国最大教师工会之一首次共同界定教育产品中可信 AI 的标准,并邀请业界共同遵循。

9月16日周三
  1. Aidan Gomez55

    Cohere 与 Aleph Alpha 宣布签署最终协议合并,成为首家立足大西洋两岸的基础 AI 模型开发商。合并后统一以 Cohere 名义全球运营,员工规模将超过 1000 人,分布欧美两大洲。Cohere CEO Aidan Gomez 转发官方公告表达对合并的期待。

    引用Cohere@cohere

    Cohere and Aleph Alpha announce the signing of a definitive agreement, becoming the first foundational AI model developer anchored on both sides of the Atlantic 🇨🇦🇩🇪 Operating globally as Cohere, the unified company will grow to more than 1,000 employees across both continents.

  2. NVIDIA Blog(RSS)53

    Emerald AI、Google 与 NVIDIA 发起 AI Energy Management Alliance 推动灵活用电数据中心

    Emerald AI、Google 与 NVIDIA 宣布发起 AI Energy Management Alliance(AEMA),推动数据中心根据电网状况动态调整用电。联盟主张技术中立、按性能衡量灵活性,制定并网前的响应义务、统一技术要求和更快并网通道,汇聚 AI 平台、数据中心、电力公司与电网运营商等价值链成员,以提升现有电网容量利用、缩短 AI 设施并网时间。

  3. Latent Space(RSS)60

    Latent Space AINews:TypeSafe 发布决策模型 Jev,同期还有 Periodic Neon 与 Gemini 3.8 Live

    Latent Space AINews 汇编 2026-09-14 至 09-15 的 AI 动态,头条是 TypeSafe 的 Jev:一个用 RLCD 训练、只做分类/路由/打分的非自回归决策模型,宣称比小型前沿 LLM 快 20–200 倍、便宜 40–400 倍且输出 token 免费,社区提醒它不能生成自由文本、更接近结构化选择的低成本推理引擎。

  4. SemiAnalysis 长文 RSS(RSS)67

    SemiAnalysis 反驳数据中心暂停令正在扼杀美国建设潮的说法

    SemiAnalysis 分析认为数据中心暂停令严重拖慢美国建设的说法不准确。其模型预测 2027 年美国新增 38GW IT 容量,是 2026 年的两倍以上;约 300 个地方暂停令中实际被直接延迟的容量仅约 2.3GW,其中纽约州约 0.8GW、地方限制约 1,525MW,主要由俄亥俄 AWS 园区等三个项目构成。

  5. Fei-Fei Li32

    机器人学习的研究人员/工程师加入 @theworldlabs 的绝佳机会!❤️‍🔥

    引用Yunzhu Li@YunzhuLiYZ

    We're hiring in robot learning at @theworldlabs! Join me, @drfeifei, and the team to define and scale the next generation of world models for robot learning! Atlas for Robotics: https://www.worldlabs.ai/blog/atlas#robotics-simulation Real-to-Sim-to-Real: https://www.worldlabs.ai/blog/real-to-sim-to-real Apply: https://jobs.ashbyhq.com/worldlabs/85994fa5-c44c-48b4-84fc-aece7934c2cb

  6. NVIDIA Technical Blog(开发者技术博客 · RSS)21

    NVIDIA Groq 3 LPX 的确定性执行如何在 NVIDIA Vera Rubin 上驱动高能效高交互推理

    NVIDIA Groq 3 LPX 通过确定性执行,在 NVIDIA Vera Rubin 平台上实现高交互推理的能效提升。该方案针对 AI 工厂的功耗约束,以每瓦性能而非原始吞吐量作为衡量 AI 平台价值的核心指标。Vera Rubin 平台正是为在有限功耗预算内最大化输出而设计。

9月15日周二
  1. NVIDIA Blog(RSS)42

    费城儿童医院如何用开源 NVIDIA AI 实现儿童心脏建模与手术模拟

    费城儿童医院(CHOP)基于开源医学影像框架 MONAI 构建心脏建模服务,将原本需 4 小时的建模流程缩短至数秒,并已用于复杂心室间隔缺损手术规划。全美超 20 家儿童医院开展心脏建模项目,波士顿儿童医院建模支持其过半心脏手术、约每年 500 例,CHOP 今年预计完成约 200 例。

  2. Josh Woodward26

    来和我们一起做设计! (引用推文核心要点:Fast Company 将 Google 评为 2026 年 Innovation by Design Awards 获奖者,表彰其整体设计愿景和全新 AI 设计语言,涵盖 Gemini App、Google Maps 沉浸式导航和 Search AI Mode 等产品。)

    引用News from Google@NewsFromGoogle

    Today @FastCompany awarded @Google the winner of their 2026 Innovation by Design Awards for our holistic design vision and new AI design language, seen across our products, from @GeminiApp to @GoogleMaps' Immersive Navigation and Search AI Mode. Read the full story. https://www.fastcompany.com/91589966/google-innovation-by-design-2026

  3. Mira Murati45

    我们正在构建机器智能,以扩展人类的意志与判断力。很高兴你能加入团队,帮助我们探索如何让这一未来变得安全。

    引用Neil Chowdhury@ChowdhuryNeil

    I’ve joined @thinkymachines to work on safety & alignment. The default trajectory is that as AI gets more powerful, control over it will concentrate in the hands of a few. I’d rather build safety systems that let control over AI be shared widely. Longer thoughts below.

9月14日周一
  1. MiniMax Design (H3)15

    最后召集 📢💥 释放你的怪兽,把大奖带回家👹💰

    引用Miora Design@Miora_Design

    Final call. Bestiary closes tonight, Sep 14 at 23:59 (PT). ⏳ $8,000 cash, 200,000 Credits, and ten Audience Choice awards are still on the table — and they go to the people who actually hit submit. One strange, beautiful short film, 30 seconds or longer, generated with MiniMax H3. Any myth, any era, any world you can dream up. The bestiary doesn't close itself. Finish your film before the clock runs out.