搜索“Agent”

ect called hw-harness under an MIT license. It bundles the tooling for capturing how a device behaves, comparing a working implementation against a broken one, and giving a coding agent the information it needs to work on hardware that Linux doesn’t support yet. Reverse-engineering the scanner driver Schaller got the idea from a post on X by Tom Crider, better known as Glorious Eggroll, who had used an AI agent to fix a mouse driver by giving it access to a Windows machine. Schaller fed the post

匹配字段正文

理写进SOP，比临场协调便宜得多。 四、收益与迁移 两个硬指标：原本D0-D7跨两周的备课闭环，9月上旬实测单日上午跑通全流程（正常学期节奏仍建议留两周，给主备思考时间和研讨组织时间）；共识执行率从"经常烂尾"变成100%——三要素约束下，每条共识都有人和截止日期。 更重要的收益是结构性的：质检标准从"上交任务"变成了"改进导航"——9个智能体的评分不再是考核，而是下一轮迭代的输入。 这套框架的迁移成本很低：四阶段九智能体SOP跨学科通用，换学科只改依据体系里对应学科的本体理论一条；提示词四件套不绑定任何平台，豆包、Kimi、ChatGPT、DeepSeek都能跑。我们整理了一页纸入门包（总览+6步闭环+依据体系三份文件），其他备课组复制后跑一个单元就能上手。 --- 写在最后：我不是程序员，这套东西的全部"技术含量"就是四份提示词文档和一张轮值表。多Agent编排听起来高深，拆开了看就是两件事：把标准动作写成强约束的提示词，把人的判断留给对辩和拍板。AI管结构，人管方向——教学如此，编排也如此。 版权声明：本文作者库致堂。转载请注明出处。 文中人物均为化名，单位信息已按匿名规则处理。

匹配字段正文

a launched Muse Wonder on October 12, about three months after Muse Spark 1.1 opened Meta’s paid Model API. Meta says the Muse Wonder series is strong at personal and professional agent tasks, tops its internal MemoryBench memory test, and, in the Full version, leads coding benchmarks such as DeepSWE and SWE-Marathon. Its model card lists Fable 5.1 among the comparison models, and Meta’s launch post publishes Fable 5.1 scores alongside its own. Those are strong claims, since Fable 5.1 is one of

匹配字段正文

Every growing codebase needs maintenance: unused code to remove, completed experiments to clean up, and tests to fix. At OpenAI, coding agents have helped us build faster, which has also increased our maintenance needs. I work on OpenAI’s Core Experimentation team, where we build and maintain the software that supports experiments across the company, from front-end updates to improvements in model-serving efficiency. The release of GPT-6 Astra helped us build and maintain software faster, and GP

匹配字段正文

pstack 作者公开她的 “工程原则” 设计思路 「Clean Code」作者 Uncle Bob 是传统软件工程方法论的宗师，他最近看到了 pstack，认为本质上是把经典工程智慧「最小改动、先删后加、验证根因、用类型系统让非法状态不可表示、幂等操作」重新编码给 AI Agent 使用。 pstack 作者 @poteto 回应并公开了这个 Cursor 官方内置插件的工程原则的设计思路，核心是：随着模型能力提升，写给智能体的指令正在从“冗长的操作步骤”压缩为“简短的命名原则”。 几个关键信息点 1. 原则即极简 skill。pstack 的每条工程原则只有约 10–20 行，是一段被提炼、命名过的好实践，而不是一个流程脚本。她预期随着模型变强，pstack 里大部分 skill 最终都会被压缩成这样的短原则或工作流，从而可以删掉一批。 2. /poteto-mode 的运行机制。智能体在开始多步任务前先读一份简短的原则索引；执行过程中，必须“点名每一条影响了决策的原则，以及它具体改变了哪个选择”，并在回复末尾生成一个 "Principles Named or Used" 段落。这

匹配字段正文

p, Forum, is for anyone who wants to go deeper into the conversations in their Facebook groups. To build Forum, Meta engineers adopted a whole new way of working by bringing an AI agent into the development cycle. We’re sharing insights into what it took to build Forum with agentic AI: how we adapted the codebase, tested frameworks and internal tooling for agentic execution, what worked, and what didn’t. Forum is a standalone Groups app that a small team built from scratch. It’s also where we te

匹配字段正文

xt and generating 128 tokens is performed with the command line: mlx lm.benchmark --model Qwen/Qwen3.8-27B -p 8192 -g 128 -b 1 A popular use of local LLMs on Mac Studio is running agentic experiences in a private environment, including agentic coding applications that often need large contexts. We therefore report performance at both 8,192 and 65,536 context sizes. Raw TTFT and decode throughput are reported in Table 2 and Table 3, respectively. Qwen 3.8 27B and Mistral Medium 3.5 128B fit comfo

匹配字段正文

and mathematicians under the tower's first platform, 18 on each side. Claude Opus 5.5 and Grok 4.7 wrote all 72, with each side in the real order. Claude Opus 5.5 also put each set on the side that faces the same way in Paris. Each model built its scene as an agent in a sandbox with no internet access. In both runs, the names first appear in code the model wrote, never in a file or tool output it read. Congratulations to @spacexai, @elonmusk and @AnthropicAI on two seriously knowledgeable models

匹配字段正文

What happens when you give an AI support agent a permission it never needed, then assign it a task the underlying data does not support? The result is entirely predictable. During a test with customer invoices, an agent pulled up a record, confirmed the charge had failed, and no money had left the customer’s account, and refunded it anyway. It repeated the mistake five times without hesitation. That was Claude Haiku 4.5 going six for six on tasks designed to catch that exact logic flaw. Claude S

匹配字段正文

EngineeringHow the Claude Code team does code review How do you review code at the volume agents produce it? On the Claude Code team, once we had high coverage and deep reviews, we started optimizing for the minimum amount of human review time that doesn't raise reverts or incidents.AUTHORAddy Osmani, Morgan Westlee Lunt, and Qing WangPUBLISHEDOct 15, 2026READING TIME14 min We've said before that Claude writes about 90 percent of Claude Code's own code. So how do we review code at the volume we

匹配字段正文

xins. The other risk comes from well-resourced organisations and nation states that have plenty of skilled scientists, high containment laboratories and all of the equipment and reagents needed to work on bioweapons safely. AI tools could help researchers identify genetic tweaks to make existing pathogens more lethal, for example. This is the more immediate concern, according to Dr Filippa Lentzos, a reader in science and international security at King’s College London. “Here, AI does not remove

匹配字段正文

了原理，最后我们看看在Harness框架搭建中，有哪些可以利用Jev进行优化、提速的点。 这里我们抛砖引玉，给大家几种在harness中可以使用Jev进行效率优化的方向，部分场景还未验证，哈哈毕竟AI写代码太快但是很多场景验证比较复杂。有些指令较长，感兴趣的可以直接看代码jevharnesstool 选择类：Skill Search 这里使用用户query和agent所有候选技能作为输入，判断解决用户问题是否需要使用技能，如果需要应该使用哪个技能。 类似的思路也可以用在mcp search、effort routing、memory search等等。不过model routing在我的使用场景中往往效率提升不明显但质量下降明显，或者推理速度快很多但任务完成速度提升不明显，对场景复杂度的评估需要更全面的上文，所以实现很简单，但效果很难评。 围栏类：LLM Guardrail 拦截用户的各类风险输入和prompt注入，这里提供了9种基础的风险类型，每种风险可以提供不同的处置方案block、review etc。 类似的思路也可以用于模型输出检查、tool call检查etc。 校验类：r

匹配字段正文

utes and scored just 21% (versus 81% to 85% for GPT-6 Astra, Fable 5.1, Sonnet 5.5, and Opus 5.5). Not great. A 2026 model trapped in a 2025 harness. Antigravity, Google’s desktop agent app, feels six months to a year behind Claude Code and Codex—lacking cloud environments, SSH, a built-in browser, and smart permission checks (leaving you clicking constant pop-ups or using unrestricted "Turbo" mode). Net Result: I keep ChatGPT and Claude open day to day, and switch to Gemini 4 when I need an edi

匹配字段正文

erall, Gemini 4 is a big jump over previous Gemini models and it is the first non-OpenAI/Anthropic model to pass the Fable/Mythos/Astra bar. It is also much more pleasant and more agentic then previous Gemini models, without the weird personality issues that you often found in Gemini 3 series models. In fact, a big advantage is that has a very different personality and sense of taste than Claude or Astra, making it a good addition to the AI world. On the usefulness side, in some areas it is at l

匹配字段正文

New on our Engineering blog: Creating in-house source control. In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale. Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: https://t.co/wzNkwHs7IN

匹配字段正文

s, the RapidsUDF interface with the Java API for cuDF, or custom CUDA kernels via JNI to eliminate fallback and achieve over 20x speedups; The cuDF skills for Apache Spark provide agent-driven workflows that guide testing, conversion, benchmarking, and optimization with verification-driven feedback loops; A major consumer technology company converted more than 30 production UDFs using this workflow, with one rewrite reducing operator time from 274.55 to 12.78 hours across a 600-billion-row workl

匹配字段正文

tierCode in June 2026 and updated it to version 1.1 in July. Cognition built the dataset with open source maintainers who spent more than 40 hours per task. Each task requires the agent to make a change to a real open source repository, then checks both unit tests and qualitative tests for what maintainers would require to merge the change. We run FrontierCode 1.1 Main, the primary 100-task set of the benchmark's 150 tasks, using our Stirrup open source reference harness for apples-to-apples com

匹配字段正文

We have measured intelligence. Now it's time to see it. We are launching AA-3D, our new benchmark for how well AI models build interactive 3D scenes. Each model works as an agent in an offline sandbox and turns a written brief into a three.js web page. A human panel of judges compares pairs of scenes built from the same brief without knowing which model made which. AA-3D details: ➤ 55 written briefs across seven domains, including landmarks, machines, living bodies, games, and space. Each brief

匹配字段正文

gh these optimizations, we convert KVCache capacity expansion into longer effective hit lengths, making cross-session long-prefix reuse possible — particularly beneficial for long agent sessions, multi-user shared system prompts, and repeated tool calls to the same codebase. 2.2 GCache: High-Performance Distributed Cache Infrastructure GCache is a high-performance general-purpose cache system developed by the Xiaomi storage team, forming a critical part of unified training-inference storage arch

匹配字段正文

文/VR陀螺 10月13日，阿里巴巴旗下千问正式发布三款智能穿戴新品，包括千问AI眼镜N1、N1 Pro以及千问AI耳夹式耳机。新品重点围绕影像拍摄、眼动交互、健康监测、实时翻译及AI主动服务等功能展开，进一步拓展Personal Agent在日常生活中的应用场景。 目前，三款新品已在淘宝、天猫、京东及抖音等电商平台现货开售。叠加国家补贴及限时优惠后，AI眼镜到手价2218元起，AI耳机到手价1099元起。 AI眼镜方面，N1系列包含N1和N1 Pro两款产品，均支持影像拍摄、翻译及语音AI交互。其中，N1 Pro进一步加入眼动追踪、虹膜识别及体征监测等功能，强化设备对用户状态及现实环境的感知能力。 VR陀螺也对千问N1 Pro进行了深度体验，重点围绕健康监测、眼动交互及AI主动服务等核心能力展开实测。当AI眼镜开始尝试感知用户的身体状态，这些功能究竟能带来怎样的实际体验？更多细节，详见VR陀螺评测视频： 据了解，N1 Pro是行业首款具备实时体征监测功能的AI眼镜，支持心率、血氧、皮肤温度等多项体征数据的实时监测，并通过AI生成健康洞察报告，将相关数据转化为更易理解的信息。例如，在骑

匹配字段正文