Topic · 主题全部主题 →

AI 编码

AI 写代码的一切：编码助手、Vibe Coding、代码模型评测与开发工作流变革。

5,065条收录
583条精选

精选归档 · 第 8 页

第 141–160 条 · 共 583 条

7月4日7月4日周六

星期六 · 3 条
03:44
Hacker News 热门（buzzing.cc 中文翻译）精选
AI 评分 83/100
pxpipe：通过图像化压缩输入token降低Claude Code成本

pxpipe是一个本地代理，将系统提示、工具文档和历史记录等密集文本渲染为PNG图像，利用图像token成本取决于像素尺寸的特性压缩输入token。在Fable 5模型上，约25k文本token压缩为约2.7k图像token，端到端账单降低59–70%。SWE-bench Lite 10个实例全部通过，成本从$54降至$27；SWE-bench Pro 19对测试中18对判定一致，单次请求成本降低约60%。该方法有损（精确ID等需保持文本），默认仅处理claude-fable-5请求，可通过PXPIPE_MODELS变量控制。

GitHub开源/仓库编码
推荐理由：pxpipe 通过把大量上下文渲染成图像来降低 token 开销，实测能削减 60-70% 的账单，对重度使用 Claude Code 的开发者很诱人，但它有损，精确值可能读错，适合容错高的编码场景。
03:22
Simon Willison 博客精选
AI 评分 73/100
Fable 的判断力：Simon Willison 从 Claude Code 团队获得的效率技巧

Simon Willison 在 AIE 上与 Claude Code 团队交流后建议，让 Fable（以及 Opus）用自己的判断力工作，而非硬性规定行为。例如，直接让 Fable 自行决定何时编写测试，比给出具体规则更好。为应对价格即将上涨、节省 Fable token，Jesse Vincent 的另一个技巧是告诉 Fable 将较小任务委托给较低功耗模型（Sonnet 用于实质性实现、Haiku 用于机械修改），主循环保留判断、审计和数据合成等任务。Willison 已将提示词存入 Claude Code 记忆文件，实际效果良好，Fable token 消耗速度明显下降。

智能体Anthropic教程/实践编码
推荐理由：Simon 从 Claude Code 团队得到的实战技巧：别硬性规定 Fable 怎么写测试、用哪个模型，让它自己判断。他实测这条 prompt 能明显节省代币消耗，Fable 涨价前偷时间的利器。
02:11
Thariq@trq212精选
AI 评分 69/100
Fable使用指南：发现你的未知http://x.com/i/article/2073090223194755072A Field Guide to Fable: Finding Your UnknownsWorking with Claude Fable 5 keeps re-teaching me an old lesson: the map is not the territory.The map, a representation of the work to be done, is my prompts and skills and context, it’s what I give Claude. The territory is where the work needs to happen, the codebase, the real world, its actual constraints.The difference between the map and the territory is what I call unknowns. When Claude runs into an unknown, it needs to make a decision based on its best guess of what I want. The more work being done, the more unknowns Claude might run intoFable is the first model where I find the quality of the work is bottlenecked by my ability to clarify its unknowns.Importantly, just planning ahead isn’t always enough. You can find unknowns deep in implementation, or your unknowns may point you to the fact that you should actually be solving the problem in a different way altogether.I’ve found that working with Fable is an iterative process of discovering my unknowns before, during, and after implementation.I've made some example artifacts for finding unknowns here, but be sure to come back to build the intuition for when to use them.Knowing your unknownsWhat are your unknowns? When I come to Claude with a problem I tend to break it down in 4 ways:• Known Knowns: This is essentially what is in my prompt. What do I tell the agent that I want?• Known Unknowns: What haven't I figured out yet, but I’m aware that I haven’t?• Unknown Knowns: What's so obvious I’d never write it down, but would recognize it if I saw it?• Unknown Unknowns: What haven't I considered at all? What knowledge am I not aware of? Do I know how good something can be?The best agentic coders are good have relatively few unknowns. Watching someone like Boris or Jarred prompt, it is obvious to me that they know what they want in-detail. They are deeply in-sync with both the codebase and the model behaviors.But they also assume unknowns. In many ways, reducing and planning for your unknowns is the skill of agentic coding. But luckily, this is a skill you can improve at, by working with Claude.Help Claude help youInstructing Claude is a delicate balance. If you are too specific, Claude will follow your instructions even when a pivot may be more appropriate. If you are too vague, Claude will often make choices and assumptions based on industry best practices that may not be a fit for your task.When you don’t account for your unknowns you fail both ways. You don't know when the path will be filled with obstacles and you don’t know when the path will be clear, but you still want Claude to veer.Claude can help you discover your unknowns faster. It can search through your codebase and the internet extremely quickly and it knows much more about the average topic than you. It can also iterate from failure faster.The most important part of this process is to give Claude context about your starting point. For example, tell it where you are in your thought process; disclose your experience with the problem and codebase; and let it work with you like a thought partner.I've previously written about using HTML with Claude, in almost all of these cases, a HTML artifact is the best way to visualize and represent it.In this article I detail some of the patterns I use to uncover these unknowns. I don't use every technique each time, but it's a useful collection of techniques to have.Pre-implementationBlind Spot PassWhen starting work, one of the most useful things you can do is understand your blindspots. For example, if you’re writing a feature in a new part of the codebase or using Claude to help you with unfamiliar work like iterating on a design, you’re likely to have a lot of unknown unknowns.You may not know what questions to ask, what good looks like, what historical work has been done or what potholes to avoid.To do this, you can ask Claude to help you find your unknown unknowns and explain them to you. I like to use the literal words “blindspot pass” and “unknown unknowns”. Giving it context on who you are and what you know is usually important forExample Prompts:• “I'm working on adding a new auth provider but I know nothing about the auth modules in this codebase. Can you do a blindspot pass to help me figure out my relevant unknown unknowns and help me prompt you better.”• “I don’t know what color grading is but I need to grade this video. Can you teach me to understand my unknown unknowns about color grading, so that I can prompt better?”Brainstorms and prototypesWhen I’m working in an area with a lot of unknown knowns, involving criteria I only know to define when I see it, I like to ask Claude to brainstorm and prototype with me.It’s extremely valuable to identify and verbalize unknown knowns early during prototyping, because finding them out during implementation can be (relatively) expensive. Small changes in a feature or spec can cause drastically different implementations in code and it can be more difficult for your agent to revert previous changes.For example, you may just want to see how a button added to a frame looks without having to wire up a backend route or maintaining additional state in the frontend.Visual design is something that for me is difficult to articulate, but I know what I want when I see it. In these cases, I’ll ask for several design approaches to an artifact.I also start almost every coding session with an exploration or brainstorming phase. This helps me start with intent to define the project’s scope. Claude often finds high-value approaches I would have missed and sometimes misses the forest through the trees. Brainstorming prevents me from setting too narrow or too wide a scope.Example prompts:• "I want a dashboard for this data but I have no visual taste and don't know what's possible. Make me an HTML page with 4 wildly different design directions so I can react to them.”• “Before wiring anything up, make a single HTML file mocking the new editor toolbar with fake data. I want to react to the layout before you touch the treal app."• "Here's my rough problem: users churn after onboarding. Search the codebase and brainstorm 10 places we could intervene, from cheapest to most ambitious. I'll tell you which ones resonate."InterviewsOnce I’ve done sufficient brainstorming, I likely still have unknowns.In this case, I ask Claude to interview me about any unknowns or ambiguities. When asking Claude to interview you, try and give it context about your problem to guide its questions. Here are some examples.Example prompts:• "Interview me one question at a time about anything ambiguous, prioritize questions where my answer would change the architecture."ReferencesSometimes you can’t describe what you want in detail. For example, you might not have the language or it might be so complicated that it would take you quite a while.In this case, the best answer is a reference. While you can include diagrams, documentation or pictures, the absolute best reference is source code.If you have a library that implements something in a certain way or a design component you really like, just point Fable at the folder and tell it what to look for, even if it’s in a different language.This is also the way Claude Design works. You don't have to hand it a file (although you can do that too). You can point it at a module on a website you like, and it reads the underlying code, not just the screenshot. This provides much richer detail around the markup, structure, and how the component is actually built.Example prompts:• This Rust crate in vendor/rate-limiter implements the exact backoff behavior I want. Read it and reimplement the same semantics in our TypeScript API client.Implementation PlansWhen I think I’m ready to implement, I tend to ask Claude to put together an implementation plan for me to review that focuses on the parts that might be most likely to change, for example to review data models, type interfaces or UX flows. This allows Claude to surface things I might actually need to alter.Example Prompts:• Write an implementation plan in HTML, but lead with the decisions I'm most likely to tweak with: data model changes, new type interfaces, and anything user-facing. Bury the mechanical refactoring at the bottom, I trust you on that part."During implementationImplementation notesOnce I am satisfied with my plan, I make a new session and pass any artifacts to the prompt. For example, I might pass in a spec file and a prototype and ask an agent to implement it.But the truth is that no matter how much planning you do, there are always unknown unknowns lurking. The agent may find during its work that it needs to take a different tack due to an edge case it found in the code.I ask Claude Code to keep a temporary ‘implementation-notes.md’ (or .html) file where it keeps track of decisions it makes so we can learn from our next attempt.Example prompts:• "Keep an implementation-notes.md file. If you hit an edge case that forces you to deviate from the plan, pick the conservative option, log it under 'Deviations', and keep going."Post implementationPitches and explainersOne of the most important parts of shipping something is getting buy-in and approvals. Building pitch and explainer artifacts in the final document helps:• Accelerate understanding when reviewers start with the same unknowns you did• Accelerate approvals when experts want to see you accounted for the unknowns and common failure points they would have anticipatedExample prompts:• "Package the prototype, the spec, and the implementation notes into a single doc I can drop in Slack to get buy-in. Lead with the demo GIF."QuizzesAfter a long working session, Claude might have accomplished a lot more than I realized. Reading the code diffs can only give me a light understanding of what happened, since much of the behavior will depend on existing code paths.Asking Claude to quiz me about the change after giving me a bunch of context helps me understand what happens. I only merge after I pass the quiz perfectly.Example prompts:• “I want to make sure I understand everything that's happened in this change. Give me a HTML report on the changes for me to read and understand with context, intuition, what was done, etc. and a quiz at the bottom on the changes that I must pass.”How this comes together: launching FableThe launch video for Fable was edited entirely by Claude Code. This was a new domain for me and I’m by no means an expert.So I started with what I did know. I knew that Claude could use code to edit videos and transcribe them, but I wasn’t sure if it was accurate enough. I then asked Claude to explain to me how transcription like Whisper worked, and whether I would be able to accurately cut out things like ums or large pauses using ffmpeg.I wanted Claude to create a UI that was timed with the words I was saying, but wasn’t sure if it would be able to so I asked Claude to create a prototype video using Remotion and a transcription to see if it would work.Finally, the video itself looked a bit muted, which I knew was the result of color grading but I didn’t really know what color grading was. My first pass attempt was to try and get Claude to do a few variations to pick, but I realized that I didn’t know what “good” looked like when it came to color grading. So instead, I asked Claude to teach me about color grading to discover my unknowns.You can watch a more in-depth explanation on that here.Matching the Map and TerritoryThe better models get, the more you can achieve with the right approach. When a long-horizon task comes back wrong, it's likely you need to spend more time defining your unknowns or creating an implementation plan that allows for Claude to improvise through them.Every explainer, brainstorm, interview, prototype, and reference is a cheap way to find out what you didn't know before it gets expensive to fix.So start your next project by asking Claude to help you find your unknowns.译作者分享与Claude Fable的协作经验，指出"地图≠领土"：提示词与上下文（地图）与实际代码库和约束（领土）之间存在未知。他将未知分为四象限：已知-已知、已知-未知、未知-已知、未知-未知。顶级智能体程序员善于减少未知并预设预案。Fable是首个模型，其工作质量受限于用户澄清未知的能力。Claude可通过快速搜索代码库和互联网、从失败中迭代，帮用户定位未知。具体技巧包括实施前的"盲点检查"及迭代优化；避免指令过于具体或模糊，应让Claude协助发现未知。
智能体Anthropic教程/实践编码
推荐理由：Thariq 总结了一套与 Claude Fable 5 协作时发现「未知的未知」的方法论，从盲点扫描到事后测验，对想用好代理编码的开发者有实操价值。

7月3日7月3日周五

星期五 · 3 条
18:14
Hacker News 热门（buzzing.cc 中文翻译）精选
AI 评分 72/100
面向 Web 开发者的 Safari MCP 服务器

Safari Technology Preview 247 推出 Safari MCP 服务器，基于 Model Context Protocol，允许任何 MCP 兼容客户端连接 Safari 浏览器窗口。智能体可获取 DOM、网络请求、截图、控制台输出等信息，自主完成调试、性能分析、可访问性检查等任务。内置 browser_console_messages、screenshot、evaluate_javascript、list_network_requests 等工具。开发者安装后启用“远程自动化与外部智能体”选项，即可通过命令接入，减少窗口切换。

MCP/工具产品更新编码
推荐理由：Safari 首次以官方身份推出 MCP 服务器，让 AI 编程助手能直接调试浏览器渲染，对前端开发者做兼容性测试和性能检查很实用，不过局限在 Safari 生态。
14:44
Hacker News 热门（buzzing.cc 中文翻译）精选
AI 评分 70/100
《Fable》通关指南：短绳AI编程法

专业开发者经过一年多研究，总结出使用AI编码代理的“短绳方法”。该方法要求开发者全程参与：先规划并分解任务，从不使用YOLO模式，每次变更前审查差异并拒绝不想要的更改，每个子任务后提交以防止AI误操作（如Opus曾出现破坏性行为）。最终需进行人工与AI双重PR审查，PR须注明使用模型，提交者须亲自审查自己PR的代码。即便不用前沿模型，此法也能产出超越Fable 5的代码质量。

智能体教程/实践编码
推荐理由：这篇是资深安全开发者一年的实战总结，提出的「短绳法」把AI代理栓紧，不是让开发者当甩手掌柜，而是逼你逐行审查，对代码质量死磕到底，比那些鼓吹全自动的大路货更有实操价值。
01:39
LangChain：Blog（RSS）精选
AI 评分 64/100
OpenWiki：为编码智能体生成并维护开源仓库文档

LangChain 推出 OpenWiki，一个为编码智能体自动生成和维护代码库文档的开源工具。它让智能体能直接检索所需的仓库上下文，无需将所有内容加载到单个指令文件中。

产品更新开源生态编码
推荐理由：LangChain 开源的这个文档生成代理解决了编码代理上下文管理的一个痛点，对重度使用 agent 做开发的团队很实用。

7月2日7月2日周四

星期四 · 5 条
19:14
Hacker News 热门（buzzing.cc 中文翻译）精选
AI 评分 71/100
Senior SWE-Bench：评估AI智能体作为高级工程师的基准测试

Senior SWE-Bench是一个开源基准测试，用于评估AI智能体完成高级软件工程师级别任务的能力。任务分功能开发与Bug修复两类：功能任务指令类似自然语言消息，采用验证智能体基于专家配方自动生成行为测试；Bug任务要求根据日志、profiling等运行时信息深入调查。排行榜显示，Claude Opus 4.8搭配Mini-SWE-Agent（max effort）通过率24.0%，Claude Sonnet 5为19.4%，GPT-5.5为16.0%，最强前沿模型在超75%任务中未能达到高级工程师级别的正确性与品味。每个功能任务平均涉及11个文件，最强智能体也需数百步完成；中位指令长度仅为SWE-Bench Pro的31%。任务来源于从库到多服务应用的仓库PR，由拥有数百次提交的工程师编写。

开源/仓库编码评测/基准
推荐理由：这个新基准把 AI 编程代理的评估拉到了更真实的复杂度，顶尖模型也只有不到四分之一的成功率，做 coding agent 的都该拿它测一测，它会比 SWE-bench 更挑出工程师的“手感”。
16:40
Hacker News 热门（buzzing.cc 中文翻译）精选
AI 评分 71/100
Kimi K2.7 Code 已在 GitHub Copilot 上正式发布

Kimi K2.7 Code 开源权重模型已在 GitHub Copilot 中正式可用，成为 Copilot 模型选择器首个可选的开源权重模型，为编程工作流提供更低成本选择。该模型由 GitHub 托管于 Microsoft Azure，按供应商列表价格以用量计费。逐步向 Copilot Pro、Pro+ 和 Max 计划用户推送，用户可在 Visual Studio Code 1.127.0 或更新版本、Visual Studio 17.14.6 或更新版本、JetBrains 1.9.1-251 或更新版本、Xcode、Eclipse 等 IDE 及 Copilot CLI、GitHub.com、GitHub Mobile 等平台中选用。后续几周将扩展至 Copilot Business 和 Enterprise，当前默认关闭，需管理员在 Copilot 设置中启用策略。

GitHub产品更新开源生态编码
另有 1 家信源报道IT之家（RSS）
推荐理由：GitHub Copilot 首次把开源权重模型放进模型选择器，Kimi K2.7 Code 作为低价选项可能会改变很多开发者的使用习惯，对个人开发者尤其友好。
10:32
腾讯混元：Research（API）精选
AI 评分 69/100
腾讯混元正式发布Hy3模型

腾讯混元于7月6日正式发布Hy3模型。相比preview版，任务解决率从72%升至90%，平均耗时缩短34%；幻觉率从12.5%降至5.4%，常识错误率从25.4%降至12.7%，多轮问题率从17.4%降至7.9%，长对话基准MRCR从42.9%升至75.1%。在270位专家盲测中均分2.67/4，优于GLM5.1的2.51/4。API价格为输入1元/百万tokens、输出4元、缓存命中0.25元。模型已基于Apache 2.0协议开源。

智能体开源/仓库模型发布编码
推荐理由：腾讯混元重建后的正式版，幻觉率砍半，工具调用稳定性大幅提升，内部盲测压过GLM5.1。做Agent和内部工具的团队值得重新评估这个高性价比选项。
04:49
Claude Code：GitHub Releases（RSS）精选
AI 评分 64/100
Claude Code v2.1.198 发布

Claude Code v2.1.198 更新。Claude in Chrome 现已全面可用。为 claude agents 新增后台智能体通知（agent_needs_input / agent_completed）。新增 /dataviz 技能，提供图表与仪表盘设计指导及配色验证器。Gateway 增加 AWS 上的 Claude Platform 作为上游提供商。后台智能体在 worktree 中完成代码后自动提交、推送并创建草稿 PR。内置 Explore 智能体现继承主会话模型（上限 opus）。修复网络短暂断开导致响应中断、后台任务卡在“Running”状态、智能体团队队友因 API 错误失败等问题。

智能体Anthropic产品更新编码
推荐理由：如果你是Claude Code用户，这次更新很实在，Chrome版终于正式可用，背景agent的自动提PR和通知功能能省不少事，/dataviz也能辅助可视化。
00:07
Z.ai@Zai_org精选
AI 评分 67/100
智谱推出GLM-5.2官方开发环境ZCodeIntroducing ZCode, the official development environment for GLM-5.2• GLM Coding Plan subscribers: now 1.5x usage quota in ZCode • BYOK supported: works with your existing subscriptions and APIs • Available on macOS, Windows, and LinuxDownload now: http://zcode.z.ai/en译推出 ZCode，GLM-5.2 的官方开发环境 • GLM Coding Plan 订阅用户：现可在 ZCode 获得 1.5 倍使用配额 • 支持 BYOK：可与您现有的订阅和 API 配合使用 • 适用于 macOS、Windows 和 Linux 立即下载：http://zcode.z.ai/en
产品更新编码
推荐理由：智谱为 GLM-5.2 推出官方 IDE，1.5 倍配额和自带密钥对已有订阅的人挺实用，但整体只是常规产品完善，算不上行业级事件。

7月1日7月1日周三

星期三 · 6 条
10:24
公众号：龙猫LongCat（美团）精选
AI 评分 78/100
美团发布 LongCat-2.0：五万卡国产算力集群训练与推理的万亿参数开源模型

美团6月30日发布并开源万亿参数大模型 LongCat-2.0，总参数1.6T、平均激活约48B，为业界首个在五万卡国产算力集群上完成全流程训练与推理的模型，原生支持1M超长上下文。

智能体开源/仓库推理模型发布
另有 1 家信源报道公众号：龙猫LongCat（美团）
推荐理由：在五万卡国产算力集群上稳定训练万亿参数 MoE 并达到前沿编程能力的工程实践，为算力受限场景下的模型架构设计提供了可参照的技术路线。
02:48
Claude Code：GitHub Releases（RSS）精选
AI 评分 81/100
Claude Code v2.1.197 发布：默认模型升级为 Claude Sonnet 5，支持原生 1M-token 上下文窗口

Claude Code v2.1.197 更新将 Claude Sonnet 5 设为默认模型，原生支持 1M-token 上下文窗口。该版本提供促销定价，输入 $2/M tokens、输出 $10/M tokens，持续至 8 月 31 日。用户更新至 v2.1.197 即可启用。

Anthropic模型发布编码
推荐理由：Sonnet 5 把中端模型的上下文干到 1M token，促销价让 Claude Code 性价比突然很能打，用 Claude 写代码的可以无脑升了。
02:27
OpenRouter@OpenRouter精选
AI 评分 73/100
Claude Sonnet 5上架OpenRouter，促销价$2/$10 per MClaude Sonnet 5 is rolling out on OpenRouter with a promo price: $2/M in and $10/M out!It boosts agentic coding and pro workflows w/ flagship intelligence at Sonnet pricing. In early tests, agents were more reliable, faster, and easier to trust with larger tasks than 4.6.译Claude Sonnet 5 正在 OpenRouter 上推出，促销价格：$2/M 输入，$10/M 输出！它以 Sonnet 定价提供旗舰智能，提升智能体编码和专业工作流。在早期测试中，智能体比 4.6 更可靠、更快，且更容易信任处理更大的任务。
智能体Anthropic模型发布编码
另有 2 家信源报道X：Rohan Paul (@rohanpaul_ai)Simon Willison 博客
推荐理由：Anthropic 把旗舰智能放进 Sonnet 定价，代理编码的可靠性明显提升，这个早期信号对做 AI 产品的团队意味着成本与性能需要重新计算。
02:02
Anthropic：Newsroom（网页）精选
AI 评分 81/100
Claude Sonnet 5 发布

Claude Sonnet 5 是 Anthropic 推出的最新 Sonnet 模型，具备计划、浏览器和终端工具使用能力，可自主运行。性能接近 Opus 4.8，定价更低：即日起至 2026 年 8 月 31 日，输入 token $2/百万，输出 $10/百万，之后恢复为 $3/百万输入和 $15/百万输出。相比 Sonnet 4.6，在推理、工具使用、编程和知识工作等智能体能力上大幅提升。在 BrowseComp 和 OSWorld-Verified 评测中严格优于 Sonnet 4.6。安全评估显示不良行为率更低，幻觉和谄媚减少，但网络安全能力弱于 Opus 4.8。即日起在所有套餐及 Claude Code、Claude API 中可用。

智能体Anthropic模型发布编码
推荐理由：Claude Sonnet 5 把代理能力从 Opus 下放到了 Sonnet，性能接近 Opus 4.8 但价格只有三分之一，这对开发者来说性价比飞跃。虽然还不是最强，但已经能让许多复杂任务从勉强可用变成可靠。
01:28
Claude：Blog（网页）精选
AI 评分 72/100
Claude Code 入门：智能体循环

Claude Code 团队将智能体循环定义为 agent 重复工作直到满足停止条件的过程，并划分出四种主要类型：turn-based 循环（用户提示触发，Claude 自行判断完成或需更多上下文）、goal-based 循环（通过 /goal 命令设定可验证完成标准与最大轮次）、time-based 循环（通过 /loop 按时间间隔重复执行，可用 /schedule 移至云端）、以及 proactive 循环（基于事件或计划自动运行，无人实时参与）。文章还介绍了如何编写 SKILL.md 文件将人工验证步骤编码，让 Claude 进行端到端自检，减少 turn-based 循环中的手动操作。

智能体AnthropicMCP/工具教程/实践
推荐理由：Anthropic把agentic loops从模糊概念变成四种可复制的模式，附带SKILL.md和命令示例，Claude Code用户读完就能设计更自主的编码流程。
01:02
Boris Cherny@bcherny精选
AI 评分 68/100
Claude Desktop Linux版正式发布You asked, we listened. Claude Desktop on Linux is here!Download link: https://code.claude.com/docs/en/desktop-linux译你们要求，我们听取。Claude Desktop Linux版来了！ 下载链接：https://code.claude.com/docs/en/desktop-linux

ClaudeDevs: Claude Desktop is now available on Linux (Ubuntu and Debian) in beta. Alongside the browser and terminal, you now get a ...

Anthropic产品更新编码
推荐理由：Claude Desktop 正式支持 Linux，对常年用 Claude Code 的开发者是补上了最缺的一环，不用再在终端和浏览器之间来回了。

6月30日6月30日周二

星期二 · 3 条
13:53
公众号：龙猫LongCat（美团）精选
AI 评分 82/100
美团 LongCat-2.0 正式发布：国产算力集群训练的万亿参数大模型

美团于6月30日发布新一代万亿参数大模型LongCat-2.0并开源。总参数1.6T，平均激活约48B，原生支持1M超长上下文，在五万卡国产算力集群上完成全流程训练与推理。采用LSA稀疏注意力、零计算专家、ScMoE及MOPD多专家融合（Agent/Reasoning/Interaction三组专家）架构。评测中SWE-bench Pro获59.5，SWE-bench Multilingual获77.3。预览版已通过OpenRouter和longcat.ai开放，月调用量跻身OpenRouter全球前三。

开源生态推理模型发布编码
另有 6 家信源报道X：Rohan Paul (@rohanpaul_ai)X：Testing Catalog (@testingcatalog)公众号：卡尔的AI沃茨Hacker News 热门（buzzing.cc 中文翻译）IT之家（RSS）X：美团 LongCat (@Meituan_LongCat)
推荐理由：国产算力上首个全流程自训的万亿开源模型，1M上下文和动态专家架构直指Agentic Coding场景，OpenRouter调用量已经冲到前三，不是Demo是生产力。
13:53
SiliconFlow@SiliconFlowAI精选
AI 评分 67/100
美团 LongCat 发布旗舰模型 LongCat-2.0The full model behind "Owl Alpha" on @OpenRouter is here🦉 Let's meet @Meituan_LongCat 's latest flagship model, LongCat-2.0 Now Day 0 live on SiliconFlow 🔥 💰 Input Cache/Input/Output: $ 0.015/0.75/2.95 per 1M tokens ⚙️ 1.6T-param MoE (~48B active) · Native 1M context window 🧠 Built for agentic coding from the ground up: ◆ LSA: sparse attention that scales efficiently to 1M ◆ Zero-Compute Experts: dynamic 33B–56B active/token, no wasted compute ◆ MOPD: three specialized expert groups (Agent / Reasoning / Interaction), gate-routed per task 🏆 59.5 SWE-bench Pro: performance on par with mainstream close-sourced modelsStart building with 🐱👇译美团 LongCat 推出旗舰模型 LongCat-2.0，采用 1.6T 参数 MoE 架构（约 48B 活跃参数），原生支持 1M 上下文窗口。定价为 Input Cache $0.015/1M tokens、Input $0.75/1M tokens、Output $2.95/1M tokens。模型专为 Agentic Coding 设计，包含三大技术：LSA 稀疏注意力实现高效 1M 扩展；Zero-Compute Experts 动态激活 33B-56B 参数/token，无算力浪费；MOPD 将专家分为 Agent / Reasoning / Interaction 三组，按任务门控路由。在 SWE-bench Pro 上取得 59.5 分，性能接近主流闭源模型。现已上线 SiliconFlow Day 0 服务。
智能体模型发布编码
另有 6 家信源报道X：Rohan Paul (@rohanpaul_ai)X：Testing Catalog (@testingcatalog)公众号：卡尔的AI沃茨Hacker News 热门（buzzing.cc 中文翻译）IT之家（RSS）X：美团 LongCat (@Meituan_LongCat)
推荐理由：美团龙猫的 LongCat-2.0 专为 agentic coding 设计的 MoE 模型，架构上三种专家分工有点意思，SWE-bench 59.5 接近闭源水平，已经能在硅基流动上直接调，做 coding agent 的可以跑跑看。
05:22
Claude：Blog（网页）精选
AI 评分 66/100
为 Amazon Bedrock 和 Google Cloud 推出的 Claude apps gateway

Anthropic 今日推出 Claude apps gateway，一个自托管控制平面，让企业能在 Amazon Bedrock 和 Google Cloud 上运行 Claude Code。它作为单个无状态容器部署于 Linux，后端使用 PostgreSQL，提供企业级 SSO 登录（通过 OIDC 对接 Google Workspace、Microsoft Entra ID、Okta 等）、集中策略管理、角色权限、路由（支持故障转移）以及按日/周/月、按组织/群组/用户的消费上限。遥测数据通过 OTLP 发送至用户配置的收集器。gateway 不会向 Anthropic 发送推理流量或使用数据（除非配置使用 Claude API）。即日起可用。

AnthropicGoogle产品更新编码
推荐理由：Claude Code企业版有了统一管理入口，SSO和成本控制是团队落地AI编程的关键，对CTO来说值得关注。
Agent 智能体Cursor教程实践