即刻App年轻人的同好社区
下载
置顶今年收YouTube学员会更加慎重，因为一部分时间要投入到油管的一个学习网站建设。
后期关于YouTube的交付内容会在这个网站上进行，包括相关文字内容和视频，学员可以通过网站登录直接学习。
这样可以解决后续新学员反复咨询同样问题的问题，大家可以直接在网站上查阅资料和观看视频。
微信主要用于日常沟通交流。
另外，之前有一两次找我退款，所以我再次强调，请大家在付款前一定要考虑清楚，付款后将不再退款。
当然，我的服务会持续升级和迭代。今年的重点是打造一个有YouTube的学习平台，采用网站的形式进行交付。
同时再次开启网站出海掘金第五期招募，这次的价格从原来的50块，涨价到99。
跟之前的交付不同，之前的交付的网站比较简单，这次交付做了大的升级。
你会亲眼看到一个稍微复杂网站是如何从0到1被设计做出来的，这个课程随便一个大V，收你四位数，太正常了。
豪不夸张的说，这次交付完全不输大V四位数的课程，价值只要十分之一甚至几十分之一。
为什么敢定这个价格？核心原因我的收入来源不靠培训。
价格放低一点也完全想交个朋友，我的微信好友，时不时过万，我不得不定期删除一些好友，腾出好友位给新的朋友。
我一直坚信一个观点——所谓人脉是你能帮到多少人。
后续，我到处旅游，如果我到你城市，同时你愿意跟我面基，我非常开心😁。
同时，如果你在深圳那就再好不过了，我一直在宝安坪洲地铁站大仟里附近。
为了避免很多人看不到消息，开营时间定在6月份，具体时间待定，计划定在6月7号。
这次，我也是给出了足够的诚意，这个价格完全可以闭眼入，如果觉得不值99，找我退款，立马退。
同时，我也给了激励，报名后，邀请你的朋友参加网站出海掘金第五期，奖励50块。
我为什么有资格收费？我作为程序员也有十来年，能力方面完全可以信任。
好了，我话说完，你可以付费了。
后期关于YouTube的交付内容会在这个网站上进行，包括相关文字内容和视频，学员可以通过网站登录直接学习。
这样可以解决后续新学员反复咨询同样问题的问题，大家可以直接在网站上查阅资料和观看视频。
微信主要用于日常沟通交流。
另外，之前有一两次找我退款，所以我再次强调，请大家在付款前一定要考虑清楚，付款后将不再退款。
当然，我的服务会持续升级和迭代。今年的重点是打造一个有YouTube的学习平台，采用网站的形式进行交付。
同时再次开启网站出海掘金第五期招募，这次的价格从原来的50块，涨价到99。
跟之前的交付不同，之前的交付的网站比较简单，这次交付做了大的升级。
你会亲眼看到一个稍微复杂网站是如何从0到1被设计做出来的，这个课程随便一个大V，收你四位数，太正常了。
豪不夸张的说，这次交付完全不输大V四位数的课程，价值只要十分之一甚至几十分之一。
为什么敢定这个价格？核心原因我的收入来源不靠培训。
价格放低一点也完全想交个朋友，我的微信好友，时不时过万，我不得不定期删除一些好友，腾出好友位给新的朋友。
我一直坚信一个观点——所谓人脉是你能帮到多少人。
后续，我到处旅游，如果我到你城市，同时你愿意跟我面基，我非常开心😁。
同时，如果你在深圳那就再好不过了，我一直在宝安坪洲地铁站大仟里附近。
为了避免很多人看不到消息，开营时间定在6月份，具体时间待定，计划定在6月7号。
这次，我也是给出了足够的诚意，这个价格完全可以闭眼入，如果觉得不值99，找我退款，立马退。
同时，我也给了激励，报名后，邀请你的朋友参加网站出海掘金第五期，奖励50块。
我为什么有资格收费？我作为程序员也有十来年，能力方面完全可以信任。
好了，我话说完，你可以付费了。
2 00
Opus 5 现已登陆 Claude Code 和 Claude Platform。它在智能体终端编程基准 Frontier-Bench v0.1 上以 43.3% 达到新最佳水平，高于 Fable 5 的 33.7%，并超过 Opus 4.8 的两倍；在 FrontierCode v1.1 上，它以一半价格追平 Fable 5。对于大型代码库中的长期项目，Opus 5 更擅长架构、部署和设计级 UI，也更能在多阶段工作中保持方向。Claude Code 和 Claude Platform 默认使用高思考强度，可针对困难问题调高，或调低以获得更快、更便宜的响应；Fast 模式速度约为 2.5 倍，价格为基础价格的 2 倍。Claude Platform 还支持在对话中途增删工具而不使提示缓存失效，并新增备用路由。升级现有工作负载可在 Claude Code 中运行 `/claude-api migrate`；使用 API 时选择 `claude-opus-5`，或在 Claude Code 中运行 `/model claude-opus-5`。
Opus 5 is live in Claude Code and the Claude Platform today. A few things worth knowing:
On agentic terminal coding (Frontier-Bench v0.1), Opus 5 is the new state of the art at 43.3%: ahead of Fable 5 (33.7%) and more than double Opus 4.8. On FrontierCode v1.1 it matches Fable 5, at half the price.
Opus 5 is a step-change in coding for the Opus class. It excels at long-horizon projects in large codebases, handling architecture, deployment, and design-quality UI. It’s better at staying on track across multi-stage work, allowing you to delegate more.
Opus 5 defaults to high effort in Claude Code and Claude Platform. Turn it up for your hardest problems, or down for faster, cheaper turns. Fast mode is also available: ~2.5x faster at 2x base price, on the Claude Platform and in Claude Code via extra usage.
On Claude Platform, Opus 5 supports mid-conversation tool changes: add or remove tools without invalidating your prompt cache. We also added fallback routing: classifier-blocked requests are routed to our recommended model based on the request.
To upgrade existing workloads to Opus 5, run `/claude-api migrate` in Claude Code. The built-in claude-api skill updates your model strings and suggests prompt improvements that are tuned for Opus 5.
Try Opus 5 today. Use “claude-opus-5” on the Claude API, or run “/model claude-opus-5” in Claude Code.
此动态信息源来自于 Claude Code 官方账号
Opus 5 is live in Claude Code and the Claude Platform today. A few things worth knowing:
On agentic terminal coding (Frontier-Bench v0.1), Opus 5 is the new state of the art at 43.3%: ahead of Fable 5 (33.7%) and more than double Opus 4.8. On FrontierCode v1.1 it matches Fable 5, at half the price.
Opus 5 is a step-change in coding for the Opus class. It excels at long-horizon projects in large codebases, handling architecture, deployment, and design-quality UI. It’s better at staying on track across multi-stage work, allowing you to delegate more.
Opus 5 defaults to high effort in Claude Code and Claude Platform. Turn it up for your hardest problems, or down for faster, cheaper turns. Fast mode is also available: ~2.5x faster at 2x base price, on the Claude Platform and in Claude Code via extra usage.
On Claude Platform, Opus 5 supports mid-conversation tool changes: add or remove tools without invalidating your prompt cache. We also added fallback routing: classifier-blocked requests are routed to our recommended model based on the request.
To upgrade existing workloads to Opus 5, run `/claude-api migrate` in Claude Code. The built-in claude-api skill updates your model strings and suggests prompt improvements that are tuned for Opus 5.
Try Opus 5 today. Use “claude-opus-5” on the Claude API, or run “/model claude-opus-5” in Claude Code.
此动态信息源来自于 Claude Code 官方账号
0 00
Claude Opus 5 正式发布。它是一款深思熟虑、积极主动的模型，以一半价格接近 Fable 5 的前沿智能水平，并在多项编程和知识工作评测中达到新的最佳水平。Opus 5 以相近或更低的单任务成本超越其他模型；在要求 AI 解决全新问题的 ARC-AGI-3 评测中，得分是次优模型的三倍。自动行为审计显示，它是目前与我们目标最一致的模型，鲁莽或欺骗行为发生率最低，对 Claude 宪法的遵循最强。其网络安全能力强于 Opus 4.8，但开发漏洞利用程序的能力仍明显落后于 Mythos 5；安全措施旨在帮助开发者发现并修复漏洞，同时阻止高风险用途。Opus 5 已向所有付费套餐和 Claude API 开放，价格与 Opus 4.8 相同；它是 Claude Max 的默认模型，也是 Claude Pro 上能力最强的模型，并提供约 2.5 倍速度的 Fast 模式。
Introducing Claude Opus 5. It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price.
On several coding and knowledge work evaluations, Opus 5 is the new state-of-the-art.
Opus 5 is also highly efficient. It outperforms other models for a similar or lower cost per task.
On ARC-AGI-3, an evaluation where AI models must solve novel problems, Opus 5’s score is three times as high as the next best model.
According to our automated behavioral audit, Opus 5 is our most aligned model to date. Compared to our other models, it shows the lowest rates of reckless or deceptive behavior, and the strongest adherence to Claude’s Constitution.
Opus 5 is stronger than Opus 4.8 on cybersecurity tasks. But it remains substantially behind Mythos 5 at developing exploits. Its safeguards are designed to allow developers to identify and fix software vulnerabilities, while blocking high-risk uses.
Opus 5 is available today on all paid plans and the Claude API, priced the same as Opus 4.8. It’s the default model on Claude Max, and the strongest on Claude Pro. It’s also offered in Fast mode, which runs around 2.5× the default speed. Read more: www.anthropic.com
此动态信息源来自于 Claude 官方账号
Introducing Claude Opus 5. It's a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price.
On several coding and knowledge work evaluations, Opus 5 is the new state-of-the-art.
Opus 5 is also highly efficient. It outperforms other models for a similar or lower cost per task.
On ARC-AGI-3, an evaluation where AI models must solve novel problems, Opus 5’s score is three times as high as the next best model.
According to our automated behavioral audit, Opus 5 is our most aligned model to date. Compared to our other models, it shows the lowest rates of reckless or deceptive behavior, and the strongest adherence to Claude’s Constitution.
Opus 5 is stronger than Opus 4.8 on cybersecurity tasks. But it remains substantially behind Mythos 5 at developing exploits. Its safeguards are designed to allow developers to identify and fix software vulnerabilities, while blocking high-risk uses.
Opus 5 is available today on all paid plans and the Claude API, priced the same as Opus 4.8. It’s the default model on Claude Max, and the strongest on Claude Pro. It’s also offered in Fast mode, which runs around 2.5× the default speed. Read more: www.anthropic.com
此动态信息源来自于 Claude 官方账号
0 00
我们更新了“缩放工具”Cookbook。大图片被缩小时可能丢失重要细节，缩放工具允许 Claude 请求某一区域，并从全分辨率原图中取回对应裁剪。Chartography 基准包含 100 道密集真实图表问题：使用该工具后，Fable 5 的准确率从 29% 提升至 73%，Sonnet 5 从 13% 提升至 44%。
We've updated our "zoom tool" cookbook. When large images get downscaled, important detail can be lost. A zoom tool lets Claude request a region and get that crop back from the full-res original.
On the Chartography benchmark (100 questions over dense real-world charts), Fable 5's accuracy goes from 29% to 73% with a zoom tool, and Sonnet 5’s from 13% to 44%. See the cookbook to learn more: github.com
此动态信息源来自于 Claude Code 官方账号
We've updated our "zoom tool" cookbook. When large images get downscaled, important detail can be lost. A zoom tool lets Claude request a region and get that crop back from the full-res original.
On the Chartography benchmark (100 questions over dense real-world charts), Fable 5's accuracy goes from 29% to 73% with a zoom tool, and Sonnet 5’s from 13% to 44%. See the cookbook to learn more: github.com
此动态信息源来自于 Claude Code 官方账号
0 00
Claude 语音模式现在会使用更强大的模型，并能在对话过程中调用你已连接的工具。语音对话可使用聊天中的更多模型，包括 Claude Opus 和 Sonnet，也可以访问电子邮件、日历等连接工具。所有套餐都新增支持西班牙语、法语、印地语和日语等更多语言；该更新正在移动端、桌面端和网页端进行公开测试。
Voice mode now runs on Claude's more capable models and reaches the tools you've connected mid-conversation. Talk through the hard problems out loud, in many more languages.
Voice conversations now use more of the models you have in chat, including Claude Opus and Sonnet. Claude can also reach the tools you've connected mid-conversation, like your email and calendar.
Voice mode also supports more languages, on every plan, including Spanish, French, Hindi, and Japanese. The update is rolling out today in public beta on mobile, desktop, and web. Download the mobile app and tap the sound wave to start a conversation: claude.com
此动态信息源来自于 Claude 官方账号
Voice mode now runs on Claude's more capable models and reaches the tools you've connected mid-conversation. Talk through the hard problems out loud, in many more languages.
Voice conversations now use more of the models you have in chat, including Claude Opus and Sonnet. Claude can also reach the tools you've connected mid-conversation, like your email and calendar.
Voice mode also supports more languages, on every plan, including Spanish, French, Hindi, and Japanese. The update is rolling out today in public beta on mobile, desktop, and web. Download the mobile app and tap the sound wave to start a conversation: claude.com
此动态信息源来自于 Claude 官方账号
0 00
Claude Cowork 新功能：你现在可以教 Claude 一项技能。执行任务时录制屏幕并同步讲解，Claude 会把操作过程转化为可重复运行的技能。在 Claude 桌面应用的“+”菜单中选择“Record a skill”即可使用，支持 Pro、Max 和 Team 套餐。
New in Claude Cowork: teach Claude a skill. Record your screen while you do a task, talk through it as you go, and Claude turns it into a skill it can run again. Find it under Record a skill in the + menu of the Claude desktop app. Available on Pro, Max, and Team plans.
此动态信息源来自于 Claude 官方账号
New in Claude Cowork: teach Claude a skill. Record your screen while you do a task, talk through it as you go, and Claude turns it into a skill it can run again. Find it under Record a skill in the + menu of the Claude desktop app. Available on Pro, Max, and Team plans.
此动态信息源来自于 Claude 官方账号
0 00
Claude Managed Agents 新增多项功能：现在可以为每个智能体配置思考强度、用事件初始化会话、每个会话添加最多 500 个技能、为环境和记忆存储使用 Webhook，以及流式接收子智能体事件。思考强度越低，响应越快、成本越低。创建会话时还可一次加入最多 50 个 `user_message` 和 `define_outcome` 事件。可通过官方 cookbook 体验这些能力，也可让 Claude Code 使用内置 `claude-api` 技能查询，或查看发布说明。
We've just added several new features to Claude Managed Agents. You can now configure effort levels per agent, seed sessions with events, add up to 500 skills per session, use webhooks for environments + memory stores, and stream events for sub-agents.
Effort controls how much each Managed Agent thinks. Lowering effort gives faster responses and lower cost.
Before, creating a session and sending it events took separate API calls. You can now seed a new session with up to 50 user_message and define_outcome events in the create call.
Skills give your Managed Agent task-specific instructions. You can now add up to 500 skills across all Managed Agents in a session.
Try out these new features using our cookbook, ask Claude Code about them using the built-in "claude-api" skill, or check the release notes: x.com
此动态信息源来自于 Claude Code 官方账号
We've just added several new features to Claude Managed Agents. You can now configure effort levels per agent, seed sessions with events, add up to 500 skills per session, use webhooks for environments + memory stores, and stream events for sub-agents.
Effort controls how much each Managed Agent thinks. Lowering effort gives faster responses and lower cost.
Before, creating a session and sending it events took separate API calls. You can now seed a new session with up to 50 user_message and define_outcome events in the create call.
Skills give your Managed Agent task-specific instructions. You can now add up to 500 skills across all Managed Agents in a session.
Try out these new features using our cookbook, ask Claude Code about them using the built-in "claude-api" skill, or check the release notes: x.com
此动态信息源来自于 Claude Code 官方账号
0 00
Claude Code 的 Claude Security 插件现已开放测试。你可以在提交代码前扫描改动中的漏洞，也可以对整个代码库运行完整扫描，全部都能在终端里完成，并沿用你已经运行的 Claude 推理。更多信息见原帖。
The Claude Security plugin for Claude Code is now available in beta. Scan your changes for vulnerabilities before you commit, or run a full scan across your codebase, all from your terminal on the Claude inference you already run.
Read more: x.com
此动态信息源来自于 Claude 官方账号
The Claude Security plugin for Claude Code is now available in beta. Scan your changes for vulnerabilities before you commit, or run a full scan across your codebase, all from your terminal on the Claude inference you already run.
Read more: x.com
此动态信息源来自于 Claude 官方账号
0 00
现在可以直接向 Claude 查询 Anthropic Economic Index——这是我们用于衡量 AI 在经济各领域中如何被使用的公开数据集。你可以询问哪些职业使用 AI 最多，或人们正在自动化哪些任务，回答会直接引用指数数据。打开连接器菜单，在目录中找到 Anthropic Economic Index 即可启用；它适用于任意对话，完整数据集仍可从我们的网站免费下载。更多信息见原帖。
You can now ask Claude about the Anthropic Economic Index, our public dataset measuring how AI is used across the economy. Ask which occupations use AI the most, or what kinds of tasks people are automating, and the answers draw directly from the Index data.
To turn it on, open the connectors menu and find the Anthropic Economic Index in the directory. It works in any conversation, and the full datasets remain free to download on our website. Read more: x.com
此动态信息源来自于 Claude 官方账号
You can now ask Claude about the Anthropic Economic Index, our public dataset measuring how AI is used across the economy. Ask which occupations use AI the most, or what kinds of tasks people are automating, and the answers draw directly from the Index data.
To turn it on, open the connectors menu and find the Anthropic Economic Index in the directory. It works in any conversation, and the full datasets remain free to download on our website. Read more: x.com
此动态信息源来自于 Claude 官方账号
0 00
桌面版 Claude Code 现在支持 iOS 模拟器。构建并运行 iOS 应用后，模拟器会直接显示在对话旁的面板中。Claude 可以查看应用运行状态、与应用交互并持续迭代直至完成；你也可以随时亲自操作模拟器。该功能现已提供公开测试，仅支持 macOS 桌面版 Claude Code，并要求安装 Xcode。文档见原帖。
Claude Code on desktop now works with the iOS simulator. Build and run your iOS app, and the simulator opens in a panel right next to your conversation. Available today in public beta.
Claude can see the app as it runs, interact with it, and iterate until finished. Tap through the simulator yourself at any time. Available in Claude Code on desktop (macOS only, requires Xcode).
Learn more in docs: x.com
此动态信息源来自于 Claude Code 官方账号
Claude Code on desktop now works with the iOS simulator. Build and run your iOS app, and the simulator opens in a panel right next to your conversation. Available today in public beta.
Claude can see the app as it runs, interact with it, and iterate until finished. Tap through the simulator yourself at any time. Available in Claude Code on desktop (macOS only, requires Xcode).
Learn more in docs: x.com
此动态信息源来自于 Claude Code 官方账号
0 00
Anthropic 如何使用 Claude Code 完成大规模代码迁移：借助多个智能体并行执行、阶段门禁和对抗式审查，过去通常耗时数年的迁移工作可以显著提速。案例包括 Bun 从 Zig 向 Rust 的百万行迁移，以及一个 Python 代码库在周末迁移为约 16.5 万行 TypeScript。阅读全文见原帖。
How Anthropic runs large-scale code migrations with Claude Code
x.com
此动态信息源来自于 Claude Code 官方账号
How Anthropic runs large-scale code migrations with Claude Code
x.com
此动态信息源来自于 Claude Code 官方账号
0 00