【文章标题】：🎙️ How I AI: Grok Bot + Grok 4.6—what’s great (and what’s still hype) & Lessons from spending $20,000 on Devin in one month
🎙️ How I AI：Grok Bot + Grok 4.6——哪些地方出色（哪些仍是炒作）以及一个月在 Devin 上花费 20,000 美元的经验教训
【文章正文】： Grok Bot + Grok 4.6—what’s great (and what’s still hype)
Grok Bot + Grok 4.6——哪些地方出色（哪些仍是炒作）
Listen now on
现在收听：
YouTube
YouTube
•
•
Spotify
Spotify
•
•
Apple Podcasts
Apple Podcasts
Brought to you by:
由以下赞助商提供：
Bolt.new
Bolt.new
—Turn your idea into a real product
——将你的想法变成真实产品
Jira AI SDLC
Jira AI SDLC
—Get your tokens’ worth with Jira
——用 Jira 让你的 token 物有所值
In this solo episode, Claire tests Grok Bot, Cursor Origin, and Grok 4.6 to figure out what’s genuinely useful and what’s still mostly hype. She shares the Grok Bot feature that immediately won her over, why she isn’t ready to replace GitHub with Origin, and how Grok 4.6 performed against GPT-5.6, Claude Sonnet 5, and Opus 5 in her own blind evaluations.
在这期单人节目中，Claire 测试了 Grok Bot、Cursor Origin 和 Grok 4.6，以弄清楚哪些是真正有用的，哪些仍然主要是炒作。她分享了自己立刻被吸引的 Grok Bot 功能、为什么她还没准备好用 Origin 取代 GitHub，以及 Grok 4.6 在她自己的盲测中与 GPT-5.6、Claude Sonnet 5 和 Opus 5 相比表现如何。
Biggest takeaways:
最重要的收获：
Grok Bot’s multi-account connectors solve a problem every other agent platform seems to ignore.
Grok Bot 的多账户连接器解决了一个其他所有智能体平台似乎都忽略的问题。
Most platforms assume each person has one Gmail account and one Slack workspace. Claire has four email addresses and seven Slack workspaces. Grok Bot lets her connect all of them to a single bot, which made it genuinely useful from day one in a way that Codex and Claude still have not matched.
大多数平台都假设每个人只有一个 Gmail 账户和一个 Slack 工作区。Claire 有四个电子邮件地址和七个 Slack 工作区。Grok Bot 让她可以将所有这些账户连接到一个机器人上，这使它从第一天起就真正有用，而 Codex 和 Claude 至今仍无法做到这一点。
Grok Bot’s simplicity is both its greatest strength and its biggest limitation.
Grok Bot 的简洁性既是它最大的优势，也是它最大的局限。
Setup is fast, the iMessage-style interface is clean, and the built-in plugins actually work. But people who enjoy customizing their agents, choosing models, shaping personalities, and tinkering with every detail may find it almost too polished. Claire loves her OpenClaw agents partly because they are chaotic and high-maintenance. So far, Grok Bot has not given her much to wrestle with.
设置很快，iMessage 风格的界面很干净，内置插件也确实能用。但喜欢自定义智能体、选择模型、塑造个性并调整每个细节的人可能会觉得它过于精致。Claire 喜欢她的 OpenClaw 智能体，部分原因就是它们混乱且需要大量维护。到目前为止，Grok Bot 还没有给她太多需要折腾的地方。
Cursor Origin is a compelling vision that is not quite ready for prime time.
Cursor Origin 是一个引人注目的愿景，但还没有完全准备好进入黄金时段。
An agent-native alternative to GitHub makes a lot of sense, especially one where Bugbot, Cursor, and the entire pull request workflow are designed around how coding agents actually work. Today, though, Origin still feels like a more attractive version of GitHub with fewer features. Teams that rely heavily on GitHub Actions, code owners, and existing automations will need a much stronger reason to migrate.
一个以智能体为原生设计的 GitHub 替代方案非常有意义，尤其是 Bugbot、Cursor 和整个拉取请求工作流都围绕编码智能体的实际工作方式设计。不过，目前 Origin 仍然感觉像是一个功能更少但更有吸引力的 GitHub 版本。严重依赖 GitHub Actions、代码所有者和现有自动化的团队需要更充分的理由才会迁移。
Grok 4.6 is a genuine frontier-model competitor.
Grok 4.6 是一个真正的前沿模型竞争者。
That conclusion did not come from someone else’s leaderboard. Claire runs her evaluations blind, grades the outputs herself, and gives her own judgment 70% of the final weight. Grok 4.6 finished alongside GPT-5.6 Sol at the top of the Claire Index, ahead of both Sonnet 5 and Opus 5.
这个结论不是来自别人的排行榜。Claire 以盲测方式进行评估，自己给输出打分，并让自己的判断占最终权重的 70%。Grok 4.6 与 GPT-5.6 Sol 并列排在 Claire Index 的顶部，领先于 Sonnet 5 和 Opus 5。
For sharp, enjoyable agent conversations, Sonnet 5 is still the model to beat.
对于犀利、愉快的智能体对话，Sonnet 5 仍然是最值得击败的模型。
When Claire wants an OpenClaw agent that is concise, responsive, and fun to talk with, Sonnet 5 continues to win. It has a conversational rhythm that feels more like working with a strong collaborator than issuing commands to a tool. Grok 4.6 does not yet compete in that category.
当 Claire 想要一个简洁、响应迅速且交谈有趣的 OpenClaw 智能体时，Sonnet 5 仍然胜出。它的对话节奏让人感觉更像是在与一位强大的合作者共事，而不是向工具发号施令。Grok 4.6 在这个类别中还没有竞争力。
Cursor and xAI are assembling a surprisingly coherent enterprise stack.
Cursor 和 xAI 正在组装一个出奇连贯的企业技术栈。
Grok Bot serves knowledge workers, Origin handles code hosting, Grok 4.6 provides a capable default model, and the Cursor IDE already sits at the center of many developers’ workflows. None of the pieces is perfect on its own, but together they are beginning to look like a credible enterprise platform. Large companies often prefer one vendor that can own the entire experience, and Cursor is increasingly positioned to become that vendor.
Grok Bot 服务于知识工作者，Origin 负责代码托管，Grok 4.6 提供了一个有能力的默认模型，而 Cursor IDE 已经处于许多开发者工作流程的中心。这些部分单独来看都不完美，但合在一起，它们开始看起来像一个可信的企业平台。大公司通常更喜欢一个能够掌控整个体验的供应商，而 Cursor 越来越有潜力成为那个供应商。
Blog and detailed workflow walkthroughs from this episode:
本期节目的博客和详细工作流演示：
My Hands-On Review of GrokBot, Cursor Origin, and the Grok 4.6 Model:
我对 GrokBot、Cursor Origin 和 Grok 4.6 模型的亲身体验评测：
↳
↳
How to Automate Knowledge Work Across Multiple Accounts with GrokBot:
如何使用 GrokBot 自动化跨多个账户的知识工作：
I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)
我在一个月内花了 20,000 美元在 Devin 上。以下是我学到的东西 | Ryan Carson（独立创始人）
Listen now on
现在收听：
YouTube
YouTube
•
•
Spotify
Spotify
•
•
Apple Podcasts
Apple Podcasts
Brought to you by:
由以下赞助商提供：
WorkOS
WorkOS
—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more
——让你的应用具备企业级能力，支持 SSO、SCIM、RBAC 等
Jira AI SDLC
Jira AI SDLC
—Get your tokens’ worth with Jira
——用 Jira 让你的 token 物有所值
Ryan Carson
Ryan Carson
is a five-time founder and the solo founder of Untangle, a B2B SaaS platform for family law firms. In this episode, he breaks down how he manages up to 15 AI agents at once, ships as many as 40 pull requests a day, and uses Devin, Codex, and Claude Code to handle everything from engineering and QA to customer success and investor updates. He also shares why more AI output doesn’t necessarily lead to a better product, how a handwritten priority list keeps his agents focused, and why talking to one real customer changed the direction of his entire company.
是一位五次创业者，也是 Untangle 的独立创始人，Untangle 是一个面向家庭法律事务所的 B2B SaaS 平台。在本期节目中，他详细介绍了自己如何同时管理多达 15 个 AI 智能体、每天提交多达 40 个拉取请求，以及如何使用 Devin、Codex 和 Claude Code 处理从工程和 QA 到客户成功和投资者更新的一切事务。他还分享了为什么更多的 AI 产出并不一定能带来更好的产品，一份手写的优先级列表如何让他的智能体保持专注，以及为什么与一位真实客户交谈改变了他整个公司的方向。
Biggest takeaways:
最重要的收获：
The most important skill for a solo founder may be managing agents, not writing code.
独立创始人最重要的技能可能是管理智能体，而不是编写代码。
Ryan runs 10 to 15 Devin threads at once, organized into P0, P1, P2, and Bugs folders. He treats each thread the way a good manager treats a direct report: give it a clear goal, set the right priority, and avoid unnecessary hand-holding. That organizational discipline is what separates founders
Ryan 同时运行 10 到 15 个 Devin 线程，并将它们组织到 P0、P1、P2 和 Bugs 文件夹中。他对待每个线程的方式，就像一位优秀的管理者对待直接下属一样：给出明确的目标、设定正确的优先级，并避免不必要的过度干预。这种组织纪律正是区分创始人的关键