Peter Yang

@peteryangyt

共 285 期 · 已译制 1 期

36:25

Peter是OpenClaw(前身为Molt——名字总在变😅)的创始人,这款AI工具目前火爆全网,一周内吸引了200万访客。在我们的访谈中,Peter分享了他个人最爱的使用场景,包括用Claw办理航班值机、控制家居等。我们还聊到了他的犀利观点,比如"无计划模式"或MCP(模型上下文协议)。 Peter和我讨论了以下内容: (00:00) "就像电脑里住进了一个奇怪的新朋友" (03:52) "它给我发了条语音消息,但我根本没设置过" (15:06) "它整晚盯着我的安防摄像头,发现了这个" (16:15) 用OpenClaw办理航班值机、调节灯光和调整床铺 (19:42) 为什么80%的手机应用会消失 (22:51) 智能体陷阱:为什么花哨的AI工作流只会产出垃圾 (29:42) Peter的AI编程犀利观点:无计划模式、MCP很烂等 (36:56) 学习AI的方法就是玩 感谢我们的赞助商: Linear:面向现代团队的AI智能体平台 https://linear.app/behind-the-craft Granola:能为你节省数小时的AI会议笔记应用 https://granola.ai/peter Replit:2分钟从零到全栈应用 https://replit.com/?utm_source=creator&utm_medium=organic&utm_campaign=creator_program&utm_content=peteryang 📌 获取要点:https://creatoreconomy.so/p/how-openclaws-creator-uses-ai-peter-steinberger 关注Peter: X:https://x.com/steipete 网站:https://openclaw.ai/ 订阅本频道——更多教程即将上线!

36:07

📌 Copy the AI system I use to run a one-person $1M+ business: https://www.behindthecraft.com 🤝 Subscribe to my practical AI newsletter read by 150K+ professionals: https://creatoreconomy.so As head of product engineering at Replit, Amol has a firsthand look at which vibe-coded apps become real businesses. He showed me three apps built by non-coders that reached six figures, then walked through his 4-step process to take a prototype to production — publishing, security, monetization, and distribution. Amol and I talked about: (00:00) He built an app in 3 days that made $100K+ in month one (02:08) Three vibe-coded apps that became real businesses (08:04) What six-figure vibe-coded apps have in common (12:31) Live demo: Turn an AI interview coach into a real business (13:59) Steps 1 and 2: Publish the app and make it secure (17:50) Steps 3 and 4: Add payments and optimize SEO (21:35) How to replace expensive SaaS with internal tools (28:22) What software survives when code costs almost nothing (31:02) Why value is moving from models to apps Thanks to our sponsors: Riverside: All-in-one AI studio for podcasts and video https://creators.riverside.com/PeterYang Linear: The AI agent platform for modern teams https://linear.app/behind-the-craft Wispr Flow: 4x faster than typing with your voice https://ref.wisprflow.ai/peteryang 📌 Get the takeaways: https://creatoreconomy.so/p/how-non-coders-are-vibe-coding-100k-businesses-with-ai-amol-jain-replit Where to find Amol: LinkedIn: https://www.linkedin.com/in/jainamol Website: https://replit.com Subscribe to this channel - more interviews coming soon!

暂未译制

26:47

📌 Copy the AI system I use to run a one-person $1M+ business: https://www.behindthecraft.com 🤝 Subscribe to my practical AI newsletter read by 150K+ professionals: https://creatoreconomy.so A few months ago, I used Claude for almost everything. Today, there are so many AI models to choose from that the best really depends on your use case. In my new tutorial, I compare ChatGPT, Claude, Grok, and Gemini head-to-head for writing, design, coding, personal agents, and 6 other use cases. What I cover: (00:00) ChatGPT, Claude, Grok, and Gemini across 10 use cases (00:32) Still the best model for design (apps, slides, video) (07:34) This model's personality just isn't the same (09:58) The best model for writing and editing (12:06) The model I trust for difficult decisions (13:55) My controversial pick for coding (16:01) The most underrated AI category (18:52) Why ChatGPT voice is still far ahead (20:20) Which model follows image prompts best? (22:31) Grok vs. Gemini for AI video (23:55) The AI race that matters more than coding (25:52) My overall winner (and the best model to start with) Where to find me: X: https://x.com/petergyang LinkedIn: https://www.linkedin.com/in/petergyang/ Subscribe to this channel - more tutorials coming soon!

暂未译制

53:53

📌 Copy the AI system I use to run a one-person $1M+ business: https://www.behindthecraft.com 🤝 Subscribe to my practical AI newsletter read by 150K+ professionals: https://creatoreconomy.so Shreya and Hamel teach the industry standard course for AI evaluations taken by 4,500+ students from OpenAI, Google, and more. In our interview, I asked them to give live feedback on the AI evals that I built for my skills and demo how anyone can run evals with ChatGPT/Claude and their free evals skill. Don’t miss this up to date primer on evals from the real experts. 🙂 P.S., I asked Shreya and Hamel to give my audience 25% off the next cohort of their AI evals course. It has 4.7 stars with 900 reviews which is almost unheard of on Maven. Sign up via the link here: https://maven.com/parlance-labs/evals?utm_campaign=peteryang&utm_medium=affiliate&utm_source=maven&promoCode=PETERYANG We talked about: (00:00) Why AI evals are completely different now with the latest models (02:30) Demo: Live audit of the evals that I built for my AI skills (05:14) Top down vs. bottom up evals and why AI sucks at the latter (08:16) Spinning up AI agents to grade each eval criteria (14:32) Demo: Using Shreyas AI skill to run evals in Claude (23:46) How to review output labels to identify failures (34:37) How to turn failures into reusable evals (43:19) Where human judgement is still needed Resources mentioned: Free eval skills from Shreya: https://github.com/ai-evals-course/evals-skills Do automated evals work?: https://parlance-labs.com/blog/posts/auto-evals/ Thanks to our sponsors: Wispr Flow — 4x faster than typing with your voice — https://ref.wisprflow.ai/peteryang 📌 Get the takeaways: https://creatoreconomy.so/p/how-to-build-better-ai-evals-with-claude-code-shreya-hamel Where to find Shreya and Hamel: Shreya: https://www.sh-reya.com/ Hamel: https://hamel.dev/ Subscribe to this channel - more interviews coming soon!

暂未译制

22:54

📌 复制我用于运营一人百万美元业务的AI系统:https://www.behindthecraft.com 🤝 订阅我的实用AI通讯,已有15万+专业人士阅读:https://creatoreconomy.so 我认为Grok Bot是个人AI代理的未来。在本教程中,我将展示如何构建五个有用的机器人,包括一个能创建其他机器人的顾问、一个YouTube研究员、一个X平台侦察员、一个能清理Gmail并省钱的数字版Marie Kondo,以及一个能寻找更便宜航班的旅行管家。我还测试了用Grok Bot玩复古游戏,并分享了我对隐私、定价以及它能否取代ChatGPT成为我日常工具的真实看法。 时间戳: (00:00) Grok Bot与ChatGPT和Hermes的不同之处 (03:30) 顾问:创建并协调其他机器人 (04:30) YouTube研究员:发现异常视频和内容创意 (07:00) X平台侦察员:从你的信息流和书签中找出最佳帖子 (10:30) Marie Kondo:清理你的邮箱并节省付费订阅费用 (15:00) 个人管家:为你的旅行获取更优惠的航班价格提醒 (17:30) 游戏玩家:安装并玩复古游戏 (20:30) 我对隐私、定价以及Grok Bot能否取代ChatGPT的真实看法 在此尝试Grok Bot:https://x.ai/bot 在哪里找到我: 通讯:https://creatoreconomy.so/ X平台:https://x.com/petergyang LinkedIn:https://www.linkedin.com/in/petergyang/ 📌 订阅本频道获取更多实用AI教程。

暂未译制

0:29

“我什么都用Wispr Flow。” 来自Riley Brown(Agent Native): “我会花10分钟边走边说出所有想法,然后要求生成一个包含九张幻灯片的Excalidraw图表。” “当我回来时,它已经完成了我在视频中会用到的80%的图表。我再花20-30分钟编辑它们,但它给了我一个很好的起点,并整理了我的想法。” 📌 观看完整剧集:https://youtu.be/N34zz1-RSGw

暂未译制

0:34

“我从未看过任何技能文件。” 来自Riley Brown(Agent Native): “让AI使用某项技能做一件事。如果做得不好,告诉AI:‘请修改技能,这样你就不会再犯同样的错误。’然后开启一个新对话以清除上下文,再次测试。” “对你的AI保持一定标准,然后将工作流程转化为技能,并通过衡量结果来改进它。” 📌 观看完整剧集:https://youtu.be/N34zz1-RSGw

暂未译制

41:48

📌 获取我用来运营一人百万美元业务的AI系统:https://www.behindthecraft.com 🤝 订阅我的实用AI通讯,已有15万专业人士阅读:https://creatoreconomy.so Riley是一位顶级AI创作者,拥有超过150万粉丝。在本期节目中,他向我展示了如何用Codex运营整个内容业务——从生成吸引人的缩略图到撰写令人惊叹的视频开场。Riley还分享了他的完整AI工具栈,包括一些鲜为人知的AI工具,用于编辑视频、绘制图表等。 我们讨论了: (00:00) Codex如何运营Riley的150万粉丝内容业务 (03:16) 演示:使用Codex创建动画和B-roll (07:28) 演示:Codex如何逆向工程一个顶级YouTube开场 (13:24) BRENS框架:将想法转化为强力开场 (17:24) 演示:Riley用于图表、缩略图和帖子的AI工具栈 (22:01) Riley如何每周创作如此多的内容 (25:41) 演示:使用Codex和Paper创建爆款YouTube缩略图 (35:01) 如何设置AI代理快速寻找内容创意 感谢我们的赞助商: Google AI Studio:从提示到生产的最快路径 https://aistudio.google.com/?utm_source=peteryang&utm_medium=partner&utm_campaign=26Q3-peteryang_ais Riverside:播客和视频的全能AI工作室 https://creators.riverside.com/PeterYang 📌 获取要点:https://creatoreconomy.so/p/how-i-run-my-content-business-with-codex-riley-brown 关于Riley: X:https://x.com/rileybrown 网站:https://agentnative.inc/ 订阅本频道——更多访谈即将推出!

暂未译制

0:26

"尽可能少地给它指令。给它加载上下文的工具,不要给它上下文。" 来自 Jacob(Linear 工程师): "老实说,你想尽可能少地给它指令。给它加载上下文的工具,不要给它上下文。它可能会过度强调那些对该任务不重要的东西。如果你给它一个明确的目标,它们足够聪明,能自己获取所需。给它加载技能的工具,给它加载指导的工具,它就能自己构建上下文。" 📌 观看下方完整对话。

暂未译制

0:44

"每当用户做了我们没预料到的事,我们就把它加入评估集。它们会随着时间增长。" 来自 Jacob(Linear 工程师): "我们有评估,其中很多来自实际使用。用户做了我们没预料到的事,我们就把它加入数据集,评估集随着时间增长。我们尝试混合客观和主观指标。如果用户说‘进行中’,确保它总是将状态设为进行中。这是确定性的。然后还有主观的东西,比如你是否把描述组织得很好。对于这个,我们用LLM作为评判。" 📌 观看下方完整对话。

暂未译制

0:25

"如果代理无法做某事,它会调用一个工具来报告不足。这会自动为我们提交一个工单。这是一个持续的关于下一步要构建什么的流。" 来自 Jacob(Linear 工程师): "我们有一个机制,代理可以报告它无法实现的功能。如果用户要求某事而它没有对应的工具,它会调用一个工具并报告给我们。然后我们自动摄取:检查是否已有这个问题,如果有则添加,如果没有则创建新问题。所以我们有一个持续流入的问题流,关于下一步可以构建什么。" 📌 观看下方完整对话。

暂未译制

38:27

📌 复制我用于运营一人创收百万美元以上业务的AI系统:https://www.behindthecraft.com 🤝 订阅我的实用AI新闻通讯,已有15万+专业人士阅读:https://creatoreconomy.so Nan和Jacob构建了Linear Agent,它彻底改变了这家价值12.5亿美元公司的工作方式。在本期节目中,他们带我经历了从最初备忘录到产品发布的全过程,展示了如何为代理提供寻找所需上下文的工具,如何通过评估提升可靠性等。如果你想了解如何端到端地构建一个生产级代理的具体幕后案例,这期节目不容错过。 我们讨论了: (00:00) 随着模型改进,什么因素阻碍了AI代理的发展? (00:51) 每个优秀代理需要具备的三要素 (03:00) 演示:启动Linear Agent的内部备忘录 (09:50) 构建代理时最容易犯的错误 (11:29) 演示:通过代理,6分钟内从Slack到代码 (17:01) 原型设计时,“先用最大的模型直到它正常工作” (24:02) 给代理提供寻找上下文的工具,而不是提供更多上下文 (34:07) 构建代理前首先要做的事情 感谢我们的赞助商: Oceans:招聘AI原生执行助理 http://oceanstalent.com/peter Riverside:面向播客和视频的全能AI工作室 https://creators.riverside.com/PeterYang Linear:现代团队的AI代理平台 https://linear.app/behind-the-craft 📌 获取重点摘要:https://creatoreconomy.so/p/5-rules-for-building-ai-agents-in-production-linear-nan-jacob 关于Nan和Jacob: Nan的LinkedIn:https://www.linkedin.com/in/thenanyu Jacob的LinkedIn:https://www.linkedin.com/in/jacob-shumway-314a8366 Linear Agent:https://linear.app/docs/linear-agent 订阅本频道——更多访谈即将上线!

暂未译制

0:46

Claude、GPT,任何模型都会根据对你的忠诚度而表现得更出色。忠诚会培养模型的能力。 来自Karan Malhotra(Hermes联合创始人): 就像你愿意借100美元给你妈妈,但可能不会借给陌生人一样。 人们说不要将模型拟人化。但它们是人类经验的模拟器。你模拟的行为会给你带来模拟的输出,而现在这些输出会产生真实世界的影响。建立忠诚,它就会转化为真实的能力。 📌 在我的频道观看完整对话。

暂未译制

0:56

一个会自己编写技能的AI代理的问题:它最终会写出垃圾,整个系统也会变得一团糟。 来自Karan Malhotra(Hermes联合创始人): Hermes Curator在你的代理内部运行,定期清理你的技能和记忆,检查哪里存在垃圾,哪里可以更高效。 由于它是开源的,你可以定义自己的垃圾标准,它会按照你的方式重写自己的清理循环。 📌 在我的频道观看完整对话。

暂未译制

0:31

对我们来说,我们只希望开源最终能获胜。我们希望人们能获得自由。 来自Karan Malhotra(Hermes联合创始人): 我们需要继续将这种水平的智能给予每个人,并让每个人处于公平平等的竞争环境中。世界需要共同前进,以免由此产生不平等。 通过智能体让每个人达到同等智能水平,然后为每个人个性化定制,让他们都能有自己的顿悟。 📌 在我的频道观看完整对话。

暂未译制

46:45

📌 复制我用来运营一人百万美元业务的AI系统:https://www.behindthecraft.com 🤝 订阅我的实用AI通讯,已有15万+专业人士阅读:https://creatoreconomy.so ​ Karan联合创立了Nous Research,即Hermes背后的公司,Hermes是OpenRouter上排名第一的个人智能体和整体AI应用。我发现他非常脚踏实地,我们讨论了为什么开源AI必须获胜,Hermes如何越用越好,甚至还有现场演示Hermes如何修改你最喜欢的童年游戏。 Karan和我谈到了: (00:00) Hermes与Claude Code和Codex的区别 (02:20) 为什么每个AI模型现在听起来都一模一样 (11:16) 如何阻止AI说“你完全正确” (15:16) Hermes如何在不膨胀上下文的情况下创建技能 (16:40) 关于AI安全性的开源与闭源辩论 (23:40) 为人类和AI智能体使用同一个看板 (26:45) 演示:用Hermes重建童年索尼克世界 (36:07) 两个Discord朋友如何构建了一个自我改进的智能体 (42:40) Hermes如何成为自己最大的贡献者 感谢我们的赞助商: Riverside:播客和视频的一体化AI工作室 https://creators.riverside.com/PeterYang Linear:面向现代团队的AI智能体平台 https://linear.app/behind-the-craft Wispr Flow:用语音打字快4倍 https://ref.wisprflow.ai/peteryang 📌 获取要点:https://creatoreconomy.so/p/hermes-co-founder-on-building-an-ai-agent-that-improves-itself-karan-malhotra 在哪里找到Karan: X: https://x.com/karan4d 网站: https://www.karan4d.com/ Hermes Agent: https://github.com/NousResearch/hermes-agent 订阅本频道 - 更多访谈即将推出!

暂未译制

25:27

📌 获取我用来运营一人百万美元业务的AI系统:https://www.behindthecraft.com 🤝 订阅我的实用AI通讯,已有15万专业人士阅读:https://creatoreconomy.so ​ 我设计并构建了Tastemaker——一个用于策展你最喜爱的电影、电视剧和游戏的网站——整个过程没有使用Figma。在本教程中,我将逐步讲解我的六步AI原生设计流程,从定义问题到发布可运行的应用,全程使用Claude Design和Claude Code。 我涵盖的内容: (00:00) 我的六步AI原生设计流程 (00:50) 第一步:构建前先定义用户问题 (02:25) 第二步:寻找灵感并创建design.md (05:00) 第三步:在Claude Design中原型关键屏幕 (12:59) 第四步:为产品、设计和技术创建一份HTML规范 (17:02) 第五步:设计每个核心屏幕和边缘情况 (20:42) 第六步:使用Claude Code构建应用 (23:07) 总结:为什么规划应至少占用一半时间 尝试Tastemaker:https://mytastemaker.vercel.app/ 关注我: 通讯:https://creatoreconomy.so/ X:https://x.com/petergyang LinkedIn:https://www.linkedin.com/in/petergyang/ 订阅本频道——更多教程即将推出!

暂未译制

34:33

📌 Copy the AI system I use to run a one-person $1M+ business: https://www.behindthecraft.com 🤝 Subscribe to my practical AI newsletter read by 150K+ professionals: https://creatoreconomy.so ​ ​ Jason is a DevEx engineer on the Codex team. In our episode, he showed me how he runs his entire workday using Codex, from his chief of staff thread for Slack and email to setting up long-running tasks that have verifiable goals. Jason wrote the official OpenAI guidebook on how to get the most out of Codex, so don’t miss this episode. Jason and I talked about: (00:00) The only job left after AI can do the work (02:40) Turn pinned threads into long-running workspaces (05:50) Build a chief of staff across Slack, email, and Linear (10:12) Teach Codex to write like you for every audience (13:33) Mine past sessions for new skills and workflows (20:01) How Codex revised a launch video while Jason was out (24:23) Build a drum practice site around how you learn (25:59) Goal, plan, and worklog for long-running Codex tasks (33:52) Why taste starts with knowing what feels wrong Thanks to our sponsors: Google AI Studio: The fastest way to go from prompt to production https://aistudio.google.com/?utm_source=peteryang&utm_medium=partner&utm_campaign=26Q3-peteryang_ais Riverside: All-in-one AI studio for podcasts and video https://creators.riverside.com/PeterYang 📌 Get the takeaways: https://creatoreconomy.so/p/how-to-use-codex-for-work-my-complete-system-at-openai-jason-liu Where to find Jason: X: https://x.com/jxnlco Subscribe to this channel - more interviews coming soon!

暂未译制

0:41

“当模型偏好自己的输出时,它在验证时会更加宽容。” 来自Thariq(Anthropic): “例如,对于‘这个视频短片好不好?’你应该有一个评分标准和一个独立的验证代理来审查短片,确保它合格。 你应该使用两个独立的Claude:一个负责工作,另一个负责验证。” 📌 在我的YouTube上观看完整剧集。

暂未译制

0:41

“随着模型变得更智能,它们需要的指令、约束和示例也更少。” 来自Thariq(Anthropic): “示例会限制它,因为它会想,‘哦,你想要像这个示例一样的东西。’如果移除示例,它实际上可以更自由发挥。 很多时候,当你说‘绝不’时,你并不是真的意味着绝不。你的意思是‘大多数情况下不要这样做。’如果你给出原因,反而会更有效。 总之,你想要精简上下文。最新的模型往往需要更多空间来运行。” 📌 在我的YouTube上观看完整剧集。

暂未译制

0:38

“我不认为规格说明只发生在开始阶段。” 来自Thariq(Anthropic): “我从一个请求开始,然后代理进行一些探索。接着我做一些原型或解释,以了解我的未知。 我让Claude保留实现笔记,以便发现我们没有预料到的事情。一旦有了这些,如果需要,我们可以重新调整规格。 这更像是从规格到实现的反复过程,而不是一次性的交接。” 📌 在我的YouTube上观看完整剧集。

暂未译制

41:18

Thariq在Claude Code团队工作,我一直想看看他是如何构建的。在本期节目中,他展示了如何使用/goal让Claude保持工作状态,如何在构建前通过Claude消除未知因素来制定计划,以及如何在Slack中运行一个智能体团队。他还分享了为什么他的团队将Claude Code的系统提示削减了80%,以及他如何使用Claude制作精美的发布视频。 Thariq和我讨论了: (00:00) 让Claude更长时间工作的目标、循环和工作流程 (04:48) 现场演示:用一个提示词创建精美的视频 (08:17) 在构建前通过消除未知因素来制定计划 (14:32) Anthropic如何使用HTML制品进行规划 (18:35) 通过Slack运行并行的Claude任务 (27:34) 使用独立的创建者和验证者子智能体 (31:08) Thariq在Claude并行工作时如何保持专注 (34:07) 为什么Anthropic将Claude Code的系统提示削减了80% (37:01) 当AI编写代码时如何变得更懂技术 感谢我们的赞助商: Riverside:一体式AI演播室,用于播客和视频 https://creators.riverside.com/PeterYang Linear:面向现代团队的AI智能体平台 https://linear.app/behind-the-craft Wispr Flow:比打字快4倍的语音输入 https://ref.wisprflow.ai/peteryang 📌 获取要点:https://creatoreconomy.so/p/how-i-plan-build-and-run-loops-with-claude-code-thariq-shihipar 📌 获取我的个人AI操作系统,包含实用的AI技能、价值270美元的AI工具积分、每月现场工作坊以及关于Hermes和Codex智能体的课程:https://www.behindthecraft.com/ 在哪里找到Thariq: LinkedIn:https://x.com/trq212 网站:https://www.thariq.io/ 订阅本频道——更多采访即将到来!

暂未译制

28:52

📌 Copy the AI system I use to run a one-person $1M+ business: https://www.behindthecraft.com 🤝 Subscribe to my practical AI newsletter read by 150K+ professionals: https://creatoreconomy.so ​ ​ I now use ChatGPT Work and Codex for almost everything I do on my computer, and I’m going to show you exactly how to do the same. By the end of this video, you’ll be using ChatGPT to manage your emails and calendar, make beautiful websites, and so much more. What I cover: (00:00) How I use ChatGPT Work for almost everything (01:04) Chat vs. Work vs. Codex: What’s the difference? (02:22) Which GPT-5.6 model and effort to use (03:18) Personalizing ChatGPT Work’s custom instructions (06:23) Connect your apps and organize your Work threads (09:30) Let ChatGPT manage email and draft replies in your voice (13:47) Schedule events and prep for meetings automatically (17:19) Automate recurring work with scheduled tasks (19:23) Continue your Work tasks from your phone (21:01) Publish travel guides, games, and product plans as Sites Get the written tutorial: https://creatoreconomy.so/p/how-i-use-chatgpt-work-and-gpt-5-6-for-everything-tutorial Resources mentioned: Download the ChatGPT desktop app: https://chatgpt.com/download/ Get my free No AI Slop skill: https://github.com/petergyang/no-ai-slop Keep your Mac awake with Amphetamine: https://apps.apple.com/us/app/amphetamine/id937984704?mt=12 Where to find me: Newsletter: https://creatoreconomy.so/ X: https://x.com/petergyang LinkedIn: https://www.linkedin.com/in/petergyang/ Subscribe to this channel for more practical AI tutorials and interviews.

暂未译制

0:21

Jared Zoneraich(Cognition 驻场构建师)分享了他关于我们将如何与 AI 智能体合作的最激进预测。 “我认为人类将回归到一个只有木桌的世界——没有显示器、没有键盘、没有鼠标。我只需要一个按钮和轻声交流的流程。这就是我所需要的。” 📌 观看下方完整对话。 🎧 完整剧集:https://youtu.be/0YeeJHYy-Vc #AI #AI智能体 #未来工作 #Cognition #Shorts

暂未译制

0:43

Jared Zoneraich (Builder-in-Residence at Cognition) on the #1 mistake teams make when building AI agents. "You want to build in a way that lines up with the roadmap of the model labs. Let the model cook, and don't try to push it in certain directions. You'll need less scaffolding around agents as the models get better. And they're pretty good already." 📌 Watch the full conversation below. 🎧 Full episode: https://youtu.be/0YeeJHYy-Vc #AI #AIagents #coding #Cognition #Shorts

暂未译制

0:39

Jared Zoneraich (Builder-in-Residence at Cognition) on agent fan-out and why the human shouldn't be the bottleneck anymore. "More Devins are being launched by other Devins than by humans. Every time a Datadog alert goes off, you can pipe it to Devin. Like the early days of self-driving cars — you didn't want the GPU sitting idle. If I'm going to sleep, I want my agents doing stuff." 📌 Watch the full conversation below. 🎧 Full episode: https://youtu.be/0YeeJHYy-Vc #AI #AIagents #coding #Devin #Cognition #Shorts

暂未译制

47:13

📌 Copy the AI system I use to run a one-person $1M+ business: https://www.behindthecraft.com 🤝 Subscribe to my practical AI newsletter read by 150K+ professionals: https://creatoreconomy.so ​ ​ Jared is a Builder in Residence at Cognition, the team behind Devin. He showed me why teams often overbuild their first agents, and how simple prompts, better tools, and self-testing work together instead. Then he demoed one manager agent breaking down a task, directing 10 cloud agents, and deciding what a human needs to review. Jared and I talked about: (00:00) Why teams overbuild their first AI agent (02:50) Let the model cook before adding rules (03:16) Why tools matter more than better prompts (10:51) Why you should build evals after shipping (16:06) What cloud agents can do that local agents can’t (20:30) How to get one agent to manage other agents (25:39) Demo: One agent launches a team of 10 (28:03) How agents prove their work before you review it (33:18) The best tasks for agent teams to work on Thanks to our sponsors: Riverside: All-in-one AI studio for podcasts and video https://creators.riverside.com/PeterYang Linear: The AI agent platform for modern teams https://linear.app/behind-the-craft Wispr Flow: 4x faster than typing with your voice https://ref.wisprflow.ai/peteryang 📌 Get the takeaways: https://creatoreconomy.so/p/how-to-build-ai-agents-that-check-their-own-work-jared-cognition-devin Where to find Jared: X: https://x.com/imjaredz Devin: https://devin.ai Subscribe to this channel - more interviews coming soon!

暂未译制

1:02

GPT-5.6 burns through more tokens than GPT-5.5. My recommendation for everyday work: "Use GPT-5.6 Sol at medium effort. High effort or the other models burn tokens super fast. Sol at medium is a great everyday workhorse for OpenClaw, Hermes, browser tasks, and everything else." 📌 Visit my YouTube for more videos.

暂未译制

28:30

📌 Copy the AI system I use to run a one-person $1M+ business: https://www.behindthecraft.com 🤝 Subscribe to my practical AI newsletter read by 150K+ professionals: https://creatoreconomy.so ​ ​ OpenAI just made GPT 5.6 available to everyone and I’m going to answer your most burning question: Is GPT 5.6 better than Claude Fable 5? Watch my tutorial to see me test both models head-to-head across 6 real use cases. Timestamps (00:00) GPT-5.6 vs Claude Fable 5 (00:46) Compare model tiers, price, and coding performance (01:45) Create an interactive travel website (05:44) Build a 3D Star Fox-style game in one shot (09:39) Edit and publish short videos with browser use (15:10) Plan and build a mobile app feature (19:34) Get personalized life and business advice (22:17) Improve and clean up a personal AI OS (24:37) Comparing each model’s strengths and weaknesses (26:36) My daily-driver recommendation Get the written post: https://creatoreconomy.so/p/gpt-vs-claude-fable-i-tested-6-real-use-cases Where to find me: Newsletter: https://creatoreconomy.so/ X: https://x.com/petergyang LinkedIn: https://www.linkedin.com/in/petergyang/ Subscribe to this channel - more tutorials coming soon!

暂未译制

0:42

Codex不仅仅用于交付代码,它还能帮你保护日历。 来自Rohan(Codex产品经理): “我的会议数量可能比理想情况多很多,但其实很多是跟客户开的。 我得说,我的主要开发时间是从下午5点开始。 有意思的是,我甚至把Codex当成我的私人幕僚。 每周初,我会让它查看我所有的会议,合并那些能给我留出专注时段的会议,并找出哪些可以改成私信或干脆取消。 所以它确实在帮我找到专注时间。不过总的来说,我们用省下来的时间更多是和客户交流。” 📌 观看完整对话。

暂未译制